No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
The HELP hospital information system: Update 1998
Abstract
The HELP hospital information system has been operational at LDS Hospital since 1967. The system initially supported a heart catheterization laboratory and a post open heart Intensive Care Unit. Since the initial installation the system has been expanded to become an integrated hospital information system providing services with sophisticated clinical decision-support capabilities to a wide variety of clinical areas such as laboratory, nurse charting, radiology, pharmacy, etc. The HELP system is currently operational in multiple hospitals of LDS Hospital's parent health care enterprise--Intermountain Health Care (IHC). The HELP system has also been integrated into the daily operations of several other hospitals in addition to those at IHC. Evaluations of the system have shown: (1) it to be widely accepted by clinical staff; (2) computerized clinical decision-support is feasible; (3) the system provides improvements in patient care; and (4) the system has aided in providing more cost-effective patient care. Plans for making the transition from the 'function rich' HELP system to more modern hardware and software platforms are also discussed.
... In the field of image processing, many edge detection algorithms have been proposed [4,5], and some of them have been used to perform tube contour detection in some single tube measurement applications [3,6]. These kinds of methods only require the gradient information in the image to complete the edge detection work. ...
... The possibility of actual active incidents of IoMT in medical centers has been demonstrated in reports in practice. At LDS Hospital in Salt Lake City, Utah, USA, a computerized hospital information system called Health Assessment Through Logic Programming (HELP) handles 17,000 logins per day [5,6]. A survey of Electronic Medical Record (EMRD) downtime in a crowded urban emergency department from May 2016 to December 2017 in [7] found there was a total of more than 58 h of downtime, and 12 episodes of EMRD occurred during the study period with 5-h unpredictable intervals. ...
The spread of the Coronavirus (COVID-19) pandemic across countries all over the world urges governments to revolutionize the traditional medical hospitals/centers to provide sustainable and trustworthy medical services to patients under the pressure of the huge overload on the computing systems of wireless sensor networks (WSNs) for medical monitoring as well as treatment services of medical professionals. Uncertain malfunctions in any part of the medical computing infrastructure, from its power system in a remote area to the local computing systems at a smart hospital, can cause critical failures in medical monitoring services, which could lead to a fatal loss of human life in the worst case. Therefore, early design in the medical computing infrastructure’s power and computing systems needs to carefully consider the dependability characteristics, including the reliability and availability of the WSNs in smart hospitals under an uncertain outage of any part of the energy resources or failures of computing servers, especially due to software aging. In that regard, we propose reliability and availability models adopting stochastic Petri net (SPN) to quantify the impact of energy resources and server rejuvenation on the dependability of medical sensor networks. Three different availability models (A, B, and C) are developed in accordance with various operational configurations of a smart hospital’s computing infrastructure to assimilate the impact of energy resource redundancy and server rejuvenation techniques for high availability. Moreover, a comprehensive sensitivity analysis is performed to investigate the components that impose the greatest impact on the system availability. The analysis results indicate different impacts of the considered configurations on the WSN’s operational availability in smart hospitals, particularly 99.40%, 99.53%, and 99.64% for the configurations A, B, and C, respectively. This result highlights the difference of 21 h of downtime per year when comparing the worst with the best case. This study can help leverage the early design of smart hospitals considering its wireless medical sensor networks’ dependability in quality of service to cope with overloading medical services in world-wide virus pandemics.
... The implementation of existing 41 MIS often relies on an underlying sophisticated networked system associated with advanced 42 computing paradigms (e.g., cloud/fog/edge computing) via dedicated communication 43 links to remote data centers [2]. 44 Computing paradigms of MIS. 45 Traditional MIS mostly relied on mainframe computing systems as a form of central- 46 ized computing in which it plays a role of a central data repository or hub in a medical 47 data processing center placed in IT department of a hospital [3]. However, such computing 48 paradigms have inherent limitations such as scalability, maintenance, and operational 49 cost not mentioning the capabilities for business continuity and interoperability between 50 MIS across different medical organizations [4]. ...
... Practical reports 85 showed the capability of realistic MIS and operational incidences in medical centers. At 86 the LDS Hospital in Salt Lake City, Utah, USA, a computerized hospital information 87 system, called the Health Evaluation through Logical Programming (HELP), serves 88 17,000 logons per day with 99.85% up-time (13.14 hours of downtime per year) [3,11]. An 89 investigation of electronic medical record downtime (EMRD) in a busy urban emergency 90 department from May 2016 to December 2017 in [12] showed that a total of 58 hour 91 downtime with 12 episodes of EMRD occurred during the study period with approximately 92 5 hours at unpredictable intervals. ...
The aggressive waves of ongoing world-wide virus pandemics urge us to conduct further studies on the performability of local computing infrastructures at hospitals/medical centers to provide a high level of assurance and trustworthiness of medical services and treatment to patients, and to help diminish the burden and chaos of medical management and operations. Previous studies contributed tremendous progress on the dependability quantification of existing computing paradigms (e.g., cloud, grid computing) at remote data centers, while a few works investigated the performance of provided medical services under the constraints of operational availability of devices and systems at local medical centers. Therefore, it is critical to rapidly develop appropriate models to quantify the operational metrics of medical services provided and sustained by medical information systems (MIS) even before practical implementation. In this paper, we propose a comprehensive performability SRN model of an edge/fog based MIS for the performability quantification of medical data transaction and services in local hospitals or medical centers. The model elaborates different failure modes of fog nodes and their VMs under the implementation of fail-over mechanisms. Sophisticated behaviors and dependencies between the performance and availability of data transactions are elaborated in a comprehensive manner when adopting three main load-balancing techniques including: (i) probability-based, (ii) random-based and (iii) shortest queue-based approaches for medical data distribution from edge to fog layers along with/without fail-over mechanisms in the cases of component failures at two levels of fog nodes and fog virtual machines (VMs). Different performability metrics of interest are analyzed including (i) recover token rate, (ii) mean response time, (iii) drop probability, (iv) throughput, (v) queue utilization of network devices and fog nodes to assimilate the impact of load-balancing techniques and fail-over mechanisms. Discrete-event simulation results highlight the effectiveness of the combination of these for enhancing the performability of medical services provided by an MIS. Particularly, performability metrics of medical service continuity and quality are improved with fail-over mechanisms in the MIS while load balancing techniques help to enhance system performance metrics. The implementation of both load balancing techniques along with fail-over mechanisms provide better performability metrics compared to the separate cases. The harmony of the integrated strategies eventually provides the trustworthiness of medical services at a high level of performability. This study can help improve the design of MIS systems integrated with different load-balancing techniques and fail-over mechanisms to maintain continuous performance under the availability constraints of medical services with heavy computing workloads in local hospitals/medical centers, to combat with new waves of virus pandemics.
... The case analysis was aimed at capturing local discourses dealing with technological implementation as well as at comparing these local discourses with previous OV identified through content, pivot and lexicometric analysis. [Doolan et al. 2003]; [Gardner et al. 1999] LDS hospital (Salt Lake City) ...
... ]; [Gardner et al. 1999] years of programming. Today, the system has been implemented in a dozen hospitals. ...
... The notion to make use of all available (i.e. most complete) patient data for the detection of ADE and for clinical decision support is not new [32][33][34][35][36]. The HELP hospital information system (Health Evaluation Through Logical Processing), introduced in 1967, pioneered the combination of all available patient data, i.e. anamnesis, laboratory values, and medication into one single monolithic database in order to facilitate clinical decision making and the detection of ADE and ME [34]. ...
... most complete) patient data for the detection of ADE and for clinical decision support is not new [32][33][34][35][36]. The HELP hospital information system (Health Evaluation Through Logical Processing), introduced in 1967, pioneered the combination of all available patient data, i.e. anamnesis, laboratory values, and medication into one single monolithic database in order to facilitate clinical decision making and the detection of ADE and ME [34]. In clinical reality it may be difficult, however, to obtain all relevant data, stored in many distributed systems. ...
Background:
Adverse drug events (ADE) involving or not involving medication errors (ME) are common, but frequently remain undetected as such. Presently, the majority of available clinical decision support systems (CDSS) relies mostly on coded medication data for the generation of drug alerts. It was the aim of our study to identify the key types of data required for the adequate detection and classification of adverse drug events (ADE) and medication errors (ME) in patients presenting at an emergency department (ED).
Methods:
As part of a prospective study, ADE and ME were identified in 1510 patients presenting at the ED of an university teaching hospital by an interdisciplinary panel of specialists in emergency medicine, clinical pharmacology and pharmacy. For each ADE and ME the required different clinical data sources (i.e. information items such as acute clinical symptoms, underlying diseases, laboratory values or ECG) for the detection and correct classification were evaluated.
Results:
Of all 739 ADE identified 387 (52.4%), 298 (40.3%), 54 (7.3%), respectively, required one, two, or three, more information items to be detected and correctly classified. Only 68 (10.2%) of the ME were simple drug-drug interactions that could be identified based on medication data alone while 381 (57.5%), 181 (27.3%) and 33 (5.0%) of the ME required one, two or three additional information items, respectively, for detection and clinical classification.
Conclusions:
Only 10% of all ME observed in emergency patients could be identified on the basis of medication data alone. Focusing electronic decisions support on more easily available drug data alone may lead to an under-detection of clinically relevant ADE and ME.
... Despite the reluctance over the usefulness of clinical decision support systems, a number of applications and expert systems have shown great performance and some of these have been successfully used for decades in health centers, as the HELP system [8]. ...
... (1) IF Fibrinogen > 1. 8 Reference intervals should preferably be taken from laboratory which performs tests, regarding the fact that these intervals can be altered by the methods and techniques used to retrieve parameter values. ...
Clinical Decision Support Systems have the potential to reduce lack of communication and errors in diagnostic steps in primary health care. Literature reports have showed great advances in clinical decision support systems in the recent years, which have proven its usefulness in improving the quality of care. However, most of these systems are focused on specific areas of diseases. In this way, we propose a rule-based expert system, which supports clinicians in primary health care, providing a list of possible diseases regarding patient's laboratory tests results in order to assist previous diagnosis. Our system also allows storing and retrieving patient's data and the history of patient's analyses, establishing a basis for coordination between the various health care levels. A validation step and speed performance tests were made to check the quality of the system. We conclude that our system could improve clinician accuracy and speed, resulting in more efficiency and better quality of service. Finally, we propose some recommendations for further research.
... Features for functions on decision support started (see e.g. [81]). During the years, such features were continuously extended for further functions. ...
Background:
Health information systems (HIS) represent an essential part of the infrastructure for the delivery of good health care.
