Article

Enhancing the Performance of Predictive Models for Hospital Mortality by Adding Nursing Data

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

Background: Mortality is the most considered outcome for assessing the quality of hospital care. However, hospital mortality depends on diverse patient characteristics; thus, complete risk stratification is crucial to correctly estimate a patient's prognosis. Electronic health records include standard medical data; however, standard nursing data, such as nursing diagnoses (which were considered essential for a complete picture of the patient condition) are seldom included. Objective: To explore the independent predictive power of nursing diagnoses on patient hospital mortality and to investigate whether the inclusion of this variable in addition to medical diagnostic data can enhance the performance of risk adjustment tools. Methods: Prospective observational study in one Italian university hospital. Data were collected for six months from a clinical nursing information system and the hospital discharge register. The number of nursing diagnoses identified by nurses within 24 h after admission was used to express the nursing dependency index (NDI). Eight logistic regression models were tested to predict patient mortality, by adding to a first basic model considering patient's age, sex, and modality of hospital admission, the level of comorbidity (CCI), and the nursing and medical condition as expressed by the NDI and the All Patient Refined-Diagnosis Related Group weight (APR-DRGw), respectively. Results: Overall, 2301 patients were included. The addition of the NDI to the model increased the explained variance by 20%. The explained variance increased by 56% when the APR-DRGw, CCI, and NDI were included. Thus, the latter model was nearly highly accurate (c = 0.89, 95% confidence interval: 0.87–0.92). Conclusion: Nursing diagnoses have an independent power in predicting hospital mortality. The explained variance in the predictive models improved when nursing data were included in addition to medical data. These findings strengthen the need to include standardized nursing data in electronic health records.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Evidence-based diagnoses by the use of SLS result in several benefits to health organizations and patients (Sanson et al., 2017), even the identification and consolidation of clinical and epidemiological indicators Sanson et al., 2019). Additionally, the use of SLS in various contexts can provide support for the elaboration of clinical guidelines by matching the information from similar patterns of response to specific conditions of the life cycle or health (Müller-Staub et al., 2016). ...
Article
Purpose: A standardized language system can support the elaboration of clinical guidelines by matching information from similar patterns of response to people. To identify the factors that are related to a higher likelihood of an ineffective health management nursing diagnosis. Methods: We conduct a systematic review and meta-analysis. An electronic search was conducted in MEDLINE databases via PubMed, Web of Science, SciELO, CINAHL, SCOPUS, and Embase between October and November 2020. Descriptive data were extracted from each article. The odds ratios for each etiological factor related to ineffective health management were directly extracted from the articles or calculated from the data described in the articles. The analysis of the measurements of exposure and the magnitude of the effect was performed using the statistical software R, and a forest plot was constructed for each etiological factor. Findings: Ten studies were included, and 15 related factors were recovered from the primary studies. The factors that significantly increased the likelihood of an ineffective health management nursing diagnosis were insufficient knowledge of the therapeutic regimen, perceived barriers, powerlessness, economic disadvantage, and difficulty managing complex treatment regimens. No effect was verified with the following factors: decision conflict, family pattern of healthcare, and inadequate number of cues to action. Conclusion: Factors related to a higher likelihood of ineffective health management may be the focus of early and targeted nursing interventions, contributing to an improved quality of care. Clinical relevance: Understanding exposure to these factors can improve diagnostic reasoning at different population levels.
... Because nurses should primarily intervene to remove the underlying antecedents of the diagnoses (i.e., predisposing, disabling, precipitating, or reinforcing factors) (de Oliveira Lopes et al., 2017), these diagnostic indicators have been objects of numerous studies, along with the essential diagnostic attributes (Ferreira et al., 2020;Mangueira Sde & Lopes, 2016;Neves da Costa et al., 2020;Paganin & Rabelo, 2013;Santos et al., 2020;Silva et al., 2020). Moreover, the systematic inclusion of nursing diagnoses in electronic health records have been shown to enhance the predictive ability of clinical data regarding length of hospital stay, inhospital mortality and use of healthcare resources (Company-Sancho et al., 2017;D'Agostino et al., 2019;Sanson et al., 2019;Sanson et al, 2017). In addition, the use of the nursing process documented with the standardized nursing languages provides more coverage for all health promotion and prevention services in primary health care (Pérez Rivas et al., 2016). ...
Article
Purpose Heart failure is a highly prevalent chronic health problem associated with poor quality‐of‐life and negative outcomes. Self‐care is a cornerstone in patients suffering from heart failure. Nurses are commonly engaged in enhancing patients’ self‐care behaviors, but the specific condition of deficit on self‐care is not clearly identified by nurses. No nursing diagnoses focused on self‐care of heart failure patients is currently available. This study aimed to develop a new nursing diagnosis that focuses on self‐care in heart failure patients. Data sources A concept and content analysis were used. Some steps of the concept analysis were performed through an integrative literature review conducted searching in PUBMED and CINAHL databases to identify attributes, antecedents, and consequences of the diagnosis. Forty‐five articles were selected from the 1450 studies found. Then, the content analysis was performed by an international panel of 29 experts. Two Delphi rounds were used to achieve consensus and an item content validity index was calculated for each diagnostic element. Data synthesis Integrative review proposed four diagnostic labels, two definitions, 15 defining characteristics, and 44 related factors. After the two Delphi rounds a consensus was reached for each diagnostic indicator with a content validity index ranging from 82.8% to 100%. The nursing diagnosis—labeled heart failure self‐care deficit—was validated with a definition, eight defining characteristics, 15 related factors, and five at‐risk populations. Conclusions This diagnosis allows nurses to document patients’ self‐care in daily clinical practice through a standard nursing terminology, by naming this health problem, describing its etiology, and clinical manifestations. Implications for nursing practice This new diagnosis is expected to assist nursing clinicians, educators, and students in clinical reasoning with the aim to improve diagnostic accuracy in identifying patients with a heart failure self‐care deficit, to select the most appropriate interventions and pursue better outcomes.
