BookPDF Available

Biomedical Informatics: Computer Applications in Health Care and Biomedicine

Authors:

Abstract

The world of biomedical research and health care has changed remarkably in the 25 years since the first edition of this book was undertaken. So too has the world of computing and communications and thus the underlying scientific issues that sit at the intersections among biomedical science, patient care, public health, and information technology. It is no longer necessary to argue that it has become impossible to practice modern medicine, or to conduct modern biological research, without information technologies. Since the initiation of the human genome project two decades ago, life scientists have been generating data at a rate that defi es traditional methods for information management and data analysis. Health professionals also are constantly reminded that a large percentage of their activities relates to information management—for example, obtaining and recording information about patients, consulting colleagues, reading and assessing the scientific literature, planning diagnostic procedures, devising strategies for patient care, interpreting results of laboratory and radiologic studies, or conducting case-based and population-based research. It is complexity and uncertainty, plus society’s overriding concern for patient well-being, and the resulting need for optimal decision making, that set medicine and health apart from many other information- intensive fields. Our desire to provide the best possible health and health care for our society gives a special significance to the effective organization and management of the huge bodies of data with which health professionals and biomedical researchers must deal. It also suggests the need for specialized approaches and for skilled scientists who are knowledgeable about human biology, clinical care, information technologies, and the scientific issues that drive the effective use of such technologies in the biomedical context.

Chapters (20)

After reading this chapter, you should know the answers to these questions: Why is information management a central issue in biomedical research and clinical practice? What are integrated information management environments, and how might we expect them to affect the practice of medicine, the promotion of health, and biomedical research in coming years? What do we mean by the terms medical computer science, medical computing, biomedical informatics, clinical informatics, nursing informatics, bioinformatics, and health informatics? Why should health professionals, life scientists, and students of the health professions learn about biomedical informatics concepts and informatics applications? How has the development of modern computing technologies and the Internet changed the nature of biomedical computing? How is biomedical informatics related to clinical practice, biomedical engineering, molecular biology, decision science, information science, and computer science? How does information in clinical medicine and health differ from information in the basic sciences? How can changes in computer technology and the way medical care is financed influence the integration of medical computing into clinical practice?
After reading this chapter, you should know the answers to these questions: • What are medical data? • How are medical data used? • What are the drawbacks of the traditional paper medical record? • What is the potential role of the computer in data storage, retrieval, and interpretation? • What distinguishes a database from a knowledge base? • How are data collection and hypothesis generation intimately linked in medical diagnosis? • What are the meanings of the terms prevalence, predictive value, sensitivity, and specificity? • How are the terms related? • What are the alternatives for entry of data into a medical database?
After reading this chapter, you should know the answers to these questions: How is the concept of probability useful for understanding test results and for making medical decisions that involve uncertainty? How can we characterize the ability of a test to discriminate between disease and health? What information do we need to interpret test results accurately? What is expected-value decision making? How can this methodology help us to understand particular medical problems? What are utilities, and how can we use them to represent patients’ preferences? What is a sensitivity analysis? How can we use it to examine the robustness of a decision and to identify the important variables in a decision? What are influence diagrams? How do they differ from decision trees?
After reading this chapter, you should know the answers to these questions: How can cognitive science theory meaningfully inform and shape design, development and assessment of health care information systems? What are some of the ways in which cognitive science differs from behavioral science? What are some of the ways in which we can characterize the structure of knowledge? What are the basic components of a cognitive architecture? What are some of the dimensions of difference between experts and novices? Describe some of the attributes of system usability. What are the gulfs of execution and evaluation? What role do these considerations play in system design? What is the difference between a textbase and a situation model? How can we use cognitive methods to develop and implement clinical practice guidelines for different kinds of clinicians?