Objectives:
To present the author's personal views on HIS developments over the last decades and on the opportunities and priorities for future HIS developments.
Methods:
Reflecting on his views, the author identified relevant semantic dimensions, which are denoted as development paths, and searched for appropriate periods to characterize HIS development leaps.
Results:
HIS developments were divided into the periods past (1961-2016), present (2017-2022), and future (the next decades). Eight development paths for HIS were considered as being relevant to presenting the author's views: life situations related to health care, entities for health care, health care facilities, settings of health care, data to be processed, features for functions, architectures of HIS, and management of HIS. For each of these paths, the past and present states as well as challenges and opportunities for future HIS developments were outlined.
Discussion and conclusions:
The presented views on HIS developments and the selected development paths and periods are by nature subjective 'avant la lettre'. The views were, however, formed over almost half a century during which the author has been engaged with HIS developments, and thus may be worth reporting and discussion. If past is prologue, the tremendous HIS developments in the past and in the present may predict a similar development intensity in the future. Present HIS are significantly better than HIS of the past, however they leave room for continued improvement with an end of HIS developments far from sight.
... Hospitals at all levels have spent a great deal of money in the installation and development of HIS with the full backing of the government. Secondary and tertiary hospitals are now widely accepted, resulting in vastly improved medical care [1]. ...
Hospital information system (HIS) can provide a full range of information support for various hospital business activities and information collection, processing, and transmission, helping medical service providers. And HIS can reduce medical service costs and improve work efficiency, greatly reducing errors in diagnosis and treatment. Although the advantages of using the HIS are obvious, there are still some challenges in its use, the most prominent being how to make the medical staff use HIS effectively. Based on this background, this paper uses machine learning (ML) technology to predict and analyze the satisfaction of HIS use in hospitals and completes the following work: firstly, introduce the situation and development trend of HIS construction at home and abroad and provide theoretical basis for model design. The related development technologies are discussed and studied in detail. Second, the ML algorithm is used to provide a prediction strategy. The support vector machine (SVM) can handle small data sets well, and this study applies the AdaBoost technique to improve the model’s generalization ability and accuracy. Lastly, a diversity metric is included to guarantee that the basic learner has good variety in order to increase the algorithm’s performance. Accuracy rates may reach more than 95% in the case of tiny data sets, according to the self-built data set used for testing. This proves the superiority of the model proposed in this paper.
... HELP included several CDS capabilities 22 and multiple inpatient functions. 23 An outpatient longitudinal version called HELP-2 was latter developed to support outpatient services. 24 HELP-2 was the result of a direct partnership with 3M to develop a commercial product. ...
Objectives This study aimed to understand if and how homegrown electronic health record (EHR) systems are used in the post–Meaningful Use (MU) era according to the experience of six traditional EHR developers.
Methods We invited informatics leaders from a convenience sample of six health care organizations that have recently replaced their long used homegrown systems with commercial EHRs. Participants were asked to complete a written questionnaire with open-ended questions designed to explore if and how their homegrown system(s) is being used and maintained after adoption of a commercial EHR. We used snowball sampling to identify other potential respondents and institutions.
Results Participants from all six organizations included in our initial sample completed the questionnaire and provided referrals to four other organizations; from these, two did not respond to our invitations and two had not yet replaced their system and were excluded. Two organizations (Columbia University and University of Alabama at Birmingham) still use their homegrown system for direct patient care and as a downtime system. Four organizations (Intermountain Healthcare, Partners Healthcare, Regenstrief Institute, and Vanderbilt University) kept their systems primarily to access historical data. All organizations reported the need to continue to develop or maintain local applications despite having adopted a commercial EHR. The most common applications developed include display and visualization tools and clinical decision support systems.
Conclusion Homegrown EHR systems continue to be used for different purposes according to the experience of six traditional homegrown EHR developers. The annual cost to maintain these systems varies from $21,000 to over 1 million. The collective experience of these organizations indicates that commercial EHRs have not been able to provide all functionality needed for patient care and local applications are often developed for multiple purposes, which presents opportunities for future research and EHR development.
... First clinical decision support system known as Health Evaluation of Logical Processing was developed to support clinical operations. The system helped doctors to identify cardiac contraction University of Utah, 3M and Latter-Day Saints Hospital 1967 based on a patient's test results' analysis and to select an appropriate medication for infectious disease cases [17]. ...
Background:
Over the last century, disruptive incidents in clinical and biomedical research fields have yielded a tremendous change in the health data management system. This is due to the breakthrough in the medical field and the need for big data analytics and the Internet of Things (IoT) to be incorporated in a real-time smart health information management system. In addition, the requirements of patient care have evolved over time, allowing for more accurate prognoses and diagnoses. In this paper, we discuss the temporal evolution of the health data management systems and capture the requirements that led to the development of a given system over a certain period of time. Consequently, we provide insights into those systems and give suggestions and research directions on how they can be improved for a better health care system.
Objective:
This study aimed to show that there is a need for a secure and efficient health data management system that will allow physicians and patients to update decentralized medical records and to analyze the medical data for supporting more precise diagnoses, prognoses, and public insights. Limitations of existing health data management systems are analyzed.
Methods:
To study the evolution and requirements of health data management systems over the years, a search was conducted to obtain research articles and information on medical lawsuits, health regulations, and acts. These materials were obtained from the Institute of Electrical and Electronics Engineers, the Association for Computing Machinery, Elsevier, MEDLINE, PubMed databases, Scopus, and Web of Science.
Results:
The health data management system has gone into disruptive transformation over the years from paper to computer, Web, cloud, IoT, big data analytics, and finally to the blockchain. The requirements of a health data management system revealed from the evolving definitions of medical records and their management are (1) medical record data, (2) real-time data access, (3) patient participation, (4) data sharing, (5) data security, (6) patient identity privacy, and (7) public insights. This paper reviews the health data management systems based on these 7 requirements across studies conducted over the years. To our knowledge, this is the first analysis of the temporal evolution of health data management systems giving insights on the system requirements for better health care.
Conclusions:
There is a need for a comprehensive real-time health data management system that allows physicians, patients, and external users to input their medical and lifestyle data into the system. The incorporation of big data analytics will aid in better prognosis or diagnosis of the diseases and the prediction of diseases. The prediction results will help in the development of an effective prevention plan.
... In this Section, we study how placement decisions of SecQL affect performance in a realistic case study. We implemented a simple hospital IT system (the query in Section 2 is from this case study) based on the well-known HELP hospital information system (Gardner et al. 1999), originally developed at the Department of Medical Informatics, University of Utah, and in routine use at the Hospitals of Intermountain Health Care (IHC) in Utah, USA (OpenClinical 2004). To demonstrate the effect of pushing selections to table nodes, the query is extended with a selection to filter tuples in PersonDB. ...
Distributed query processing is an effective means for processing large amounts of data. To abstract from the technicalities of distributed systems, algorithms for operator placement automatically distribute sequential data queries over the available processing units. However, current algorithms for operator placement focus on performance and ignore privacy concerns that arise when handling sensitive data.
We present a new methodology for privacy-aware operator placement that both prevents leakage of sensitive information and improves performance. Crucially, our approach is based on an information-flow type system for data queries to reason about the sensitivity of query subcomputations. Our solution unfolds in two phases. First, placement space reduction generates deployment candidates based on privacy constraints using a syntax-directed transformation driven by the information-flow type system. Second, constraint solving selects the best placement among the candidates based on a cost model that maximizes performance. We verify that our algorithm preserves the sequential behavior of queries and prevents leakage of sensitive data. We implemented the type system and placement algorithm for a new query language SecQL and demonstrate significant performance improvements in benchmarks.
... The approach of this work is to introduce the less-radical principles of Business Process Management (BPM) [Becker et al. 2003;van der Aalst et al. 2003] to healthcare and employ those principles to existing medical information systems [Borst et al. 1999;Gardner et al. 1999;Teich et al. 1999]. We performed a case study to show how BPM and information technology contribute to lower the frequency of human errors in healthcare [Institute of Medicine 2001; Kohn et al. 2000]. ...
... These were followed some years later by attempts to evolve from these administrative, hospital-centric systems, to patient-centric systems integrating clinical components into administrative and financial systems. Some of the early efforts included the work of Larry Weed on the Problem-Oriented Medical Record (POMR) at the University of Vermont in the early 1970s [3] and the work of Homer Warner on the HELP System at the LDS Hospital in Utah at around the same time [4]. ...
Health informatics has benefitted from the development of Info-Communications Technology (ICT) over the last fifty years. Advances in ICT in healthcare have now started to spur advances in Data Technology as hospital information systems, electronic health and medical records, mobile devices, social media and Internet Of Things (IOT) are making a substantial impact on the generation of data. It is timely for healthcare institutions to recognize data as a corporate asset and promote a data-driven culture within the institution. It is both strategic and timely for IMIA, as an international organization in health informatics, to take the lead to promote a data-driven culture in healthcare organizations. This can be achieved by expanding the terms of reference of its existing Working Group on Data Mining and Big Data Analysis to include (1) data analytics with special reference to healthcare, (2) big data tools and solutions, (3) bridging information technology and data technology and (4) data quality issues and challenges.
... As can be largely explained by Rogers' theory of the diffusion of innovations [13], "early adopters" of EHRs were mostly enthusiastic and proud to be a part of a new, innovative, and technological health care revolution. A number of these pioneering EHR users were working in academic institutions with home-grown EHRs that they developed and improved upon internally [14,15,16,17]. Once enough people or organizations have adopted an innovation, adoption from then on becomes self-sustaining. ...
Although the health information technology industry has made considerable progress in the design, development, implementation, and use of electronic health records (EHRs), the lofty expectations of the early pioneers have not been met. In 2006, the Provider Order Entry Team at Oregon Health & Science University described a set of unintended adverse consequences (UACs), or unpredictable, emergent problems associated with computer-based provider order entry implementation, use, and maintenance. Many of these originally identified UACs have not been completely addressed or alleviated, some have evolved over time, and some new ones have emerged as EHRs became more widely available. The rapid increase in the adoption of EHRs, coupled with the changes in the types and attitudes of clinical users, has led to several new UACs, specifically: complete clinical information unavailable at the point of care; lack of innovations to improve system usability leading to frustrating user experiences; inadvertent disclosure of large amounts of patient-specific information; increased focus on computer-based quality measurement negatively affecting clinical workflows and patient-provider interactions; information overload from marginally useful computer-generated data; and a decline in the development and use of internally-developed EHRs. While each of these new UACs poses significant challenges to EHR developers and users alike, they also offer many opportunities. The challenge for clinical informatics researchers is to continue to refine our current systems while exploring new methods of overcoming these challenges and developing innovations to improve EHR interoperability, usability, security, functionality, clinical quality measurement, and information summarization and display.