... Numerous studies propose different explanatory models of hospital mortality [16][17][18][19]. These studies show that in-hospital mortality is influenced by numerous different factors and should be assessed with due consideration of a wide range of potential confounds including patient's factors (individual and clinical) and hospital-related factors [20]. ...
Article
Full-text available
Background: In-hospital mortality is a key indicator of the quality of care. Studies so far have demonstrated the influence of patient and hospital-related factors on in-hospital mortality. Currently, new variables, such as nursing workload or the level of dependency, are being incorporated. We aimed to identify which individual, clinical and hospital characteristics are related to hospital mortality. Methods: A multicentre prospective observational study design was used. Sampling was conducted between February 2015 and October 2017. Patients over 16 years, admitted to medical or surgical units at 11 public hospitals in Andalusia (Spain), with a foreseeable stay of at least 48 h were included. Multivariate regression analyses were performed to analyse the data. Results: The sample consisted of 3821 assessments conducted in 1004 patients. The mean profile was that of a male (52%), mean age of 64.5 years old, admitted to a medical unit (56.5%), with an informal caregiver (60%). In-hospital mortality was 4%. The INICIARE (Inventario del Nivel de Cuidados Mediante Indicadores de Clasificación de Resultados de Enfermería) scale yielded an adjusted odds ratio [AOR] of 0.987 (95% confidence interval [CI]: 0.97–0.99) and the nurse staffing level (NSL) yielded an AOR of 1.197 (95% CI: 1.02–1.4). Conclusion: Nursing care dependency measured by INICIARE and nurse staffing level was associated with in-hospital mortality.
... In addition, several studies found that NDs are an independent predictor of patient hospital outcomes (e.g. patient mortality) and should be included in the hospital discharge abstract as a complement to the medical Diagnosis Related Groups [12][13][14]. Education, together with adequate nurse staffing and an enhanced care environment, contributes to better patient outcomes [7]. Consequently, nursing students education on accurate clinical reasoning using SNL represents the first step to allowing future nurses to make the difference on clinical practice outcomes [15]. ...
Chapter
Nursing process has a relevant impact on overall quality of healthcare services and patient outcomes, however nursing contribution appears to be almost ‘invisible’. Use of an international Standardized Nursing Language (SNL), as NANDA-I NOC NIC (NNN) taxonomy, allows making nursing visible in education, practice and research with final better outcomes on patients. Electronic Health Record (EHR) could facilitate learning of standardized languages in nursing undergraduate students, but only few studies analyzed it. This paper aims to report the experience of the ‘Caring project’ utilizing a SNL in an Italian healthcare setting and to discuss potentialities of EHR in improving nursing education and practice. ‘Caring project’ was an Italian pilot observational study, conducted on 231 patients of 8 Units retrospectively (January 2018–March 2019), using a ‘paper’ assessment form with Gordon’s Functional Health Patterns (FHPs) and an Individual Care Plan (ICP), an ‘Excel® based health record prototype’. In the study a total of 484 Nursing Diagnosis (NDs) has been identified, corresponding to a mean of 2.0 ± 1.5 NDs/patient. Integration of SNL with EHRs could help nurses to use a holistic approach and, in nursing education, it could improve undergraduate students clinical reasoning skills. Further researches are necessary in this subject, in particular regarding the nursing diagnostic accuracy.
... Numerous studies propose different explanatory models of hospital mortality [16][17][18][19]. These studies show that in-hospital mortality is influenced by numerous different factors and should be assessed with due consideration of a wide range of potential confounds including patient's factors (individual and clinical) and hospital-related factors [20]. ...
Article
RESUMO Objetivos: compreender a percepção dos enfermeiros da Atenção Primária à Saúde sobre a aplicação do Processo de Enfermagem. Métodos: estudo qualitativo, descritivo. Os dados foram coletados por entrevistas semiestruturadas com enfermeiros da Atenção Primária à Saúde de uma cidade do interior do estado de São Paulo, analisados pela Análise de Conteúdo sob o referencial teórico de Processo de Trabalho. Resultados: obtiveram-se três categorias: Fatores extrínsecos ao Processo de Enfermagem; Fatores intrínsecos ao Processo de Enfermagem; e Saber. Considerações Finais: os enfermeiros consideraram o Processo de Enfermagem relevante para a profissão, mas questões de ordem histórica, política e social relativas à enfermagem e à saúde, bem como conflitos quanto ao seu conceito e à formação acadêmica, dificultam sua aplicação.
Article
Data science continues to be recognized and used within healthcare due to the increased availability of large data sets and advanced analytics. It can be challenging for nurse leaders to remain apprised of this rapidly changing landscape. In this article, we describe our findings from a scoping literature review of papers published in 2019 that use data science to explore, explain, and/or predict 15 phenomena of interest to nurses. Fourteen of the 15 phenomena were associated with at least one paper published in 2019. We identified the use of many contemporary data science methods (eg, natural language processing, neural networks) for many of the outcomes. We found many studies exploring Readmissions and Pressure Injuries. The topics of Artificial Intelligence/Machine Learning Acceptance, Burnout, Patient Safety, and Unit Culture were poorly represented. We hope that the studies described in this article help readers: (1) understand the breadth and depth of data science's ability to improve clinical processes and patient outcomes that are relevant to nurses and (2) identify gaps in the literature that are in need of exploration.