After reading this chapter, you should know the answers to these questions: What key functions do medical computer systems perform? Why is communication between medical personnel and computing personnel crucial to the successful design and implementation of a health information system? What are the trade-offs between purchasing a turnkey system and developing a custom-designed system? What resources are available remotely for medical computer systems? What design features most heavily affect a system’s acceptance by health professionals? Why do systems in health care, once implemented and installed successfully, have a long lifetime?
After reading this chapter, you should know the answers to these questions: Why are standards important in biomedical informatics? What data standards are necessary to be able to exchange data seamlessly among systems? What organizations are active in standards development? What aspects of biomedical information management are supported today by standards? What is the process for creating consensus standards? What factors and organizations influence the creation of standards?
After reading this chapter, you should know the answers to these questions: Why is natural language processing (NLP) important? What are the potential uses for NLP in the biomedical domain? What forms of knowledge are used in NLP? What are the principal techniques of NLP? What are the challenges for NLP in the clinical domain? What are the challenges for NLP in the biological domain?
As is evident to anyone who has had an X-ray, a magnetic resonance imaging (MRI) exam, or a biopsy, images play a central role in the health care process. In addition, images play important roles in medical communication and education, as well as in research. In fact much of our recent progress, particularly in diagnosis, can be traced to the availability of increasingly sophisticated images that not only show the structure of the body in incredible detail but also show the function.
After reading this chapter, you should know the answers to these questions: Why is ethics important to informatics? What are the leading ethical issues that arise in health care informatics? What are examples of appropriate and inappropriate uses and users for health-related software? Why does the establishment of standards touch on ethical issues? Why does system evaluation involve ethical issues? What challenges does informatics pose for patient and provider confidentiality? How can the tension between the obligation to protect confidentiality and that to share data be minimized? How might computational health care alter the traditional provider–patient relationship? What ethical issues arise at the intersection of informatics and managed care? What are the leading issues in the debate over governmental regulation of health care computing tools?
After reading this chapter, you should know the answers to these questions: • Why are empirical studies based on the methods of evaluation and technology assessment important to the successful implementation of information resources to improve health care? • What challenges make studies in informatics difficult to carry out? How are these challenges addressed in practice? • Why can all evaluations be classified as empirical studies? • What are the major assumptions underlying objectivist and subjectivist approaches to evaluation? What are the advantages and disadvantages of each? • What are the factors that distinguish the three stages of technology assessment? • How does one distinguish measurement and demonstration aspects of objectivist studies, and why are both aspects necessary? • What steps are typically undertaken in a measurement study? What designs are typically used in demonstration studies? • What is the difference between cost-effectiveness and cost-benefit analyses? How can investigators address issues of cost effectiveness and cost benefit of medical information resources? • What steps are followed in a subjectivist study? What techniques are employed by subjectivist investigators to ensure rigor and credibility of their findings? • Why is communication between investigators and clients central to the success of any evaluation?
After reading this chapter, you should know the answers to these questions: What is the definition of an electronic health record (EHR)? How does an EHR differ from the paper record? What are the functional components of an EHR? What are the benefits of an EHR? What are the impediments to development and use of an EHR?
After reading this chapter, you should know the answers to these questions: What are the primary information requirements of healthcare organizations? What are the clinical, financial, and administrative functions provided by a healthcare information system (HCIS), and what are the potential benefits of implementing such a system? How have changes in healthcare delivery models changed the scope and capabilities of HCISs over time? How do differences among business strategies and organizational structures influence information systems choices? What are the major challenges to implementing and managing HCISs? How are ongoing healthcare reforms, technological advances, and changing social norms likely to affect HCIS requirements in the future?
After reading this chapter you should know the answers to these questions: What factors contribute to the increasing pressure for lay people to actively participate in health care? How does direct access to health information technologies assist patients in participating in their own health care? Critically appraise the informatics requirements for successful telehealth. How can lay people determine the value of a telehealth innovation such as a healthrelated Web site or an on-line disease management service?