... At the time of this paper, the term 'Information' is frequently replaced with the word "Informatics". From the 1970s to the 1990s, hospitals and large ambulatory care practices with computing systems integral to operations, had remarkable successes leveraging health IT [38][39][40][41][42][43][44][45][46][47]. The National Library of Medicine funded post-doctoral fellowships in many of these early adopter sites [48,49]. ...
... The HELP system group produced many innovative clinical applications, e.g., for optimizing antibiotics use [53,54], detecting and preventing adverse drug events [55,56], and computerized methods to wean patients from mechanical ventilators [57,58]. The HELP system was transferred to the highly reliable Tandem computers hardware to improve its availability and provide greater computing capabilities [59,60]. Around 2002, Paul Clayton and colleagues updated and modernized the HELP system to a system designated HELP II [61]. ...
Objectives:
To review the history of clinical information systems over the past twenty-five years and project anticipated changes to those systems over the next twenty-five years.
Methods:
Over 250 Medline references about clinical information systems, quality of patient care, and patient safety were reviewed. Books, Web resources, and the author's personal experience with developing the HELP system were also used.
Results:
There have been dramatic improvements in the use and acceptance of clinical computing systems and Electronic Health Records (EHRs), especially in the United States. Although there are still challenges with the implementation of such systems, the rate of progress has been remarkable. Over the next twenty-five years, there will remain many important opportunities and challenges. These opportunities include understanding complex clinical computing issues that must be studied, understood and optimized. Dramatic improvements in quality of care and patient safety must be anticipated as a result of the use of clinical information systems. These improvements will result from a closer involvement of clinical informaticians in the optimization of patient care processes.
Conclusions:
Clinical information systems and computerized clinical decision support have made contributions to medicine in the past. Therefore, by using better medical knowledge, optimized clinical information systems, and computerized clinical decision, we will enable dramatic improvements in both the quality and safety of patient care in the next twenty-five years.
... HELP was instrumental in demonstrating the ability of CDS to reduce medical errors and save money with high levels of user acceptance. For example, the antibiotic prescribing features were linked to a 58 % reduction in per-patient antibiotic costs and a 30 % decrease in antibioticrelated adverse events [ 16 ]. ...
Clinical decision support (CDS) systems provide clinicians and patients with intelligently filtered information at appropriate times to foster better health processes, better individual patient care, and better population health. This chapter provides a brief history of CDS systems, reviews best practices for implementing CDS, describes the knowledge management cycle, and highlights unintended consequences of CDS coupled with quality, safety, ethical, legal, and regulatory concerns. Emerging trends include the use of CDS to enable population health management and to conduct clinical trials.
... At the time of this paper, the term 'Information' is frequently replaced with the word "Informatics". From the 1970s to the 1990s, hospitals and large ambulatory care practices with computing systems integral to operations, had remarkable successes leveraging health IT [38][39][40][41][42][43][44][45][46][47]. The National Library of Medicine funded post-doctoral fellowships in many of these early adopter sites [48,49]. ...
Introduction:
The emerging operational role of the "Chief Clinical Informatics Officer" (CCIO) remains heterogeneous with individuals deriving from a variety of clinical settings and backgrounds. The CCIO is defined in title, responsibility, and scope of practice by local organizations. The term encompasses the more commonly used Chief Medical Informatics Officer (CMIO) and Chief Nursing Informatics Officer (CNIO) as well as the rarely used Chief Pharmacy Informatics Officer (CPIO) and Chief Dental Informatics Officer (CDIO).
Background:
The American Medical Informatics Association (AMIA) identified a need to better delineate the knowledge, education, skillsets, and operational scope of the CCIO in an attempt to address the challenges surrounding the professional development and the hiring processes of CCIOs.
Discussion:
An AMIA task force developed knowledge, education, and operational skillset recommendations for CCIOs focusing on the common core aspect and describing individual differences based on Clinical Informatics focus. The task force concluded that while the role of the CCIO currently is diverse, a growing body of Clinical Informatics and increasing certification efforts are resulting in increased homogeneity. The task force advised that 1.) To achieve a predictable and desirable skillset, the CCIO must complete clearly defined and specified Clinical Informatics education and training. 2.) Future education and training must reflect the changing body of knowledge and must be guided by changing day-to-day informatics challenges.
Conclusion:
A better defined and specified education and skillset for all CCIO positions will motivate the CCIO workforce and empower them to perform the job of a 21st century CCIO. Formally educated and trained CCIOs will provide a competitive advantage to their respective enterprise by fully utilizing the power of Informatics science.
... The developments of Expert Systems (ESs) have drawn much attention of the research community in the last few decades. The possibility of expert's systems has additionally been generally acknowledged in clinical environment, beginning from a straightforward database inquiry to complex treatment proposal[1]. The logical writing gives the significant wellspring of learning joined by nearby and rehearsed based proof. ...
Offline clinical guidelines are typically designed to integrate a clinical knowledge base, patient data and an inference engine to generate case specific advice. In this regard, offline clinical guidelines are still popular among the healthcare professionals for updating and support of clinical guidelines. Although their current format and development process have several limitations, these could be improved with artificial intelligence approaches such as expert systems/decision support systems. This paper first, presents up to date critical review of existing clinical expert systems namely AAPHelpm, MYCIN, EMYCIN, PIP, GLIF and PROforma. Additionally, an analysis is performed to evaluate all these fundamental clinical expert systems. Finally, this paper presents the proposed research and development of a clinical expert system to help healthcare professionals for treatment.
... Other systems, without extensive decision support models, have successfully delivered clinical alerts beyond those available via bedside physiologic monitors [27][28][29], sampled and archived dense physiologic data to support clinical research [30][31][32][33][34], or made medical monitor data available remotely [35,36]. Gardner and colleagues demonstrated many of these advancements as early as 1972 with the University of Utah's HELP system [37], and commercial solutions are beginning to offer many of these capabilities. The Physionet project [38] provides a rich on-line collection of physiological datasets, algorithms, and other resources. ...
SIMON (Signal Interpretation and MONitoring) continuously collects and processes bedside medical device data. As of December 2009, SIMON has monitored over 7,630 trauma intensive care unit (TICU) patients, representing approximately 731,000 hours of continuous monitoring, and is currently operational on all TICU beds at Vanderbilt University Medical Center. Parameters captured include heart rate, blood pressures, oxygen saturations, cardiac function variables, intracranial and cerebral perfusion pressures, and EKG waveforms. This repository supports research to identify "new vital signs" based on features of patient physiology observable through dense data capture and analysis, with the goal of improving predictions of patient status. SIMON's alerting and reporting capabilities include web display, sentinel event notification, and daily summary reports of traditional and new vital sign statistics. This allows discoveries to be rapidly tested and implemented in a working clinical environment. The work details SIMON's technology and corresponding design requirements to realize the value of dense physiologic data in critical care.
A panel sponsored by the American College of Medical Informatics (ACMI) at the 2021 AMIA Symposium addressed the provocative question: “Are Electronic Health Records dumbing down clinicians?” After reviewing electronic health record (EHR) development and evolution, the panel discussed how EHR use can impair care delivery. Both suboptimal functionality during EHR use and longer-term effects outside of EHR use can reduce clinicians’ efficiencies, reasoning abilities, and knowledge. Panel members explored potential solutions to problems discussed. Progress will require significant engagement from clinician-users, educators, health systems, commercial vendors, regulators, and policy makers. Future EHR systems must become more user-focused and scalable and enable providers to work smarter to deliver improved care.
Rising aggressive virus pandemics urge to conduct studies on dependability and security of modern computing systems to secure autonomous and continuous operations of healthcare systems. In that regard, we propose to quantify dependability and security measures of an Internet of Medical Things (IoMT)infrastructure relied on an integrated physical architecture of Cloud/Fog/Edge (CFE) computing paradigms in this paper. We propose a reliability/availability quantification methodology for the IoMT infrastructure using a hierarchical model of three levels:(i) fault tree (FT) of overall IoMT infrastructure consisting of CFE member systems, (ii) FT of subsystems within CFE member systems, and (iii) continuous time Markov chain (CTMC) models of components/devices in the subsystems. We incorporate a number of failure modes for the underlying subsystems including Mandel-bug related failures and non-Mandel bugs related failure, as well as failures due to cyber-security attacks on software subsystems. Five case-studies of configuration alternation and four operational scenarios of the IoMT infrastructure are considered to comprehend the dependability characteristics of the IoMT physical infrastructure. The metrics of interest include reliability over time, steady state availability (SSA), sensitivity of SSA wrt. selected Mean Time to Failure - Equivalent (MTTFeq) and Mean Time to Recovery -Equivalent (MTTReq) and sensitivity of SSA wrt. frequencies of cyber-security attacks on software subsystems. Analysis results help comprehend operational behaviors and properties of a typical IoMT infrastructure. The findings of this study can improve the design and implementation of real-world IoMT infrastructures consisting of cloud, fog and edge computing paradigms.
In this chapter, we discuss the use of computers in collecting, displaying, storing, and interpreting clinical data, making therapeutic recommendations, and alarming and alerting. In the past, most monitoring data (called vital signs) were in the form of HR and respiratory rate, blood pressure (BP), and body temperature. However, today’s ICU monitoring systems are able integrate data from bedside monitors and devices, as well as data from many sources outside the ICU. Although the material presented here deals primarily with patients who are in ICUs, the general principles and techniques are also applicable to other hospitalized patients and electronic medical records (EMRs). Patient monitoring is performed extensively for diagnostic purposes in the emergency department or for therapeutic purposes in the OR. Techniques that initially were only used in the ICU such as bedside monitors are now used routinely on general hospital wards and in some situations even by patients in their homes.
The concept of Big Data is popular in a variety of domains. The purpose of this review was to summarize the features, applications, analysis approaches, and challenges of Big Data in health care. Big Data in health care has its own features, such as heterogeneity, incompleteness, timeliness and longevity, privacy, and ownership. These features bring a series of challenges for data storage, mining, and sharing to promote health-related research. To deal with these challenges, analysis approaches focusing on Big Data in health care need to be developed and laws and regulations for making use of Big Data in health care need to be enacted. From a patient perspective, application of Big Data analysis could bring about improved treatment and lower costs. In addition to patients, government, hospitals, and research institutions could also benefit from the Big Data in health care.