Article
Purpose: To analyze the accuracy of nursing diagnoses determined by users of a clinical decision support system (CDSS) and to identify the predictive factors of high/moderate diagnostic accuracy. Methods: This is an exploratory-descriptive study carried out from September 2017 to January 2018. Participants were nurses, resident nurses, and senior year undergraduates. Two written case studies provided the participants with the clinical data to fill out the assessment forms in the CDSS. The accuracy of the selected diagnostic labels was determined by a panel of experts using the Diagnostic Accuracy Scale, Version 2. Descriptive statistics were used to describe the level of accuracy according to each group of participants. Analysis of variance was used to compare the mean percentages of accuracy categories across groups. A linear regression model was used to identify the predictors of diagnostic accuracy. The significance level was 5%. The study was approved by the Ethics Committee. Results: Fifteen undergraduates, 10 residents, and 22 nurses were enrolled in the study. Although resident nurses and students had selected predominantly highly accurate diagnoses (51.8 ± 19.1 and 48.9 ± 27.4, respectively), and nurses had selected mostly diagnoses of moderate accuracy (54.7 ± 14.7), there were no differences in the accuracy level of selected diagnoses across groups. According to the linear regression model, each diagnosis added by the participants decreased the diagnostic accuracy by 2.09% (p = .030), and no experience or a low level of experience using the system decreased such diagnostic accuracy by 5.41% (p = .022). Conclusions: The CDSS contributes to decision making about diagnoses of less experienced people. Adding diagnoses not indicated by the CDSS and experience with the system are predictors of diagnostic accuracy. Clinical relevance: In-service education regarding the use of CDSSs seems to be crucial to improve users' clinical judgment and decision making.
Article
Full-text available
Objectives: Previous studies regarding nursing documentation focused primarily on documentation quality, for instance, in terms of the accuracy of the documentation. The combination between accuracy measurements and the quality and frequencies of outcome variables such as the length of the hospital stay were only minimally addressed. Method: An audit of 300 randomly selected digital nursing records of patients (age of >70 years) admitted between 2013-2014 for hip surgery in two orthopaedic wards of a general Dutch hospital was conducted. Results: Nursing diagnoses: Impaired tissue perfusion (wound), Pressure ulcer, and Deficient fluid volume had significant influence on the length of the hospital stay. Conclusion: Nursing process documentation can be used for outcome calculations. Nevertheless, in the first generation of electronic health records, nursing diagnoses were not documented in a standardized manner (First generation 2010-2015; the first generation of electronic records implemented in clinical practice in the Netherlands).
Article
Full-text available
The aim of this study is to explore the relations of workplace culture on nursing-sensitive organizational factors. The need for standardized and valid measures for nursing-sensitive organizational outcomes has already been recognized in the literature. A cross-sectional questionnaire survey of 21 inpatient acute care units in 9 organizations at the municipal primary healthcare level was conducted. Participants included licensed practical nurses, registered nurses, and nurse managers. Workplace culture, especially the overarching factor of stress, correlated with the use of supplemental nursing staff and patients' length of stay. It is essential to find and test workplace-sensitive indicators so that managers will have a wider range of methods to plan and evaluate nursing outcomes.
Article
Full-text available
Risk stratification is nowadays crucial when estimating the patient's prognosis in terms of treatment outcome and it also helps in clinical decision making. Several risk assessment models have been developed to predict short-term outcomes in patients with acute coronary syndrome. This study was aimed at developing an outcome prediction model for patients with acute coronary syndrome submitted to percutaneus coronary intervention using data mining approach. A total of 2030 patients hospitalized for acute coronary syndrome and treated with percutaneous coronary intervention from December 2008 to December 2011 were assigned to a derivation cohort. Demographic and anamnestic data, clinical characteristics on admission, biochemical analysis of blood parameters on admission, and left ventricular ejection fraction formed the basis ofthe study. A number of machine learning algorithms available within Waikato Environment for Knowledge Discovery had been evaluated and the most successful was chosen. The predictive model was subsequently validated in a different population of 931 patients (validation cohort), hospitalized during 2012. The best prediction results were achieved using Alternating Decision Tree classifier, which was able to predict in-hospital mortality with 89% accuracy, and preserved good performance on validation cohort with 87% accuracy. Alternating Decision Tree classifier identified a subset of 6 attributes most relevant to mortality prediction: systolic and diastolic blood pressure, heart rate, left ventricular ejection fraction, age, and troponin value. Data mining approach enabled the authors to develop a model capable of predicting the in-hospital outcome following percutaneous coronary intervention. The model showed excellent sensitivity and specificity during internal validation.
Article
Full-text available
To describe the promise and potential of big data analytics in healthcare. The paper describes the nascent field of big data analytics in healthcare, discusses the benefits, outlines an architectural framework and methodology, describes examples reported in the literature, briefly discusses the challenges, and offers conclusions. The paper provides a broad overview of big data analytics for healthcare researchers and practitioners. Big data analytics in healthcare is evolving into a promising field for providing insight from very large data sets and improving outcomes while reducing costs. Its potential is great; however there remain challenges to overcome.
Article
Full-text available
Objective To determine the state of the science for the five standardized nursing terminology sets in terms of level of evidence and study focus. Design Systematic Review. Data sources: Keyword search of PubMed, CINAHL, and EMBASE databases from 1960s to March 19, 2012 revealed 1,257 publications. Review Methods: From abstract review we removed duplicate articles, those not in English or with no identifiable standardized nursing terminology, and those with a low-level of evidence. From full text review of the remaining 312 articles, eight trained raters used a coding system to record standardized nursing terminology names, publication year, country, and study focus. Inter-rater reliability confirmed the level of evidence. We analyzed coded results. Results On average there were 4 studies per year between 1985 and 1995. The yearly number increased to 14 for the decade between 1996-2005, 21 between 2006-2010, and 25 in 2011. Investigators conducted the research in 27 countries. By evidence level for the 312 studies 72.4% were descriptive, 18.9% were observational, and 8.7% were intervention studies. Of the 312 reports, 72.1% focused on North American Nursing Diagnosis-International, Nursing Interventions Classification, Nursing Outcome Classification, or some combination of those three standardized nursing terminologies; 9.6% on Omaha System; 7.1% on International Classification for Nursing Practice; 1.6% on Clinical Care Classification/Home Health Care Classification; 1.6% on Perioperative Nursing Data Set; and 8.0% on two or more standardized nursing terminology sets. There were studies in all 10 foci categories including those focused on concept analysis/classification infrastructure (n = 43), the identification of the standardized nursing terminology concepts applicable to a health setting from registered nurses’ documentation (n = 54), mapping one terminology to another (n = 58), implementation of standardized nursing terminologies into electronic health records (n = 12), and secondary use of electronic health record data (n = 19). Conclusions Findings reveal that the number of standardized nursing terminology publications increased primarily since 2000 with most focusing on North American Nursing Diagnosis-International, Nursing Interventions Classification, and Nursing Outcome Classification. The majority of the studies were descriptive, qualitative, or correlational designs that provide a strong base for understanding the validity and reliability of the concepts underlying the standardized nursing terminologies. There is evidence supporting the successful integration and use in electronic health records for two standardized nursing terminology sets: (1) the North American Nursing Diagnosis-International, Nursing Interventions Classification, and Nursing Outcome Classification set; and (2) the Omaha System set. Researchers, however, should continue to strengthen standardized nursing terminology study designs to promote continuous improvement of the standardized nursing terminologies and use in clinical practice.