After reading this chapter you should know the answers to these questions: What are the three core functions of public health, and how do they help shape the different foci of public health and medicine? What are the current and potential effects of a) the genomics revolution; and b) 9/11 on public health informatics? What were the political, organizational, epidemiological, and technical issues that influenced the development of immunization registries? How do registries promote public health, and how can this model be expanded to other domains (be specific about those domains) ? How might it fail in others?Why? What is the vision and purpose of the National Health Information Infrastructure? What kinds of impacts will it have, and in what time periods? Why don’t we have one already? What are the political and technical barriers to its implementation? What are the characteristics of any evaluation process that would be used to judge demonstration projects?
After reading this chapter, you should know the answers to these questions: What are the four major information-management issues in patient care? How have patient-care systems evolved during the past four decades? How have patient-care systems influenced the process and outcomes of patient care? Why are patient-care systems essential to the computer-based patient record? How can they be differentiated from the computer-based patient record itself ?
After reading this chapter, you should know the answers to these questions: • What is patient monitoring, and why is it done? • What are the primary applications of computerized patient-monitoring systems in the intensive-care unit? • How do computer-based patient monitors aid health professionals in collecting, analyzing, and displaying data? • What are the advantages of using microprocessors in bedside monitors? • What are the important issues for collecting high-quality data either automatically or manually in the intensive-care unit? • Why is integration of data from many sources in the hospital necessary if a computer is to assist in critical-care-management decisions?
In chapter 9 we introduce the concept of digital images as a fundamental datatype that, because of its ubiquity, must be considered in many applications. We define biomedical imaging informatics as the study of methods for generating, manipulating, managing, and integrating images in many biomedical applications.We describe many of the methods for generating and manipulating images, particularly as applied to the brain, and discuss the relationship of these methods to structural informatics.
After reading this chapter, you should know the answers to these questions: What types of online content are available and useful to health care practitioners, researchers, and consumers? What are the major components of the information retrieval process? How do techniques differ for indexing various types of knowledge-based biomedical information? What are the major approaches to retrieval of knowledge-based biomedical information? How effectively do searchers utilize information retrieval systems? What are the important research directions in information retrieval? What are the major challenges to making digital libraries effective for health and biomedical users?
After reading this chapter, you should know the answers to these questions: • What are three requirements for an excellent decision-making system? • What are three decision-support roles for computers in clinical medicine? • How has the use of computers for clinical decision support evolved since the1960s? • What is a knowledge-based system? • What influences account for the gradual improvement in professional attitudes toward use of computers for clinical decision support? • What are the five dimensions that characterize clinical decision-support tools? • What are clinical-practice guidelines, and what are the challenges in providing guideline-based decision support? • What are the principal scientific challenges in building useful and acceptable clinical decision-support tools? • What legal and regulatory barriers could affect distribution of clinical decisionsupport technologies?
After reading this chapter, you should know the answers to these questions: What are the advantages of computer-aided instruction over traditional lecture-style instruction in medical education? What are the different learning methods that can be implemented in computer-based education? How can computer-based simulations supplement students’ exposure to clinical practice? What are the issues to be considered when developing computer-based educational programs? What are the significant barriers to widespread integration of computer-aided instruction into the medical curriculum?
... Clinical decision support (CDS) systems have been proved to enhance evidencebased practice and support cost-effectiveness [1][2][3][4][5][6]. Based on Shortliffe's three levels classification, clinical predictive tools, here referred to simply as predictive tools, belong to the highest CDS level; providing patient-specific recommendations based on clinical scenarios, which usually follow clinical rules and algorithms, cost benefit analysis, or clinical pathways [7,8]. Such tools include various applications; ranging from the simplest manual clinical prediction rules to the most sophisticated machine learning algorithms [9,10]. ...
... A reminder email, in two weeks, was sent to the potential participants who did not respond or complete the survey. 8 ...