To apply Artificial Intelligence (AI), Machine Learning (ML) and Machine Reasoning (MR) in health informatics are often challenging as they comprise with multivariate information coming from heterogeneous sources e.g. sensor signals, text, etc. This book chapter presents the research development of AI, ML and MR as applications in health informatics. Five case studies on health informatics have been discussed and presented as (1) advanced Parkinson’s disease, (2) stress management, (3) postoperative pain treatment, (4) driver monitoring, and (5) remote health monitoring. Here, the challenges, solutions, models, results, limitations are discussed with future wishes.
Health informatics (HI) is an increasingly important discipline to healthcare. HI is the scientific field concerned with improving how information in healthcare is captured, used, and managed. Developments in HI have streamlined and improved the efficacy of health service delivery, ranging from administration to bedside care to telehealth. Anecdotally, one observes that the paradigm of health domain experts working with information technology (IT) domain experts still produces health information systems that fail or do not work adequately; thus, there is a need for individuals knowledgeable in both information methods/tools and health. HI is a very broad discipline, but demonstrates features of a profession that set it apart from conventional IT or computer science; one notes different aspects of knowledge and skill and an ethos that is more aligned with that of health. This chapter provides an overview of HI, introducing the concepts of HI, its history, and how it relates to the skills, knowledge and attitudes of the emerging HI professional. HI is changing how healthcare is delivered and HI professionals are a part of that process. There are a range of roles these individuals fill, with some overlap with more established positions, such as health information managers. Despite the emergence of the HI profession, there are hurdles to overcome in terms of consistent education and registration or accreditation/credentialing.
Healthcare IT (HIT) has failed to live up to its promise in the United States. HIT solutions and decisions need to be evidence based and standardized. Interventional informatics is ideally positioned to provide evidence based and standardized solutions in the enterprise (aka, the medical center) which includes all or some combination of hospital(s), hospital based-practices, enterprise owned offsite medical practices, faculty practice and a medical school. For purposes of this chapter, interventional informatics is defined as applied medical or clinical informatics with an emphasis on an active interventional role in the enterprise. A department of interventional informatics, which integrates the science of informatics into daily operations, should become a standard part of any 21st century medical center in the United States. The objectives of this chapter are to: review and summarize the promise and challenge of IT in healthcare; define healthcare IT; review the legacy of IT in healthcare; compare and contrast IT in healthcare with that of other industries; become familiar with evidence based IT: Medical informatics; differentiate medical informatics from IT in healthcare; distinguish medical, clinical, and interventional informatics; justify the need for operational departments of interventional informatics.
The concept of Big Data is popular in a variety of domains. The purpose of this review was to summarize the features, applications, analysis approaches, and challenges of Big Data in health care. Big Data in health care has its own features, such as heterogeneity, incompleteness, timeliness and longevity, privacy, and ownership. These features bring a series of challenges for data storage, mining, and sharing to promote health-related research. To deal with these challenges, analysis approaches focusing on Big Data in health care need to be developed and laws and regulations for making use of Big Data in health care need to be enacted. From a patient perspective, application of Big Data analysis could bring about improved treatment and lower costs. In addition to patients, government, hospitals, and research institutions could also benefit from the Big Data in health care.
Computer-Interpretable Guidelines (CIGs) are machine readable representations of Clinical Practice Guidelines (CPGs) that serve as the knowledge base in many knowledge-based systems oriented towards clinical decision support. Herein we disclose a comprehensive CIG representation model based on Web Ontology Language (OWL) along with its main components. Additionally, we present results revealing the expressiveness of the model regarding a selected set of CPGs. The CIG model then serves as the basis of an architecture for an execution system that is able to manage incomplete information regarding the state of a patient through Speculative Computation. The architecture allows for the generation of clinical scenarios when there is missing information for clinical parameters.
After reading this chapter, you should be able to answer these questions
1.
What is patient monitoring, and why is it used?
2.
What patient parameters do bedside physiological monitors provide?
3.
What are the major problems with acquisition and presentation of monitoring parameters?
4.
In addition to bedside physiological parameters, what other information is fundamental to the care of acutely ill patients?
5.
How are patient care protocols used to enhance the care of critically ill patients?
6.
Why is real-time computerized decision support potentially more beneficial than monthly or quarterly quality of care reporting?
7.
What technical and social factors must be considered when implementing real-time data acquisition and decision support systems?
Most pediatric healthcare providers use an electronic health record (EHR) system in both office-based and hospital-based practice in the United States. While some pediatric-specific EHR systems exist for the office-based market, the majority of EHR systems used in the care of children are designed for general use across all specialties. Pediatric providers have succeeded in influencing the development of these systems to serve the special needs of child health (e.g., immunization management, dosing by body weight, growth monitoring, developmental assessment), but the pediatric community continues to press for further refinement of these systems to meet the advanced needs of pediatric specialties. These clinical systems are typically integrated with administrative (scheduling, billing, registration, etc.) systems, and the output of both types of systems are often used in research. A large portion of the data from the clinical side remains in free-text form, which raises challenges to the use of these data in research. In this chapter, we discuss workflows with data implications of special importance in pediatrics. We will also summarize efforts to create standard quality measures and the rise in EHR-based registry systems.
In recent years, the general IT community has been moving from a monolithic-type of software architecture to a service-oriented architecture that involves developing systems using independent, well-defined software services that are then coordinated to meet business needs. The main benefit of a service-oriented architecture is the ability to more easily and more rapidly implement needed business capabilities using independent software services. While lagging behind many industries, the healthcare industry has been moving towards a service-oriented architecture, including in the space of clinical decision support. In this chapter, we describe notable efforts in service-oriented clinical decision support and speculate on its potential evolution in the future.
Pediatric providers use electronic health record systems to review patient information, to document care, to order clinical interventions, and to perform related administrative tasks. All of these activities create data that might be useful in research, although research is seldom the objective of EHR-related data entry. Providers may use other information systems (e.g., specialized systems for analyzing electrocardiograms), but the EHR is the central application for clinical and administrative clinical activities. While there are a few EHR systems designed specifically for care of pediatric patients, most pediatric providers adopt general-purpose EHRs that must be customized for specialized pediatric environments. In this chapter we outline the special functional requirements of EHRs (e.g., growth monitoring, medication dosing, and immunization management), the relative difficulty of meeting these requirements with EHRs that are currently available in the marketplace, and current adoption trends. We discuss workflows that present special challenges to EHR implementation. We discuss the typical workflow phenomena that affect the use of data for research and other secondary uses. We also discuss special aspects of terminology systems employed by EHRs that have implications for pediatric usability. Lastly, we address special issues in the use of EHR data for the extraction of care quality measures.
Primary medical record databases are data repositories constructed for direct health care delivery to process clinical information, to carry out the special functions for which the data have been collected, integrated, and stored by health-care providers for the direct care of their patients. Medical record data are collected in a variety of medical sites and for a variety of purposes, including helping physicians in making decisions for the diagnosis and treatment of patients, helping nurses in their patient care functions, and helping technical personnel in their clinical support services. The great utility of medical databases resides in their capacity for storing huge volumes of data, and for their ability to help users to search, retrieve, and analyze information on individual patients relevant to their clinical needs. Michalski et al. (1982) added that medical databases were also constructed, in addition to keeping track of clinical data, to be used to study and learn more about the phenomena that produced the data.
At the end of this lecture, you:
In the 1960s, large hospital systems began to acquire mainframe computers, primarily for business and administrative functions. In the 1970s, lower-cost, minicomputers enabled placement of smaller, special purpose clinical application systems in various hospital departments. Early time-sharing applications used display terminals located at nursing stations. In the 1960s and 1970s, a small number of pioneering institutions, many of them academic teaching hospitals with federal funding, developed their own hospital information systems (HISs). Vendors then acquired and marketed some of the successful academic prototypes. In the 1980s, widespread availability of local area networks fostered development of large HISs with advanced database management capabilities, generally using a mix of large mini- and microcomputers linked to large numbers of clinical workstations and bedside terminals. When federal funding for HIS development diminished in the mid-1990s, academic centers decreased, and commercial vendors increased their system development efforts. Interoperability became a main design requirement for HISs and for electronic patient record (EPR) systems. Beyond 2010, open system architectures and interconnection standards hold promise for full interchange of information between multi-vendor HISs and EPR systems and their related subsystems.
The clinical laboratory (LAB) was an early adopter of computer technology, beginning with the chemistry and hematology laboratories, which had similar information processing requirements. LAB systems in the early 1960s were primarily offline, batch-oriented systems that used punched cards for data transfer to the hospital mainframe. The advent of minicomputers in the 1970s caused a rapid surge in the development of LAB systems that supported online processing of data from automated laboratory instruments. In the 1980s, LAB systems increasingly employed minicomputers to integrate data into a common database and satisfy functional requirements, including programs for quality control, reference values, trend analyses, graphical presentation, online test interpretations, and clinical guidelines. By 1987 about 20 % of US hospitals had computer links between their LAB systems and their hospital information systems and affiliated outpatient information systems. In the 1990s, LAB systems began using client-server architecture with networked workstations, and most hospitals had a variety of specialized clinical support information systems interconnected to form a medical information system with a distributed database of clinical data that constituted the electronic patient record. By the 2000s, several hundred different clinical tests were routinely available (there had been only a few dozen in the 1950s). The need for more sophisticated and powerful LAB systems has largely been met by commercially available standalone laboratory information systems (LIS); however, there is now increasing pressure to replace these products with the lab-system functionality of the enterprise-wide integrated electronic health record system, for which there is little reported experience.
Changing economics gave rise to the development of Multi-Hospital Information Systems (MHISs) serving systems of three or more hospitals and their associated services. Functional and technical capabilities, including translational databases, were developed to support the exchange and integration of multiple forms of information within and among facilities. Early examples in the private sector included MHISs at The Sisters of the Third Order of St. Francis (1960s) and Intermountain Health Care (1970s), and in mental health hospitals (1960s–1970s). In the federal sector, the U.S. Public Health Service and Indian Health Services began to develop MHISs in the 1970s. Efforts to use automation to support services started in the 1960s at the Department of Defense, which used a top down approach, and Veterans Administration, which worked bottom up; the complicated histories of these developments spanned decades. Also in the MHIS marketplace were commercial entities, such as IBM, McDonnell Douglas (later Technicon), and many others. By the end of the 1980s the Institute of Medicine deemed that MHISs had reached sufficient maturity to warrant study, published as The Computer-based Patient Record: An Essential Technology for Patient Care in 1991. The development of functioning information technology for health systems had hit a plateau with the focus now shifting sharply toward informatics, e.g., the use of information and communications technology to produce safer, higher quality care for individuals and populations.