Article
Full-text available
The path to improving healthcare quality for individuals with complex health conditions is complicated by a lack of common understanding of complexity. Modern medicine, together with social and environmental factors, has extended life, leading to a growing population of patients with chronic conditions. In many cases, there are social and psychological factors that impact treatment, health outcomes, and quality of life. This is the face of complexity. Care challenges, burden, and cost have positioned complexity as an important health issue. Complex chronic conditions are now being discussed by clinicians, researchers, and policy-makers around such issues as quantification, payment schemes, transitions, management models, clinical practice, and improved patient experience. We conducted a scoping review of the literature for definitions and descriptions of complexity. We provide an overview of complex chronic conditions, and what is known about complexity, and describe variations in how it is understood. We developed a Complexity Framework from these findings to guide our approach to understanding patient complexity. It is critical to use common vernacular and conceptualization of complexity to improve service and outcomes for patients with complex chronic conditions. Many questions still persist about how to develop this work with a health and social care lens; our framework offers a foundation to structure thinking about complex patients. Further insight into patient complexity can inform treatment models and goals of care, and identify required services and barriers to the management of complexity. Journal of Comorbidity 2012;2:1–9
Article
Full-text available
The hospital standardized mortality ratio (HSMR) is developed to evaluate and improve hospital quality. Different methods can be used to standardize the hospital mortality ratio. Our aim was to assess the validity and applicability of directly and indirectly standardized hospital mortality ratios. Retrospective scenario analysis using routinely collected hospital data to compare deaths predicted by the indirectly standardized case-mix adjustment method with observed deaths. Discharges from Dutch hospitals in the period 2003-2009 were used to estimate the underlying prediction models. We analysed variation in indirectly standardized hospital mortality ratios (HSMRs) when changing the case-mix distributions using different scenarios. Sixty-one Dutch hospitals were included in our scenario analysis. A numerical example showed that when interaction between hospital and case-mix is present and case-mix differs between hospitals, indirectly standardized HSMRs vary between hospitals providing the same quality of care. In empirical data analysis, the differences between directly and indirectly standardized HSMRs for individual hospitals were limited. Direct standardization is not affected by the presence of interaction between hospital and case-mix and is therefore theoretically preferable over indirect standardization. Since direct standardization is practically impossible when multiple predictors are included in the case-mix adjustment model, indirect standardization is the only available method to compute the HSMR. Before interpreting such indirectly standardized HSMRs the case-mix distributions of individual hospitals and the presence of interactions between hospital and case-mix should be assessed.
Article
Full-text available
The accuracy of binary discrimination models (discrimination between cases with and without any condition) is usually summarized by classification matrix (also called a confusion, assignment, or prediction matrix). Receiver operating characteristic (ROC) curve can visualize the association between probabilities of incorrect classification of cases from the group without condition (False Positives) versus the probabilities of correct classification of cases from the group with condition (True Positives) across all the possible cut-point values of discrimination score. Area under ROC curve (AUC) is one of summary measures. This article describes the possibility of AUC estimate with the use of web based application of bootstrap (resampling). Bootstrap is useful mainly to data for which any distributional assumptions are not appropriate. The quality of the bootstrap application was evaluated with the use of a special programme written in C#.NET language that allows to automate the process of repeating different experiments. Estimates of AUC and confidence limits given by bootstrap method were compared with bi-normal and nonparametric estimates. Results indicate that usually bootstrap confidence intervals are narrower than nonparametric one, mainly for small data samples.
Article
Full-text available
Background When outcomes are binary, the c-statistic (equivalent to the area under the Receiver Operating Characteristic curve) is a standard measure of the predictive accuracy of a logistic regression model. Methods An analytical expression was derived under the assumption that a continuous explanatory variable follows a normal distribution in those with and without the condition. We then conducted an extensive set of Monte Carlo simulations to examine whether the expressions derived under the assumption of binormality allowed for accurate prediction of the empirical c-statistic when the explanatory variable followed a normal distribution in the combined sample of those with and without the condition. We also examine the accuracy of the predicted c-statistic when the explanatory variable followed a gamma, log-normal or uniform distribution in combined sample of those with and without the condition. Results Under the assumption of binormality with equality of variances, the c-statistic follows a standard normal cumulative distribution function with dependence on the product of the standard deviation of the normal components (reflecting more heterogeneity) and the log-odds ratio (reflecting larger effects). Under the assumption of binormality with unequal variances, the c-statistic follows a standard normal cumulative distribution function with dependence on the standardized difference of the explanatory variable in those with and without the condition. In our Monte Carlo simulations, we found that these expressions allowed for reasonably accurate prediction of the empirical c-statistic when the distribution of the explanatory variable was normal, gamma, log-normal, and uniform in the entire sample of those with and without the condition. Conclusions The discriminative ability of a continuous explanatory variable cannot be judged by its odds ratio alone, but always needs to be considered in relation to the heterogeneity of the population.