Article
Full-text available
Background: When selecting predictive tools, for implementation in clinical practice or for recommendation in clinical guidelines, clinicians and healthcare professionals are challenged with an overwhelming number of tools. Many of these tools have never been implemented or evaluated for comparative effectiveness. To overcome this challenge, the authors developed and validated an evidence-based framework for grading and assessment of predictive tools (The GRASP Framework), based on the critical appraisal of the published evidence on such tools. Objectives: To examine the impact of using the GRASP framework on clinicians and healthcare professionals’ decisions in selecting clinical predictive tools. Methods: A controlled experiment was conducted through an online survey. Participants were randomised to either review the derivation publications on common traumatic brain injury predictive tools (control group), or to review an evidence-based summary, where each tool had been graded and assessed using the GRASP framework (intervention group). Participants in both groups were asked to select the best tool based on greatest validation and/or implementation. A wide group of international clinicians and healthcare professionals were invited to take the survey. Task completion time, rate of correct decisions, rate of objective versus subjective decisions, and level of decisional conflict were measured. Results: Valid responses received were 194. Compared to not using GRASP, using the framework significantly increased correct decisions by 64%, from 53.7% to 88.1% (88.1/53.7=1.64) (T=8.53, P<.001), increased objective decision making by 32%, from 3.11/5 to 4.10/5 (T=9.24, P<.001), and decreased subjective decision making; based on guessing and based on prior knowledge or experience, by 20%, from 2.48/5 to 1.98/5 (T=-5.47, P<.001) and 8%, from 3.55/5 to 3.27/5 (T=-2.99, P=.003) respectively. Using GRASP significantly decreased decisional conflict, increasing confidence and satisfaction of participants with their decisions by 11%, from 3.55/5 to 3.96/5 (T=4.27, P<.001) and 13%, from 3.54/5 to 3.99/5 (T=4.89, P<.001) respectively. Using GRASP decreased task completion time, on the 90th percentile, by 52%, from 12.4 to 6.4 minutes (T=-0.87, P=0.384). The average system usability scale of GRASP framework was very good; 72.5%, and 108 out of 122 of participants (88%) found GRASP useful. Conclusions: Using GRASP has positively supported and significantly improved evidence-based decision making and increased accuracy and efficiency of selecting predictive tools. GRASP is not meant to be prescriptive; it represents a high-level approach and an effective, evidence-based, and comprehensive, yet simple and feasible, method to evaluate, compare, and select clinical predictive tools.
... The focus of human-computer interaction (HCI) research in healthcare expanded significantly from its beginning, spanning from persuasive designs for vitality promotion [1] to body interactions in motor rehabilitation [2] and medical informatics for the provision of healthcare services [3]. In the healthcare field, it became increasingly prevalent to use technologies to support caregivers in everyday tasks. ...
... We mainly employed ConsultAI as an intelligent assistant for the scenario of the OH consult. Our participants believed that not only consultation would benefit from such application but also some repeated coordination tasks, such as standardizing diagnostic reports (P1, P3, P7) and taking over administrative work (P2, 3,5). It would involve some efforts to advance data collection and management. ...
Article
Full-text available
This paper presents an exploratory study on using conversational interfaces (CIs) to support physicians in conducting occupational health consultations. The CI was achieved through a web-based information dashboard with a chatbot assistant for providing real-time suggestions through text messages. Two system designs were developed: the first using a proactive chatbot, the second using an on-demand type of interaction. The effectiveness of the proposed CI and the two types of chatbot designs were investigated in a field study consisted of eight healthcare consultations. Quantitative results showed that the CI was positively evaluated as a reliable tool to be used during medical consultations and that occupational health physicians were eager to use this technology in their work. The qualitative data analysis suggested that our design concept might improve the workflow during the consultation, particularly with respect to the access to relevant information and structured decision-making processes using valuable references. The on-demand, lightweight type of chatbot interaction was better perceived than the proactive one. Based on these findings, we discuss implications for the future development of occupational health consultation based on CIs and their potential contribution to computer-assisted, data-driven healthcare.