Operating within a larger medical information system (MIS), clinical support information systems (CSISs) process the specialized subsystem information used in support of the direct care of patients. Most of these CSISs were developed as stand-alone systems. This chapter highlights the early efforts to combine data from disparate departmental data systems into more “integrated ones” that support the full spectrum of data management needs of multi-hospital and ambulatory health systems. In the 1960s and 1970s, institutions incorporated clinical laboratory and medication subsystems into their MISs; more subsystems were added (pathology, imaging, etc.); and systems with integrated CSIS were developed for ambulatory care settings. Despite all the progress made over the past 40 years, two key challenges remain unsolved: first is the lack of data interoperability among myriad systems; second is the lack of a useful point of care system. Both threaten to make the clinician’s work harder; overcoming them is key to transforming the health care system.
Health informatics (HI) is an increasingly important discipline to healthcare. HI is the scientific field concerned with improving how information in healthcare is captured, used, and managed. Developments in HI have streamlined and improved the efficacy of health service delivery, ranging from administration to bedside care to telehealth. Anecdotally, one observes that the paradigm of health domain experts working with information technology (IT) domain experts still produces health information systems that fail or do not work adequately; thus, there is a need for individuals knowledgeable in both information methods/tools and health. HI is a very broad discipline, but demonstrates features of a profession that set it apart from conventional IT or computer science; one notes different aspects of knowledge and skill and an ethos that is more aligned with that of health. This chapter provides an overview of HI, introducing the concepts of HI, its history, and how it relates to the skills, knowledge and attitudes of the emerging HI professional. HI is changing how healthcare is delivered and HI professionals are a part of that process. There are a range of roles these individuals fill, with some overlap with more established positions, such as health information managers. Despite the emergence of the HI profession, there are hurdles to overcome in terms of consistent education and registration or accreditation/credentialing.
Machines that support highly complex decisions of doctors have been a reality for almost half a century. In the 1950s, computer-supported medical diagnostic systems started with “punched cards in a shoe box”. In the 1960s and 1970s medicine was, to a certain extent, transformed into a quantitative science by intensive interdisciplinary research collaborations of experts from medicine, mathematics and electrical engineering; This was followed by a second shift in research on machine support of medical decisions from numerical probabilistic to knowledge based approaches. Solutions of the later form came to be known as (medical) expert systems, knowledge based systems research or Artificial Intelligence in Medicine. With growing complexity of machines physician patient interaction can be supported in various ways. This includes not only diagnosis and therapy options but could also include ethical problems like end-of-life decisions. Here questions of shared responsibility need to be answered: should machine or human have the last say? This chapter explores the question of shared responsibility mainly in ethical decision making in medicine. After addressing the historical development of decision support systems in medicine the demands of users on such systems are analyzed. Then the special structure of ethical dilemmas is explored. Finally, this chapter discusses the question how decision support systems can be used in ethical dilemma situations in medicine and how this translates into shared responsibility.
With the growth in the number of elderly and people with chronic diseases, the number of hospital services will need to increase in the near future. With myriad of information technologies utilized daily and crucial information-sharing tasks performed at hospitals, understanding the relationship between task performance and information system has become a critical topic. This research explored the resource pooling of hospital management and considered a computed tomography (CT) patient-referral mechanism between two hospitals using the information system theory framework of Task-Technology Fit (TTF) model. The TTF model could be used to assess the 'match' between the task and technology characteristics. The patient-referral process involved an integrated information framework consisting of a hospital information system (HIS), radiology information system (RIS), and picture archiving and communication system (PACS). A formal interview was conducted with the director of the case image center on the applicable characteristics of TTF model. Next, the Icam DEFinition (IDEF0) method was utilized to depict the As-Is and To-Be models for CT patient-referral medical operational processes. Further, the study used the 'leagility' concept to remove non-value-added activities and increase the agility of hospitals. The results indicated that hospital information systems could support the CT patient-referral mechanism, increase hospital performance, reduce patient wait time, and enhance the quality of care for patients.
Medical decision-making requires the clinician to apply accumulated knowledge to a specific amount of patient information to produce a result that may be a diagnosis, prognosis, course of therapy, or selection of further tests. Too often, the decisions are based on limited knowledge, the information is incomplete or imperfect, and the decisions must be made during a limited period of time. The improvement in health care quality and safety expected by the public will depend in part on appropriate use of computerized applications. LDS Hospital in Salt Lake City, Utah, has been developing decision support applications on the Health Evaluation through Logical Processing (HELP) System for over 30 years. The system was designed to be an electronic health record with decision support and research capabilities. Numerous other applications have been developed that use different levels and methods of decision support to improve the patient care process and the quality of patient care. Many of these applications have been scientifically evaluated to measure their impact on patient care. This chapter discusses a number of these applications as examples to demonstrate different methods of design, development, implementation, and evaluation along with what has been worked, not worked, and why. The HELP System architecture and capabilities, which are needed to develop and run the applications, have been described and highlighted within the examples.
Objectives: Adverse drug reactions (ADRs) leading to hospitalisation or occurring during hospital stay contribute significantly to patient morbidity and mortality as well as representing an additional cost for healthcare systems. The aim of this study was to provide data about the type and incidence of ADRs in a neurological department and to compare two different methodological approaches to collecting information on ADRs.
Methods: The two methods used were intensified surveillance of neurological wards by daily ward rounds and computer-assisted screening for ADRs by means of pathological laboratory parameters.
Results: Of admissions to the neurological department, 2.7% were caused by an ADR and 18.7% of patients experienced at least one ADR during hospitalisation. The positive predictive values of pathological laboratory parameters ranged between 0% (eosinophil count) and 100% for increased drug serum concentrations and international normalised ratio, i.e. the latter were always accompanied by a clinically relevant ADR. However, only half of all ADR could be detected by pathological laboratory parameters, the sensitivity of this method came to 45.1% with a specificity of 78.9%.
Conclusion: Similar to departments of internal medicine, a high number of ADRs occur on neurological wards. The predominant ADRs were those typical of neurotropic medications such as dyskinesia and increased sedation. Due to the age of the patients involved, cardiovascular co-medication is often prescribed and represents an additional risk factor for ADRs. By measuring pathological laboratory parameters the majority of ADRs could not be detected in neurological patients.
Three years ago Intermountain Healthcare made the decision to participate in the Medicare and Medicaid Electronic Heath Record (EHR) Incentive Program which required that hospitals and providers use a certified EHR in a meaningful way. At that time, the barriers to enhance our home grown system, and change clinician workflows were numerous and large. This paper describes the time and effort required to enhance our legacy systems in order to pass certification, including filling 47 gaps in (EHR) functionality. We also describe the processes and resources that resulted in successful changes to many clinical workflows required by clinicians to meet meaningful use requirements. In 2011 we set meaningful use targets of 75% of employed physicians and 75% of our hospitals to meet Stage 1 of meaningful use by 2013. By the end of 2013, 87% of 696 employed eligible professionals and 100% of 22 Intermountain hospitals had successfully attested for Stage 1. This paper describes documented and perceived costs to Intermountain including time, effort, resources, postponement of other projects, as well as documented and perceived benefits of attainment of meaningful use.
Hospital-acquired infections (HAIs) and the selection of empiric antibiotics continue to create problems for physicians. We developed computerized methods to identify patients at high risk of acquiring HAIs. Data from 3,151 patients with HAIs were compared with 3,152 control patients. Logistic regression was used to create a model to predict HAIs. Computer programs now monitor hospitalized patients every day and infection control personnel are notified of high risk patients before the onset of infections. During a six month study, between 60 and 70 percent of patients with HAIs were identified before infection onset. We used similar methods to identify patient factors that can be used to predict the pathogens and to help select empiric antibiotics for individual patients. A computerized antibiotic assistant program was developed to be used by physicians both inside and outside the hospital. The computer program utilizes five years of microbiology data (over 13,500 cultures) and a knowledge base containing empiric logic from infectious disease experts to help physicians select antibiotics. The computer predicted a susceptible antibiotic in 238 of 250 (95%) patients with infections.
Background and methods:
Optimal decisions about the use of antibiotics and other antiinfective agents in critically ill patients require access to a large amount of complex information. We have developed a computerized decision-support program linked to computer-based patient records that can assist physicians in the use of antiinfective agents and improve the quality of care. This program presents epidemiologic information, along with detailed recommendations and warnings. The program recommends antiinfective regimens and courses of therapy for particular patients and provides immediate feedback. We prospectively studied the use of the computerized antiinfectives-management program for one year in a 12-bed intensive care unit.
Results:
During the intervention period, all 545 patients admitted were cared for with the aid of the antiinfectives-management program. Measures of processes and outcomes were compared with those for the 1136 patients admitted to the same unit during the two years before the intervention period. The use of the program led to significant reductions in orders for drugs to which the patients had reported allergies (35, vs. 146 during the preintervention period; P<0.01), excess drug dosages (87 vs. 405, P<0.01), and antibiotic-susceptibility mismatches (12 vs. 206, P<0.01). There were also marked reductions in the mean number of days of excessive drug dosage (2.7 vs. 5.9, P<0.002) and in adverse events caused by antiinfective agents (4 vs. 28, P<0.02). In analyses of patients who received antiinfective agents, those treated during the intervention period who always received the regimens recommended by the computer program (n=203) had significant reductions, as compared with those who did not always receive the recommended regimens (n= 195) and those in the preintervention cohort (n = 766), in the cost of antiinfective agents (adjusted mean, $102 vs. $427 and $340, respectively; P<0.001), in total hospital costs (adjusted mean, $26,315 vs. $44,865 and $35,283; P<0.001), and in the length of the hospital stay days (adjusted mean, 10.0 vs. 16.7 and 12.9; P<0.001). CONCLUSIONS; A computerized antiinfectives-management program can improve the quality of patient care and reduce costs.
Surveillance of hospital-acquired infections and antibiotic use is required of US hospitals. The time and cost needed to actively perform this surveillance can be extensive. We developed a computerized infectious disease monitor that automatically generates four types of surveillance "alerts" for patients (1) with hospital-acquired infections, (2) not receiving antibiotics to which their pathogens are susceptible, (3) who could be receiving less expensive antibiotics, or (4) who are receiving prophylactic antibiotics too long. Surveillance personnel using computer screening for two months found more hospital-acquired infections when compared with our traditional surveillance methods, while requiring only 35% of the time. In addition, alerts from the computer identified 37 patients not receiving appropriate antibiotics, 31 patients who could have been receiving less expensive antibiotics, and 142 patients, during one month, receiving prolonged cephalosporin prophylaxis. Computer screening can help focus the activities and improve the efficiency of hospital surveillance personnel.