Article
Full-text available
To develop a transparent and reproducible measure for hospitals that can indicate when deaths in hospital or within 30 days of discharge are high relative to other hospitals, given the characteristics of the patients in that hospital, and to investigate those factors that have the greatest effect in changing the rank of a hospital, whether interactions exist between those factors, and the stability of the measure over time. Retrospective cross sectional study of admissions to English hospitals. Hospital episode statistics for England from 1 April 2005 to 30 September 2010, with linked mortality data from the Office for National Statistics. 36.5 million completed hospital admissions in 146 general and 72 specialist trusts. Deaths within hospital or within 30 days of discharge from hospital. The predictors that were used in the final model comprised admission diagnosis, age, sex, type of admission, and comorbidity. The percentage of people admitted who died in hospital or within 30 days of discharge was 4.2% for males and 4.5% for females. Emergency admissions comprised 75% of all admissions and 5.5% died, in contrast to 0.8% who died after an elective admission. The percentage who died with a Charlson comorbidity score of 0 was 2% in contrast with 15% who died with a score greater than 5. Given these variables, the relative standardised mortality rates of the hospitals were not noticeably changed by adjusting for the area level deprivation and number of previous emergency visits to hospital. There was little evidence that including interaction terms changed the relative values by any great amount. Using these predictors the summary hospital mortality index (SHMI) was derived. For 2007/8 the model had a C statistic of 0.911 and accounted for 81% of the variability of between hospital mortality. A random effects funnel plot was used to identify outlying hospitals. The outliers from the SHMI over the period 2005-10 have previously been identified using other mortality indicators. The SHMI is a relatively simple tool that can be used in conjunction with other information to identify hospitals that may need further investigation.
Article
Full-text available
With advances in the effectiveness of treatment and disease management, the contribution of chronic comorbid diseases (comorbidities) found within the Charlson comorbidity index to mortality is likely to have changed since development of the index in 1984. The authors reevaluated the Charlson index and reassigned weights to each condition by identifying and following patients to observe mortality within 1 year after hospital discharge. They applied the updated index and weights to hospital discharge data from 6 countries and tested for their ability to predict in-hospital mortality. Compared with the original Charlson weights, weights generated from the Calgary, Alberta, Canada, data (2004) were 0 for 5 comorbidities, decreased for 3 comorbidities, increased for 4 comorbidities, and did not change for 5 comorbidities. The C statistics for discriminating in-hospital mortality between the new score generated from the 12 comorbidities and the Charlson score were 0.825 (new) and 0.808 (old), respectively, in Australian data (2008), 0.828 and 0.825 in Canadian data (2008), 0.878 and 0.882 in French data (2004), 0.727 and 0.723 in Japanese data (2008), 0.831 and 0.836 in New Zealand data (2008), and 0.869 and 0.876 in Swiss data (2008). The updated index of 12 comorbidities showed good-to-excellent discrimination in predicting in-hospital mortality in data from 6 countries and may be more appropriate for use with more recent administrative data.
Article
Full-text available
Most efforts to modify the diagnosis-related group (DRG) case classification system focus on variables related to medical management. In this study, we investigated the separate but related natures of medicine and nursing by examining 1,288 adult medical and surgical patients in an urban teaching hospital. The complexity of medical treatment was measured by use of the DRG relative cost weight. The nursing indicator was derived from a set of nursing diagnoses. We found that the DRG cost weight is a poor predictor of nursing dependency and that the nursing dependence index added significantly to the DRG weight in explaining length of stay.
Article
Full-text available
To ascertain hospital inpatient mortality in England and to determine which factors best explain variation in standardised hospital death ratios. Design: Weighted linear regression analysis of routinely collected data over four years, with hospital standardised mortality ratios as the dependent variable. England. Subjects: Eight million discharges from NHS hospitals when the primary diagnosis was one of the diagnoses accounting for 80% of inpatient deaths. Main outcome measures: Hospital standardised mortality ratios and predictors of variations in these ratios. The four year crude death rates varied across hospitals from 3.4% to 13.6% (average for England 8.5%), and standardised hospital mortality ratios ranged from 53 to 137 (average for England 100). The percentage of cases that were emergency admissions (60% of total hospital admissions) was the best predictor of this variation in mortality, with the ratio of hospital doctors to beds and general practitioners to head of population the next best predictors. When analyses were restricted to emergency admissions (which covered 93% of all patient deaths analysed) number of doctors per bed was the best predictor. Analysis of hospital episode statistics reveals wide variation in standardised hospital mortality ratios in England. The percentage of total admissions classified as emergencies is the most powerful predictor of variation in mortality. The ratios of doctors to head of population served, both in hospital and in general practice, seem to be critical determinants of standardised hospital death rates; the higher these ratios, the lower the death rates in both cases.
Article
Full-text available
The Centers for Medicare and Medicaid Services has begun an ambitious recalibration of the inpatient prospective payment system, the first since its introduction in 1983. Unfortunately, inpatient nursing care has been overlooked in the new payment system and continues to be treated as a fixed cost and billed at a set per-diem "room and board" fee despite the known variability of nursing intensity across different care settings and diagnoses. This article outlines the historical influences regarding costing, billing, and reimbursement of inpatient nursing care and provides contemporary evidence about the variability of nursing intensity and costs at acute care hospitals in the United States. A remedy is proposed to overcome the existing limitations of the Inpatient Prospective Payment System by creating a new nursing cost center and nursing intensity adjustment by DRG for each routine-and intensive-care day of stay to allow independent costing, billing, and reimbursement of inpatient nursing care.
Article
Purpose: To investigate whether the number of nursing diagnoses on hospital admission is an independent predictor of the hospital length of stay. Design: A prospective observational study was carried out. A sample of 2,190 patients consecutively admitted (from July to December 2014) in four inpatient units (two medical, two surgical) of a 1,547-bed university hospital were enrolled for the study. Methods: Data were collected from a clinical nursing information system and the hospital discharge register. Two regression analyses were performed to investigate if the number of nursing diagnoses on hospital admission was an independent predictor of length of stay and length of stay deviation after controlling for patients' sociodemographic characteristics (age, gender), clinical variables (disease groupers, disease severity morbidity indexes), and organizational hospital variables (admitting inpatient unit, modality of admission). Findings: The number of nursing diagnoses was shown to be an independent predictor of both the length of stay (β = .15; p < .001) and the length of stay deviation (β = .19; p < .001). Conclusions: The number of nursing diagnoses is a strong independent predictor of an effective hospital length of stay and of a length of stay longer than expected. Clinical relevance: The systematic inclusion of standard nursing care data in electronic health records can improve the predictive ability on hospital outcomes and describe the patient complexity more comprehensively, improving hospital management efficiency.