... Medical Informatics is an interdisciplinary field in which computer science, software, information science, medicine, statistics, mathematics and cognitive sciences can be used. The task and mission of this field is to use concepts, tools, methods and software techniques and modeling to improve health care services, reduce costs and care errors [1][2][3][4]. ...
Article
Full-text available
Introduction: One of the challenges of multidisciplinary disciplines such as Medical Informatics, is the lack of familiarity with research fields. Due to the specializations and clinical facilities concentrated in each university, research is being done differently and with variety. Therefore, in this study, in order to identify the most researched fields and the neglected fields of research, the dissertations done in the field of medical informatics in Iranian universities were studied based on the health informatics framework. Material and Methods: Defended dissertations available to master and doctoral students of medical informatics during 2011 to 2019 in the universities of Tehran, Iran, Tarbiat Modares, Shahid Beheshti, Shiraz, Tabriz and Mashhad were collected. Three medical informatics experts assigned dissertation titles to a competency and an area of skill based on health informatics competencies framework. The second stage of the study was performed by two other experts (different from the previous three experts). Each dissertation title was assigned to a specific competency and a specific area of skill by the majority opinion method. Results: The results showed that the most of master and doctoral dissertations were in the field of information science and methods, in which area of skill of data analysis and visualization, which decision support systems and informatics for participatory health were more than others. Among PhD students, the area of skill of decision support system and architecture of health information systems were more popular. PhD students at the universities of Mashhad, Tehran and Shahid Beheshti worked in the field of methods and basic principles of activities more than other areas, information and communication technology, biomedical science and health were not considered. Conclusion: Results of this research could be helpful for field researchers in terms of conducting new research in the field and can help to design useful, scientific and effective research projects.
... Clinical decision support (CDS) systems have been discussed to enhance evidence-based practice and support cost-effectiveness [1][2][3][4][5][6][7][8][9][10]. On the basis of the three-level classification by Shortliffe, clinical predictive tools, referred to as predictive tools in this paper, belong to the highest CDS level, providing patient-specific recommendations based on clinical scenarios, which usually follow clinical rules and algorithms, a cost-benefit analysis, or clinical pathways [11,12]. Such tools include various applications, ranging from the simplest manual clinical prediction rules to the most sophisticated machine learning algorithms [13,14]. ...
Article
Full-text available
Background: While selecting predictive tools for implementation in clinical practice or for recommendation in clinical guidelines, clinicians and health care professionals are challenged with an overwhelming number of tools. Many of these tools have never been implemented or evaluated for comparative effectiveness. To overcome this challenge, the authors developed and validated an evidence-based framework for grading and assessment of predictive tools (the GRASP framework). This framework was based on the critical appraisal of the published evidence on such tools. Objective: The aim of the study was to examine the impact of using the GRASP framework on clinicians’ and health care professionals’ decisions in selecting clinical predictive tools. Methods: A controlled experiment was conducted through a web-based survey. Participants were randomized to either review the derivation publications, such as studies describing the development of the predictive tools, on common traumatic brain injury predictive tools (control group) or to review an evidence-based summary, where each tool had been graded and assessed using the GRASP framework (intervention group). Participants in both groups were asked to select the best tool based on the greatest validation or implementation. A wide group of international clinicians and health care professionals were invited to participate in the survey. Task completion time, rate of correct decisions, rate of objective versus subjective decisions, and level of decisional conflict were measured. Results: We received a total of 194 valid responses. In comparison with not using GRASP, using the framework significantly increased correct decisions by 64%, from 53.7% to 88.1% (88.1/53.7=1.64; t193=8.53; P<.001); increased objective decision making by 32%, from 62% (3.11/5) to 82% (4.10/5; t189=9.24; P<.001); decreased subjective decision making based on guessing by 20%, from 49% (2.48/5) to 39% (1.98/5; t188=−5.47; P<.001); and decreased prior knowledge or experience by 8%, from 71% (3.55/5) to 65% (3.27/5; t187=−2.99; P=.003). Using GRASP significantly decreased decisional conflict and increased the confidence and satisfaction of participants with their decisions by 11%, from 71% (3.55/5) to 79% (3.96/5; t188=4.27; P<.001), and by 13%, from 70% (3.54/5) to 79% (3.99/5; t188=4.89; P<.001), respectively. Using GRASP decreased the task completion time, on the 90th percentile, by 52%, from 12.4 to 6.4 min (t193=−0.87; P=.38). The average System Usability Scale of the GRASP framework was very good: 72.5% and 88% (108/122) of the participants found the GRASP useful. Conclusions: Using GRASP has positively supported and significantly improved evidence-based decision making. It has increased the accuracy and efficiency of selecting predictive tools. GRASP is not meant to be prescriptive; it represents a high-level approach and an effective, evidence-based, and comprehensive yet simple and feasible method to evaluate, compare, and select clinical predictive tools.