(JAMA 1986;256:1007-1011)
Objective : To determine the clinical and financial outcomes of antibiotic practice guidelines implemented through computer-assisted decision support. Design : Descriptive epidemiologic study and financial analysis. Setting : 520-bed community teaching hospital in Salt Lake City, Utah. Patients : All 162 196 patients discharged from LDS Hospital between 1 January 1988 and 31 December 1994. Intervention : An antibiotic management program that used local clinician-derived consensus guidelines embedded in computer-assisted decision support programs. Prescribing guidelines were developed for impatient prophylactic, empiric, and therapeutic uses of antibiotics. Measurements : Measures of antibiotic use included timing of preoperative antibiotic administration and duration of postoperative antibiotic use. Clinical outcomes included rates of adverse drug events, patterns of antimicrobial resistance, mortality, and length of hospital stay. Financial and use outcomes were expressed as yearly expenditures for antibiotics and defined daily doses per 100 occupied bed-days. Results : During the 7-year study period, 63 759 hospitalized patients (39.3%) received antibiotics. The proportion of the hospitalized patients who received antibiotics increased each year, from 31.8% in 1988 to 53.1% in 1994. Use of broad-spectrum antibiotics increased from 24% of all antibiotic use in 1988 to 47% in 1994. The annual Medicare case-mix index increased from 1.7481 in 1988 to 2.0520 in 1993. Total acquisition costs of antibiotics (adjusted for inflation) decreased from 24.8% ($987 547) of the pharmacy drug expenditure budget in 1988 to 12.9% ($612 500) in 1994. Antibiotic costs per treated patient (adjusted for inflation) decreased from $122.66 per patient in 1988 to $51.90 per patient in 1994. Analysis using a standardized method (defined daily doses) to compare antibiotic use showed that antibiotic use decreased by 22.8% overall. Measures of antibiotic use and clinical outcomes improved during the study period. The percentage of patients having surgery who received appropriately timed preoperative antibiotics increased from 40% in 1988 to 99.1% in 1994. The average number of antibiotic doses administered for surgical prophylaxis was reduced from 19 doses in the base year to 5.3 doses in 1994. Antibiotic-associated adverse drug events decreased by 30%. During the study, antimicrobial resistance patterns were stable, and length of stay remained the same. Mortality rates decreased from 3.65% in 1988 to 2.65% in 1994 (P < 0.001). Conclusions : Computer-assisted decision support programs that use local clinician-derived practice guidelines can improve antibiotic use, reduce associated costs, and stabilize the emergence of antibiotic-resistant pathogens.
Computerized health information systems can contribute to the care received by patients in a number of ways, Not the least of these is through interactions with health care providers to modify diagnostic and therapeutic decisions. Since its beginnings, developers have used the HELP hospital information system to explore computerized interventions into the medical decision making process. By their nature these interventions imply a computer-directed interaction with the physicians, nurses, and therapists involved in delivering care. In this paper we describe four different approaches to this intervention. These include: (1) processes that respond to the appearance of certain types of clinical data by issuing an alert informing caregivers of these data's presence and import, (2) programs that critique new orders and propose changes in those orders when appropriate, (3) programs that suggest new orders and procedures in response to patient data suggesting their need, and (4) applications that function by summarizing patient care data and that attempt to retrospectively assess the average or typical quality of medical decisions and therapeutic interventions made by health care providers. These approaches are illustrated with experience from the HELP system.
At the LDS Hospital in Salt Lake City, an interface was developed between the microbiology laboratory computer system and the HELP integrated central hospital computer system. The HELP system includes medical information from most clinical care support areas. The microbiology data are translated from the laboratory computer file structure to a hierarchical data structure on the HELP system. A knowledge base was created with the help of infectious disease experts, and became part of a Computerized Infectious Disease Monitoring system (CIDM). The knowledge base is automatically activated when specific microbiology data are entered into a patient's computer file (data driven), thus decisions are made automatically with no additional effort required of medical personnel. The CIDM was designed to inform infectious disease personnel when a patient has one of the following conditions: (1) a hospital-acquired infection, (2) an infection at a normally sterile body site, (3) an infection due to a bacteria with an unusual antibiotic sensitivity pattern, (4) an infection for which the patient is not receiving an antibiotic to which the offending bacteria is sensitive, (5) an infection that could be treated with a less expensive antibiotic, (6) an infection which is required by law to be reported to state and national health authorities, and (7) those patients receiving prophylactic antibiotics longer than is medically indicated. All of the microbiology data are now extensively reviewed by nurses and physicians from terminals at nursing stations or intensive care units. The CIDM is currently being used for hospital-acquired infection surveillance at LDS Hospital.
The HELP system, designed and developed at the LDS Hospital in Salt Lake City, is a data driven hospital and medical information system. In contrast to most hospital information systems the HELP system is primarily designed to implement medical decision-making in real time for all aspects of patient care. The current HELP system is implemented on a Tandem "non stop" computer system consisting of 4 CPUs, disc storage and 240 communication ports. The major subsystems used in development of the application programs consist of a data base management subsystem, a decision-making subsystem, a manual data entry subsystem and a communications subsystem. Applications running on the HELP system include ADT, order entry, pharmacy, laboratory, x-ray, patient monitoring, medical records, clinical research and teaching.
It is estimated that in 1992 the United States spent 14% of its gross domestic product on health care. This level of health care spending is the highest in the world and almost twice as high as any other country. It is expected that 20% of the gross domestic product of the United States will be spent on health care by the year 2000. This has raised considerable interest in methods for health care cost containment. Assessing cost outcomes of medical care is one method of measuring and comparing the costs of medical care. Hospitals account for the largest share of health care spending. Unfortunately methods for linking detailed cost outcomes with hospital care are primitive at best. This study develops a methodology to link adverse effects of clinical care in the hospital with detailed cost outcomes. This study focusses on three adverse events that are common in hospital patients and are associated with large resource use. For this project a hospital information system known as HELP was used. This system is a comprehensive clinical information in operation at LDS Hospital where this study was performed. The HELP System is linked with an IBM Financial system. Patient hospitalizations are linked in both systems by a unique identifier, which allowed linking of clinical and financial information. The HELP system includes a variety of surveillance programs that detect various adverse events occurring in hospital patients including nosocomial surgical wound infections and urinary tract infections and adverse drug events. This study matched patients with each of these three adverse events to cohort patients base on sex, age, discharge diagnosis, severity of illness, and calendar year of discharge. Attributable differences in hospital length of stay and costs were compared using an attribution methodology. Over the period January 1, 1990 to August 1, 1992, a total of 1,552 case patients with these adverse events were matched to 17,747 cohort patients without these events. The mean attributable difference in length of stay between cases and matched cohorts for nosocomial surgical wound infections was 5.34 days (p < .00001). The mean attributable difference in hospital costs between the nosocomial surgical wound infection patients and the matched patients was $4,935 (p < .00001). The mean attributable difference in length of stay between the cases and matched cohorts for UTIs was 3.84 days (p< .00001). The mean attributable difference in hospital costs between the urinary tract infection patients and the matched patients was $3,803 (p<.00001). For adverse drug events the mean attributable difference in length of stay between these two groups was 1.94 days (p=.062). The mean attributable difference in hospital costs between the adverse drug event patients and the matched patients was $1,939 (p=.147). The total cost of all three adverse events at LDS Hospital in 1992 was $5,439,243, which accounted for over 3% of the hospital's annual budget. Master of Science;
The HELP (Health Evaluation through Logical Processing) system is a computerized hospital information system developed by the authors at the LDS Hospital at the University of Utah, USA. It provides clinical, hospital administration and financial services through the use of a modular, integrated design. This book thoroughly documents the HELP system. Chapters discuss the use of the HELP system in intensive care units, the use of APACHE and APACHE II on the HELP system, various clinical applications and inactive or experimental HELP system modules.
Adverse drug events (ADEs) are a serious health problem and are the leading adverse event experienced by hospitalized patients. Numerous hospitals have used different methods to improve the reporting of ADEs but few have undertaken studies aimed at the prevention of ADEs. We found that computerized ADE surveillance identified significantly more ADEs than our previous voluntary reporting method. Moreover, the computerized ADE surveillance system created a database of ADEs which allowed us to analyze the ADEs and design methods for prevention. We found that computer alerts of previously known drug allergies generated when drugs were ordered significantly reduced the number of type B ADEs, 56 vs 8 (p < 0.001). In addition, we found that the timely surveillance of ADEs combined with physician notification reduced the number of severe ADEs, 41 vs 12 (p < 0.001). Initial analysis of the ADE database has shown that on average patients with type B ADEs are hospitalized longer (17 vs 14 days) and have larger hospitalization costs ($30,617 vs $23,256) than patients with type A ADEs. Patients with severe ADEs also are hospitalized longer (20 vs 13 days) and have larger hospitalization costs ($38,007 vs $22,474) than patients with moderate ADEs. This indicates that the prevention and early treatment of ADEs can reduce the length of hospitalization and result in a considerable cost savings to the hospital.
Surveillance for hospital-acquired infections is required in U.S. hospitals, and statistical methods have been used to predict the risk of infection. We used the HELP (Health Evaluation through Logical Processing) Hospital Information System at LDS Hospital to develop computerized methods to identify and verify hospital-acquired infections. The criteria for hospital-acquired infection are standardized and based on the guidelines of the Study of the Efficacy of Nosocomial Infection Control and the Centers for Disease Control. The computer algorithms are automatically activated when key items of information, such as microbiology results, are reported. Computer surveillance identified more hospital-acquired infections than did traditional methods and has replaced manual surveillance in our 520-bed hospital. Data on verified hospital-acquired infections are electronically transferred to a microcomputer to facilitate outbreak investigation and the generation of reports on infection rates. Recently, we used the HELP system to employ statistical methods to automatically identify high-risk patients. Patient data from more than 6000 patients were used to develop a high-risk equation. Stepwise logistic regression identified 10 risk factors for nosocomial infection. The HELP system now uses this logistic-regression equation to monitor and determine the risk status for all hospitalized patients each day. The computer notifies infection control practitioners each morning of patients who are newly classified as being at high risk. Of 605 hospital-acquired infections during a 6-month period, 472 (78%) occurred in high-risk patients, and 380 (63%) were predicted before the onset of infection. Computerized regression equations to identify patients at risk of having hospital-acquired infections can help focus prevention efforts.
Randomized, controlled trials have shown that prophylactic antibiotics are effective in preventing surgical-wound infections. However, it is uncertain how the timing of antibiotic administration affects the risk of surgical-wound infection in actual clinical practice.