Article
Nursing care documentation in electronic health records (EHRs) with standardized nursing terminologies (SNTs) can facilitate nursing's participation in big data science that involves combining and analyzing multiple sources of data. Before merging SNTs data with other sources, it is important to understand how such data are being used and analyzed to support nursing practice. The main purpose of this systematic review was to identify studies using SNTs data, their aims and analytical methods. A two-phase systematic process resulted in inclusion and review of 35 publications. Aims of the studies ranged from describing most popular nursing diagnoses, outcomes, and interventions on a unit to predicting outcomes using multi-site data. Analytical techniques varied as well and included descriptive statistics, correlations, data mining, and predictive modeling. The review underscored the value of developing a deep understanding of the meaning and potential impact of nursing variables before merging with other sources of data.
Article
Background: The use of electronic clinical and administrative data can be an advantageous source of information for assessing nursing performance in primary care. In Québec (Canada), the I-CLSC electronic database could be used to measure performance indicators. However, little is known about the reliability of the data contained in this database. The objective of this study was to assess the reliability of the clinical and administrative data contained in the I-CLSC electronic database based on the data entered in medical records. Methods: We used a longitudinal design for this study. A sample of 100 patients who had experienced 107 episodes of wound care were randomly selected from all patients who had two or more consultations during the year 2015. The paper records were used as reference. We collected data regarding eight nursing sensitive indicators from both sources. We assessed the concordance between the electronic data and the paper records by measuring inter-rater agreement. Results: Six of the eight indicators showed a percentage agreement ≥ 85%, and kappa scores between 0.7 and 1.00 (p < 0.001), indicating high to perfect levels of agreement between the two data sources. Two indicators presented fair kappa scores. Conclusion: This database provides reliable data relating to the organization of care but shows lower reliability for specific acts performed by nurses in primary care. This existing database can be used to assess, manage and improve certain dimensions of nursing performance in primary care.
Article
Background: Oncological diseases affect the biopsychosocial aspects of a person's health, resulting in the need for complex multidisciplinary care. The quality and outcomes of healthcare cannot be adequately assessed without considering the contribution of nursing care, whose essential elements such as the nursing diagnoses (NDs), nursing interventions (NIs), and nursing activities (NAs) can be recorded in the Nursing Minimum Data Set (NMDS). There has been little research using the NMDS in oncology setting. Objective: The aim of this study was to describe the prevalence and distribution of NDs, NIs, and NAs and their relationship across patient age and medical diagnoses. Methods: This was a prospective observational study. Data were collected between July and December 2014 through an NMDS and the hospital discharge register in an Italian hospital oncology unit. Results: On average, for each of 435 enrolled patients, 5.7 NDs were identified on admission; the most frequent ND was risk for infection. During the hospital stay, 16.2 NIs per patient were planned, from which 25.2 NAs per day per patient were delivered. Only a third of NAs were based on a medical order, being the highest percentage delivered on nursing prescriptions. The number of NDs, NIs, and NAs was not related to patient age, but differed significantly among medical diagnoses. Conclusions: An NMDS can depict patient needs and nursing care delivered in oncology patients. Such data can effectively describe nursing contribution to patient care. Implications for practice: The use of an NMDS raises the visibility of nursing care in the clinical records. Such data enable comparison and benchmarking with other healthcare professions and international data.
Article
As we move toward a value-based health care system and payment models based on individual performance of providers, nurses are faced with a dilemma. Should we as a profession actively pursue the development of individual nurse performance metrics, analysis, benchmarks, and practice standards, similar to those being implemented for physicians? Or should we wait until these metrics are imposed by payers and policymakers with little or no input from nurses?
Article
Purpose: To determine the acceptability, usefulness, and ease of use for four nursing clinical decision support interface prototypes. Methods: In a simulated hospital environment, 60 registered nurses (48 female; mean age = 33.7 ± 10.8; mean years of experience = 8.1 ± 9.7) participated in a randomized study with four study groups. Measures included acceptability, usefulness, and ease of use scales. Findings: Mean scores were high for acceptability, usefulness, and the ease of use for all four groups. Inexperienced participants (<1 year) reported higher perceived ease of use (p = .05) and perceived usefulness (p = .01) than those with experience of 1 year or more. Conclusions: Participants completed the protocol and reported that all four interfaces, including the control (HANDS), were acceptable, easy to use, and useful. Implications for nursing knowledge: Further study is warranted before clinical implementation within the electronic health record.
Article
Aim and objectives: To investigate the impact of nursing diagnoses on patient and organisational outcomes in any field of healthcare where nurses are involved. Background: In healthcare systems, descriptions of patient complexity and outcomes and payment criteria are primarily based on medical diagnoses and procedures. Other aspects of patient care are rarely considered. Nursing diagnoses are believed to be related to healthcare outcomes, but comprehensive evidence for this association is missing. Design: Systematic literature review. Methods: The search was conducted in PubMed, CINAHL and Scopus databases without year or language limitations. The studies were categorised according to their methodological quality (low, good or high) and classified based on their levels of evidence on a scale of 1 (strongest evidence) to 5 (weakest evidence). Results: Seventeen of 3,426 potentially relevant studies met the eligibility criteria. Eleven studies were classified as low, five as good and one as high quality. The levels of evidence were rated as 2 for one study, 3 for two studies, 4 for nine studies and 5 for five studies. Nursing diagnoses were found to predict patient (quality of life, mortality) and organisational (length of hospital stay, hospital charges, amount of nursing care, discharge dispositions) outcomes. Patient care plans based on nursing diagnoses improved sleep quality, quality of life and glycaemic control. When added to information from disease-based classification systems (e.g., diagnosis-related groups), nursing diagnoses improved the predictions of the above outcomes. Conclusions: Nursing diagnoses have a great potential to predict patient and organisational outcomes. High-quality research is required to better investigate the existence and strength of these relationships. This article is protected by copyright. All rights reserved.