... Pada pengklasifikasian penyakit kandungan, Naïve Bayesian Classifier dengan Laplacian Smoothing memiliki tingkat akurasi lebih tinggi daripada Learning Vector Quantization. [4] Naïve Bayesian telah terbukti dapat bekerja dengan sangat baik pada bidang kesehatan [5], [6]. Karena induksi datanya cepat, metode ini kerap digunakan sebagai algoritma pendasar dalam studi komparatif [1]. ...
Article
Full-text available
keakuratan data yang digunakan pada bidang kesehatan dituntut untuk memiliki tingkat akurasi yang tinggi. Oleh karena itu banyaknya data pada bidang kesehatan ini perlu diimbangi dengan pemrosesan data yang sesuai salah satunya dengan menggunakan data mining. Data mining dapat digunakan untuk menggali informasi-informasi dari banyaknya data yang telah ada. Pada penelitian terdahulu khususnya pada masalah kehamilan dan persalinan, beberapa metode data mining telah diaplikasikan.. Dalam data mining, terdapat metode prediksi yang juga kerap digunakan untuk menggali dapat di bidang kehamilan dan persalinan. Pada paper ini, akan dijelaskan kelebihan dan kelemahan metode-metode prediksi yang sering digunakan pada masalah kehamilan dan persalinan.
Chapter
Full-text available
In this book, we present some experiences that go through a scientific, theoretical and technical foundation, and of practical application. The book begins with a theoretical approach in which the focus is on the introduction to ehealth and the strategies for evaluating and validating these technologies. In the second part of the book, we demonstrate the application of ehealth in designing tools for improving health care in 14 chapters that bring successful experiences that can inspire readers.
Book
Full-text available
In this book, we present some experiences that go through a scientific, theoretical and technical foundation, and of practical application. The book begins with a theoretical approach in which the focus is on the introduction to ehealth and the strategies for evaluating and validating these technologies. In the second part of the book, we demonstrate the application of ehealth in designing tools for improving health care in 14 chapters that bring successful experiences that can inspire readers.
Chapter
We can observe that the focus of modern information systems is moving from “data processing” towards “concept processing,” meaning that the basic unit of processing is less and less an atomic piece of data and is becoming more a semantic concept which carries an interpretation and exists in a context with other concepts. An ontology is commonly used as a structure capturing knowledge about a certain area by providing relevant concepts and relations between them. Analysis of textual data plays an important role in construction and usage of ontologies, especially with the growing popularity of semi-automated ontology construction (here referred to also as ontology learning). Different knowledge discovery methods have been adopted for the problem of semi-automated ontology construction [10] including unsupervised, semi-supervised and supervised learning over a collection of text documents, using natural language processing to obtain semantic graph of a document, visualization of documents, information extraction to find relevant concepts, visualization of context of named entities in a document collection.