We prospectively monitored the timing of antibiotic prophylaxis and studied the occurrence of surgical-wound infections in 2847 patients undergoing elective clean or "clean-contaminated" surgical procedures at a large community hospital. The administration of antibiotics 2 to 24 hours before the surgical incision was defined as early; that during the 2 hours before the incision, as preoperative; that during the 3 hours after the incision, as perioperative; and that more than 3 but less than 24 hours after the incision, as postoperative.
Of the 1708 patients who received the prophylactic antibiotics preoperatively, 10 (0.6 percent) subsequently had surgical-wound infections. Of the 282 patients who received the antibiotics perioperatively, 4 (1.4 percent) had such infections (P = 0.12; relative risk as compared with the preoperatively treated group, 2.4; 95 percent confidence interval, 0.9 to 7.9). Of 488 patients who received the antibiotics postoperatively, 16 (3.3 percent) had wound infections (P less than 0.0001; relative risk, 5.8; 95 percent confidence interval, 2.6 to 12.3). Finally, of 369 patients who had antibiotics administered early, 14 (3.8 percent) had wound infections (P less than 0.0001; relative risk, 6.7; 95 percent confidence interval, 2.9 to 14.7). Stepwise logistic-regression analysis confirmed that the administration of antibiotics in the preoperative period was associated with the lowest risk of surgical-wound infection.
We conclude that in surgical practice there is considerable variation in the timing of prophylactic administration of antibiotics and that administration in the two hours before surgery reduces the risk of wound infection.
Adverse events during drug therapy are receiving renewed attention. Some adverse drug events (ADEs) are identified only after the widespread clinical use of a drug. The Food and Drug Administration advocates post-marketing surveillance systems to provide early warnings of previously undetected ADEs. The identification of ADEs by U.S. hospitals is now required by the Joint Commission on Accreditation of Healthcare Organizations. We developed a series of computer programs and data files on the HELP System to help identify ADEs. The HELP System monitors laboratory test results, drug orders, and data entered through a computerized ADE reporting program. A nurse or pharmacist verifies computer alerts of possible ADEs. The computerized system identified 401 ADEs during the first year of use compared to 9 by voluntary reporting methods during the previous year (p less than 0.001). This paper describes the development and early use of the computerized ADE surveillance system.
To develop a new method to improve the detection and characterization of adverse drug events (ADEs) in hospital patients.
Prospective study of all patients admitted to our hospital over an 18-month period.
LDS Hospital, Salt Lake City, Utah, a 520-bed tertiary care center affiliated with the University of Utah School of Medicine, Salt Lake City.
We developed a computerized ADE monitor, and computer programs were written using an integrated hospital information system to allow for multiple source detection of potential ADEs occurring in hospital patients. Signals of potential ADEs, both voluntary and automated, included sudden medication stop orders, antidote ordering, and certain abnormal laboratory values. Each day, a list of all potential ADEs from these sources was generated, and a pharmacist reviewed the medical records of all patients with possible ADEs for accuracy and causality. Verified ADEs were characterized as mild, moderate, or severe and as type A (dose-dependent or predictable) or type B (idiosyncratic or allergic) reactions, and causality was further measured using a standardized scoring method.
The number and characterization of ADEs detected.
Over 18 months, we monitored 36,653 hospitalized patients. There were 731 verified ADEs identified in 648 patients, 701 ADEs were characterized as moderate or severe, and 664 were classified as type A reactions. During this same period, only nine ADEs were identified using traditional detection methods. Physicians, pharmacists, and nurses voluntarily reported 92 of the 731 ADEs detected using this automated system. The other 631 ADEs were detected from automated signals, the most common of which were diphenhydramine hydrochloride and naloxone hydrochloride use, high serum drug levels, leukopenia, and the use of phytonadione and antidiarrheals. The most common symptoms and signs were pruritus, nausea and/or vomiting, rash, and confusion-lethargy. The most common drug classes involved were analgesics, anti-infectives, and cardiovascular agents.
We believe that screening for ADEs with a computerized hospital information system offers a potential method for improving the detection and characterization of these events in hospital patients.
To develop and evaluate a computerized system to monitor therapeutic antibiotics in a hospital setting.
From November 1986 through October 1987, we prospectively monitored 1,632 hospitalized patients who had 2,157 microbiology specimens sent for culture and sensitivity testing. During the study period, computer algorithms were used to identify patients whose antibiotic therapy was inappropriate in relation to microbiology culture and sensitivity data. When inconsistencies occurred between antibiotic therapy and in vitro sensitivity data, computer algorithms generated therapeutic antibiotic monitor (TAM) alerts. A clinical pharmacist then notified the attending physician of the alert.
Antibiotic therapy was identified by the computer as inappropriate in 696 instances (32%). After we eliminated false-positive alerts, 420 evaluable TAM alerts remained. Physicians responded to the TAM alerts by either changing or starting antimicrobial therapy in 125 cases (30%). Moreover, physicians were previously unaware of the relevant susceptibility test results in 49% of the alerts.
Computer-assisted monitoring is an efficient and promising method to identify and correct errors in antimicrobial prescribing and to assure the appropriate use of therapeutic antibiotics.
The use of antibiotic prophylaxis for unnecessarily prolonged periods after surgical procedures can contribute to increased health care costs and adverse drug reactions as well as the development of antibiotic-resistant infections. Hospitals are under economic pressures to develop methods to control the excessive use of these drugs. We expanded the capabilities of our hospital information system to monitor the duration of surgical antibiotic prophylaxis. For six months during one year we used the computer system to monitor antibiotics received by every surgical patient and to identify patients receiving antibiotic prophylaxis longer than was deemed necessary according to generally accepted guidelines. For six months in the following year we used the system to monitor and identify the same types of patients and clinical pharmacists placed antibiotic "stop orders" in the charts of the patients identified by the computer. Surgical patients received an average of 19 doses of antibiotics in the first year compared with 13 doses in the second year (p less than 0.001). The average cost of antibiotics received more than 48 hours after the operation was $42 less per patient in year 2 than in year 1, resulting in a potential cost savings of $44,562 in six months. The computer system was found to be an efficient tool for monitoring all antibiotics given to surgical patients and identifying patients receiving antibiotic prophylaxis longer than necessary. Clinical use of this system appears to have resulted in improved usage of antibiotic prophylaxis.
A computerized data acquisition tool, the special purpose radiology understanding system (SPRUS), has been implemented as a module in the Health Evaluation through Logical Processing Hospital Information System. This tool uses semantic information from a diagnostic expert system to parse free-text radiology reports and to extract and encode both the findings and the radiologists' interpretations. These coded findings and interpretations are then stored in a clinical data base. The system recognizes both radiologic findings and diagnostic interpretations. Initial tests showed a true-positive rate of 87% for radiographic findings and a bad data rate of 5%. Diagnostic interpretations are recognized at a rate of 95% with a bad data rate of 6%. Testing suggests that these rates can be improved through enhancements to the system's thesaurus and the computerized medical knowledge that drives it. This system holds promise as a tool to obtain coded radiologic data for research, medical audit, and patient care.
A prospective study was performed over a two-year period to determine whether computer-generated reminders of perioperative antibiotic use could improve prescribing habits and reduce postoperative wound infections. During the first year, baseline patterns of antibiotic use and postoperative infection rates were established. During the second year, computer-generated reminders regarding perioperative antibiotic use were placed in the patient's medical record prior to surgery and patterns of antibiotic use and postoperative wound infections monitored.
Hospitalized patients undergoing non-emergency surgery from June to November 1985 (3,263 patients), and from June to November 1986 (3,568) were monitored with respect to indications for perioperative antibiotic use, timing of antibiotic use and postoperative infectious complications. Perioperative antibiotic use was considered advisable for 1,621 (50%) patients in the 1985 sample and for 1,830 (51%) patients in the 1986 sample. Among these patients, antibiotics were given within two hours before the surgical incision in 638 (40%) of the 1985 sample and 1,070 (58%) of the 1986 sample ( p <0.001). Overall, postoperative wound infections were detected in 28 (1.8%) of 1,621 patients in 1985 compared with 16 (0.9%) of 1,830 such patients in 1986 ( p <0.03).
We conclude that computer-generated reminders of perioperative antibiotic use improved prescribing habits with a concurrent decline in postoperative wound infections.
Surveillance of hospital-acquired infections and antibiotic use is required of US hospitals. The time and cost needed to actively perform this surveillance can be extensive. We developed a computerized infectious disease monitor that automatically generates four types of surveillance "alerts" for patients with hospital-acquired infections, not receiving antibiotics to which their pathogens are susceptible, who could be receiving less expensive antibiotics, or who are receiving prophylactic antibiotics too long. Surveillance personnel using computer screening for two months found more hospital-acquired infections when compared with our traditional surveillance methods, while requiring only 35% of the time. In addition, alerts from the computer identified 37 patients not receiving appropriate antibiotics, 31 patients who could have been receiving less expensive antibiotics, and 142 patients, during one month, receiving prolonged cephalosporin prophylaxis. Computer screening can help focus the activities and improve the efficiency of hospital surveillance personnel.
Development of a comprehensive computer system for acquiring medical data and implementing medical decision logic has been on going for over 15 years at the University of Utah and the LDS Hospital in Salt Lake City, Utah. This system is known as HELP and is presently operational at LDS Hospital which is a 550 bed tertiary care hospital serving the needs of the intermountain west. This hospital also serves as one of the primary teaching centers for the University of Utah Medical School. Having been developed in this environment, the design of the HELP system was required to meet the administrative, clinical, teaching, and research needs of hospitals, as well as provide the decision making capability.
To measure the attitudes of physicians and nurses who use the Health Evaluation through Logical Processing (HELP) clinical information system.
Questionnaire survey of 360 attending physicians and 960 staff nurses practicing at the LDS Hospital. The physicians' responses were signed, permitting follow-up for nonresponse and use of demographic data from staff files. The nurses' responses were anonymous and their demographic data were obtained from the questionnaires.
Fixed-choice questions with a Likert-type scale, supplemented by free-text comments. Question categories included: computer experience; general attitudes about impact of the system on practice; ranking of available functions; and desired future capabilities.
The response rate was 68% for the physicians and 39% for the nurses. Age, specialty, and general computer experience did not correlate with attitudes. Access to patient data and clinical alerts were rated highly. Respondents did not feel that expert computer systems would lead to external monitoring, or that these systems might compromise patient privacy. The physicians and nurses did not feel that computerized decision support decreased their decision-making power.
The responses to the questionnaire and "free-text comments" provided encouragement for future development and deployment of medical expert systems at LDS Hospital and sister hospitals. Although there has been some fear on the part of medical expert system developers that physicians would not adapt to or appreciate recommendations given by these systems, the results presented here are promising and may be of help to other system developers and evaluators.