Article
Despite an unprecedented amount of health-related data being amassed from various technological innovations, our ability to process this data and extract hidden knowledge has yet to catch up with this explosive growth. Although nursing care plans can be an effective tool to support the achievement of desired patient outcomes, their online collection, storage, and processing is lagging far behind. As a result, the impact of nursing care is not well understood from qualitative as well as quantitative perspectives. In this article, we first outline a complete life cycle of nursing care data, and present a knowledge discovery and analysis framework for such data sets. We also highlight Big Data issues pertaining to the analysis of nursing care data. Using an exemplar data set, we demonstrate the broad applicability of the proposed framework by showing knowledge discovery results for different outcomes related to patients, nursing staff, and administrators.
Article
Nurses are accountable to apply the nursing process, which is key for patient care: It is a problem-solving process providing the structure for care plans and documentation. The state-of-the art nursing process is based on classifications that contain standardized concepts, and therefore, it is named Advanced Nursing Process. It contains valid assessments, nursing diagnoses, interventions, and nursing-sensitive patient outcomes. Electronic decision support systems can assist nurses to apply the Advanced Nursing Process. However, nursing decision support systems are missing, and no "gold standard" is available. The study aim is to develop a valid Nursing Process-Clinical Decision Support System Standard to guide future developments of clinical decision support systems. In a multistep approach, a Nursing Process-Clinical Decision Support System Standard with 28 criteria was developed. After pilot testing (N = 29 nurses), the criteria were reduced to 25. The Nursing Process-Clinical Decision Support System Standard was then presented to eight internationally known experts, who performed qualitative interviews according to Mayring. Fourteen categories demonstrate expert consensus on the Nursing Process-Clinical Decision Support System Standard and its content validity. All experts agreed the Advanced Nursing Process should be the centerpiece for the Nursing Process-Clinical Decision Support System and should suggest research-based, predefined nursing diagnoses and correct linkages between diagnoses, evidence-based interventions, and patient outcomes. Copyright
Article
Purpose: To develop methods for rapid and simultaneous design, testing, and management of multiple clinical decision support (CDS) features to aid nurse decision-making. Methods: We used quota sampling, think-aloud and cognitive interviews, and deductive and inductive coding of synchronized audio video data and archival libraries. Findings: Our methods and organizational tools allowed us to rapidly improve the usability, understandability, and usefulness of CDS in a generalizable sample of practicing nurses. Conclusions: The method outlined allows the rapid integration of nursing terminology based electronic health record data into routine workflow and holds strong potential for improving patient outcomes. Implications for nursing practice: The methods and organizational tools for development of multiple CDS system features can be used to translate knowledge into practice.
Article
Aims: To describe the nursing diagnoses, outcomes and interventions for patients admitted to intensive care units and to assess their possible relation with classical outcomes like length of stay and mortality. Background: The analysis of nursing diagnosis frequencies may help to estimate the patients' complexity and the need for nursing interventions and can predict hospital outcomes. Nonetheless, few studies were conducted on critical patients. Design: Prospective cohort observational study. Methods: Between 15 July-31 October 2013 we collected the above-described nursing parameters of 100 subjects throughout their stay in intensive care. We classified the parameters according to established taxonomies. The independent association between the number of nursing diagnoses and length of stay/mortality was investigated with multiple regressions. Results: We found an average of 19 diagnoses, 24 outcomes and 60 interventions per patient. Most frequently, the plans of care involved support for self-care deficits or interrupted family processes. They also included strategies to prevent infection, disuse syndrome and impairment of skin integrity. Nineteen nursing diagnoses were significantly related with mortality or length of stay in bivariate analyses. In regression models, the number of such diagnoses explained 29·7% of the variance in length of stay and was an independent predictor of mortality. Conclusion: In critically ill patients, the analysis of nursing diagnoses, outcomes and interventions confirmed an intense activity in response to a broad spectrum of patient needs. The number of nursing diagnoses allowed to predict patient outcomes.
Article
Today's consumers purchasing any product or service are armed with information and have high expectations. They expect service providers and payers to know about their unique needs. Data-driven decisions can help organizations meet those expectations and fulfill those needs.Health care, however, is not strictly a retail relationship-the sacred trust between patient and doctor, the clinician-patient relationship, must be preserved. The opportunities and challenges created by the digitization of health care are at the crux of the most crucial strategic decisions for academic medicine. A transformational vision grounded in data and analytics must guide health care decisions and actions.In this Commentary, the authors describe three examples of the transformational force of data and analytics to improve health care in order to focus attention on academic medicine's vital role in guiding the needed changes.
Article
The aim of this study was to report an analysis of the concept of patient safety. Despite recent increase in the number of work being done to clarify the concept and standardize measurement of patient safety, there are still huge variations in how the term is conceptualized and how to measure patient safety data across various healthcare settings and in research. Concept analysis. A literature search was conducted through PubMed and Cumulative Index to Nursing and Allied Health Literature, Plus using the terms 'patient safety' in the title and 'concept analysis,' 'attributes' or 'definition' in the title and or abstract. All English language literature published between 2002-2014 were considered for the review. Walker and Avant's method guided this analysis. The defining attributes of patient safety include prevention of medical errors and avoidable adverse events, protection of patients from harm or injury and collaborative efforts by individual healthcare providers and a strong, well-integrated healthcare system. The application of Collaborative Alliance of Nursing Outcomes indicators as empirical referents would facilitate the measurement of patient safety. With the knowledge gained from this analysis, nurses may improve patient surveillance efforts that identify potential hazards before they become adverse events and have a stronger voice in health policy decision-making that influence implementation efforts aimed at promoting patient safety, worldwide. Further studies are needed on development of a conceptual model and framework that can aid with collection and measurement of standardized patient safety data. © 2015 John Wiley & Sons Ltd.