Physicians frequently need to order antibiotic therapy before the results of bacterial cultures and antibiotic susceptibility tests are available. Therapy selected empirically should be chosen on the basis of the most recent information about probable pathogens and their susceptibility to various drugs. We have developed a series of computer programs to help physicians identify the antibiotic regimens with the highest probability of acting against the pathogens that are most likely to be present at suspected sites of infection in individual patients. This automated antibiotic consultant is now available on our hospital information system. A comparison of the antibiotic regimens suggested by the computer with those indicated by cultures and susceptibility tests showed that the computer suggested an appropriate regimen for 717 of 761 culture events (94%).
At LDS Hospital, we have developed and evaluated a computerized critical value reporting system based on digital pagers. Criteria used to identify critical values are patient-specific. An evaluation of the system was conducted from October 23, 1993 to January 21, 1994. Results showed that 100% of all critical values (497 values in the form of 335 alerts) were reported to clinicians within an average of 38.6 minutes, and that 51% of all alerts were received within 12 minutes. Data also showed that 92% of the alerts were considered valid, that 76% were communicated directly to the primary care nurse, and that 67% of the time nurses were previously unaware of the critical value(s).
To determine the clinical and financial outcomes of antibiotic practice guidelines implemented through computer-assisted decision support.
Descriptive epidemiologic study and financial analysis.
520-bed community teaching hospital in Salt Lake City, Utah.
All 162 196 patients discharged from LDS Hospital between 1 January 1988 and 31 December 1994.
An antibiotic management program that used local clinician-derived consensus guidelines embedded in computer-assisted decision support programs. Prescribing guidelines were developed for inpatient prophylactic, empiric, and therapeutic uses of antibiotics.
Measures of antibiotic use included timing of preoperative antibiotic administration and duration of postoperative antibiotic use. Clinical outcomes included rates of adverse drug events, patterns of antimicrobial resistance, mortality, and length of hospital stay. Financial and use outcomes were expressed as yearly expenditures for antibiotics and defined daily doses per 100 occupied bed-days.
During the 7-year study period, 63 759 hospitalized patients (39.3%) received antibiotics. The proportion of the hospitalized patients who received antibiotics increased each year, from 31.8% in 1988 to 53.1% in 1994. Use of broad-spectrum antibiotics increased from 24% of all antibiotic use in 1988 to 47% in 1994. The annual Medicare case-mix index increased from 1.7481 in 1988 to 2.0520 in 1993. Total acquisition costs of antibiotics (adjusted for inflation) decreased from 24.8% ($987,547) of the pharmacy drug expenditure budget in 1988 to 12.9% ($612,500) in 1994. Antibiotic costs per treated patient (adjusted for inflation) decreased from $122.66 per patient in 1988 to $51.90 per patient in 1994. Analysis using a standardized method (defined daily doses) to compare antibiotic use showed that antibiotic use decreased by 22.8% overall. Measures of antibiotic use and clinical outcomes improved during the study period. The percentage of patients having surgery who received appropriately timed preoperative antibiotics increased from 40% in 1988 to 99.1% in 1994. The average number of antibiotic doses administered for surgical prophylaxis was reduced from 19 doses in the base year to 5.3 doses in 1994. Antibiotic-associated adverse drug events decreased by 30%. During the study, antimicrobial resistance patterns were stable, and length of stay remained the same. Mortality rates decreased from 3.65% in 1988 to 2.65% in 1994 (P < 0.001). Conclusions: Computer-assisted decision support programs that use local clinician-derived practice guidelines can improve antibiotic use, reduce associated costs, and stabilize the emergence of antibiotic-resistant pathogens.
Hospital information systems designed to support the needs of health care professionals include patient data entered using both freetext and precoded storage schemes. A major disadvantage of freetext storage schemes is that data captured in this format can only be presented as is to the user for review tasks. In the view of many health care scientists, natural language understanding systems capable of identifying, extracting, and encoding information contained in freetext data may provide the necessary tools to overcome this weakness. This paper describes the development and evaluation of a such a system designed to encode freetext admission diagnoses. This system combines both semantic and syntactic linguistic analysis techniques. Evaluation results demonstrate the overall performance of this system to be reasonable, accurately encoding approximately 76% of admission diagnoses. Inefficiencies are primarily due to the inability of this system to generate encodings in roughly 15% of test cases. When encodings are produced, however, accuracy equals that of the current manual coding method. With further modification, this application can partially automate the coding process.
To determine acceptable strategies for automated data acquisition and artifact rejection from computerized ventilators using the Medical Information Bus.
Medical practitioners were surveyed to establish 'clinically important' ventilator events. A prospective study involving frequent data collection from ventilators was also conducted.
Data from 10 adult patients were collected every 10 seconds from a Puritan Bennett 7200A ventilator for a total of 617.1 hours.
Twelve different computerized data selection and artifact algorithms were tested and evaluated.
Data derived from 12 data selection algorithms were compared with each other and with data manually charted by respiratory therapists into a computerized charting system. Ventilator setting data collected by the algorithms, such as FIO2, reduced the amount of data collected to about 25% compared to manually charted data. The amount of data collected for measured parameters, such as tidal volume, from the ventilator had large variability and many artifacts. Automated data capture and selection generally increased the amount of data collected compared to manual charting, for example for the 3 minute median the increase was a modest 1.2 times.
Computerized methods for collecting ventilator setting data were relatively straightforward and more-efficient than manual methods. However, the method for automated selection and presentation of observed measured parameters is much more difficult. Based on the findings and analysis presented here, the authors recommend recording ventilator setting data after they have existed for three minutes and measured parameters using a three minute median data selection strategy. Such an algorithm rejected most artifacts, required minimal computational time, had minimal time-delay, and provided clinically acceptable data acquisition. The results presented here are but a starting point in developing automated ventilator data selection strategies.
To identify factors which influence the choice of nurses to use automated collection of i.v. pump data from a prototype Medical Information Bus.
Observational study for a duration of three and one-half months.
Four intensive care units, each with different missions, in an adult hospital.
One hundred fifty-eight registered nurses including both full and part time.
Data were collected from the hospital information system about infusion orders including the type of medication, the number of rate changes, the method of documenting rate changes and the infusion methods. The method of documentation for infusion rate changes was defined as either automated, using a prototype Medical Information Bus (MIB), or manual, using the keyboard at a bedside computer terminal. The method of infusion was defined as either straight gravity feed without an i.v. pump ('no pump'), infusion using a pump but without connection to the hospital information system ('pump only') and infusion using a pump which was connected to the hospital information system using a prototype Medical Information Bus ('automated'). A total of 22,199 rate changes were documented during the study period and of those, 22,055 (99.35%) used the 'automated' method. Medications with the highest average rate change per single container were; Nitroprusside Sodium (9.50), Epinephrine (9.08) and Epoprostenol (7.50).
The nurses used automated i.v. pump data acquisition with medications which required frequent rate changes.
Automated data capture from bedside patient medical devices is now possible using a new Institute of Electrical and Electronic Engineering (IEEE) and American National Standards Institute (ANSI) Medical Information Bus (MIB) data communications standard (IEEE 1073). The first two standard documents, IEEE 1073.3.1 (Transportation Profile) and IEEE 1073.4.1 (Physical Layer), define the hardware protocol for bedside device communications. With the above noted IEEE MIB standards in place, hospitals can now start designing customized applications for acquiring data from bedside devices such as bedside monitors, i.v. pumps, ventilators, etc. for multiple purposes. The hardware 'plug and play' features of the MIB will enable nurses and physicians to establish communications with these devices simply and conveniently by plugging them into a bedside data connector. No other action will be necessary to establish identification of the device or communications with the device. Presently to connect bedside devices, technical help from hardware and software experts are required to establish such communications links. As a result of standardization of communications, it will be easy to establish a highly mobile network of bedside devices and more promptly and efficiently collect patient related data. Collection of data automatically should lead to the design of new medical computing applications that will tie in directly with the emerging mission and operations of hospitals. The MIB will permit acquisition of patient data more efficiently with greater accuracy, more completeness and more promptly. The above noted features are all essential to the development of computerized treatment protocols and should lead to improved quality of patient care. This manuscript provides the rational and historical overview of the development of the MIB standard.
To improve the detection and characterization of adverse drug events (ADEs) in hospitalized patients, a computerized adverse drug event monitor was developed. Computer programs were written to allow for voluntary as well as automated detection of adverse drug events using the HELP hospital information system, a large integrated hospital database containing computerized patient medical records and a knowledge base allowing for automated medical decisions. Programs were created to allow simple computer entry of potential adverse drug events by physicians, pharmacists, and nurses. Automated detection of potential adverse drug events relied on signals such as sudden medication stop orders, "antidote" orders, and selected abnormal laboratory values. Each day a list of all potential adverse drug events from these sources was generated and a pharmacist reviewed the medical records and interviewed healthcare personnel associated with patients identified as having potential adverse drug events. This process allowed for characterization of the event, causality assessment, and follow-up of the resulting clinical course by the pharmacist. The permanent storage of these results in the computerized patient medical record permits their future retrieval to prevent adverse drug events during subsequent hospital care. The authors conclude that fully integrated hospital systems will permit the further development and evaluation of computer-assisted methods for the detection of adverse drug events in hospitalized patients.
The large arteries may be expected to respond to a central pulse wave as a resonant system and the pressure pulse can be resolved into a series of pure sinusoidal waves. Therefore, a frequency filter network was designed which could duplicate the resonant frequency and damping coefficient of a segment of artery by proper adjustment of the circuit constants. Data are presented which support the concept that much of the distortion of a pressure wave in its transmission down an artery can be explained in terms of a resonant frequency and damping coefficient, and that these variables in turn arc dependent upon physical properties of the segment of artery transmitting the wave.
Building a computer-based patient record system in an evolving integrated health system
- L C Grandia
- T A Pryor
- D F Willson
- R M Gardner
- P A Haug
- S M Huff
- B R Farr
- S H Lam
L.C. Grandia, T.A. Pryor, D.F. Willson, R.M. Gardner, P.A. Haug, S.M. Huff, B.R. Farr, S.H. Lam, Building a computer-based patient record system in an evolving integrated health system, in: Elaine B. Steen (Ed.) First Annu. Nicholas E. Davies CPR Recognit. Symp. Proc., April 4 – 6, 1995, pp. 3–33 (soon to be published by McGraw-Hill).
Integration of computer support for institutional practice: the HELP system
- H R Warner
- T A Pryor
- S Clark
- J Morgan
Adverse drug events in hospitalized patients: excess length of stay, extra costs, and attributable mortality
- Classen