Article
Purpose: The purpose of the study is (a) to describe care needs derived from records of patients in Dutch hospitals, and (b) to evaluate whether nurses employed the NANDA-I classification to formulate patients' care needs. Methods: A stratified cross-sectional random-sampling nursing documentation audit was conducted employing the D-Catch instrument in 10 hospitals comprising 37 wards. Findings: The most prevalent nursing diagnoses were acute pain, nausea, fatigue, and risk for impaired skin integrity. Conclusions: Most care needs were determined in physiological health patterns and few in psychosocial patterns. Implications for nursing practice: To perform effective interventions leading to high-quality nursing-sensitive outcomes, nurses should also diagnose patients' care needs in the health management, value-belief, and coping stress patterns.
Article
The establishment of a Nursing Minimum Data Set (NMDS) can facilitate the use of health information systems. The adoption of these sets and represent them based on archetypes are a way of developing and support health systems. The objective of this paper is to describe the definition of a minimum data set for nursing in endometriosis represent with archetypes. The study was divided into two steps: Defining the Nursing Minimum Data Set to endometriosis, and Development archetypes related to the NMDS. The nursing data set to endometriosis was represented in the form of archetype, using the whole perception of the evaluation item, organs and senses. This form of representation is an important tool for semantic interoperability and knowledge representation for health information systems.
Article
Describe the development and validation of the Nursing Assessment Form (NAF), within a clinical nursing information system, to support nurses in the identification of nursing diagnoses. Content validity and consensus on NAF contents were established using a panel of experts in nursing diagnosis and Delphi rounds. Expert consensus was achieved to validate an instrument to support nurses in the process of nursing diagnoses identification. The use of the NAF can help nurses in diagnostic reasoning, facilitating the identification of the more suitable nursing diagnoses, and provide a basis for the best nursing interventions and outcomes. The use of computerized decision support can improve the implementation of standardized terminology and the accuracy of nursing diagnosis. Descrivere lo sviluppo e il processo di validazione della Scheda di Accertamento Infermieristico (SAI), contenuta all'interno di un sistema informativo infermieristico, ideata al fine di supportare gli infermieri nel processo di identificazione delle diagnosi infermieristiche. La validità di contenuto e il consenso sui contenuti della SAI sono state stabilite tramite un panel di esperti sulla diagnosi infermieristica e Delphi rounds. Un consenso di esperti è stato ottenuto al fine di validare uno strumento utile per supportare gli infermieri nel processo di identificazione delle diagnosi infermieristiche. L'uso della SAI può aiutare gli infermieri nel ragionamento diagnostico, facilitando l'identificazione delle diagnosi infermieristiche più adatte e fornire una base per i migliori interventi e risultati infermieristici. L'uso di sistemi di supporto decisionale computerizzati può favorire l'implementazione della terminologia standard e l'accuratezza della diagnosi infermieristica.
Article
To review nurse-sensitive indicators that may be suitable to assess nursing care quality. Patient safety concerns, fiscal pressures and patient expectation create a demand that healthcare providers demonstrate the quality of nursing care delivered. As a result, nurse managers are increasingly encouraged to provide evidence of nursing care quality. Nurse-sensitive indicators are being proposed as a means of meeting this need. Literature review. A review of the literature was conducted using CINAHL and MEDLINE from 2002-2011. Key search terms were nurs* and sensitive indicators, outcome measures, indicators, metrics and patient outcomes. Most of the research has examined the relationship between nursing structural variables and patient outcomes in acute care settings and have explored potential indicators for specific patient groups and nursing roles. When using nurse-sensitive indicators, issues concerning the selection, reporting and sustained use are important for nurse managers to consider. Evidence for the nurse-sensitivity of some commonly used indicators is inconsistent due to the disparity in definitions used, data collection and analysis methods. Further research on the application and implementation of these indicators is required to assist nurse managers in attempting to quantify the quality of nursing care. Nurses need to continue to strive to achieve agreement on the definitions of indicators, gather strong consistent evidence of nurse-sensitivity, resolve issues of regular data collection and consider selection, reporting and sustainment when implementing nurse-sensitive indicators. Once identified, nurse-sensitive indicators can be applied for quality improvement purposes, but consensus is required to fully realise their potential. Nurse managers need to be aware of the factors that can influence the use of indicators at unit level. Strategies need to be implemented to promote these indicators becoming integrated with routine nursing care.
Article
Prior studies have not examined the validity of severity of illness instruments in patients at low risk for mortality. We, therefore, examined the predictive validity of a newly developed instrument, the Nursing Severity Index in 5347 adult medical and surgical patients with musculoskeletal diagnoses admitted to an academic medical center in 1985–1988. The Index is based on aggregating 34 clinical observations which were recorded by primary nurses during patient care; observations reflect biologic, functional, cognitive and psychosocial abnormalities. Other data, including patient demographic data and outcomes were obtained from hospital data bases. We found that, among all study patients, admission Nursing Severity Index scores were highly related (p < 0.001) to in-hospital death rates—which were 0, 0.4, 0.8, 2.6, 6.7 and 23.5% in six hierarchical strata defined by the Index—and to nursing home discharge rates. In multivariate analyses, adjusting for diagnosis and other important covariates, each strata was associated with a 2.5-fold increased risk of mortality and a 1.6-fold increased risk of nursing home discharge. In addition, the Nursing Severity Index was an independent predictor (p < 0.001) of hospital charges and length of stay. We conclude that the Nursing Severity Index assesses multiple dimensions of illness, can be easily recorded during routine patient care, and accurately predicts hospital outcomes in an important ‘low risk’ group of patients. The validity of the Nursing Severity Index in other clinical subgroups should be further studied.
Article
Research on pressing health services and policy issues requires access to complete, accurate, and timely patient and organizational data. This paper describes how administrative and health records (including electronic medical records) can be linked for comparative effectiveness and health services research. We categorize the major agents (i.e., who owns and controls data and who carries out the data linkage) into three areas: (1) individual investigators; (2) government sponsored linked data bases; and (3) public-private partnerships that facilitate linkage of data owned by private organizations. We describe challenges that may be encountered in the linkage process, and the benefits of combining secondary databases with primary qualitative and quantitative sources. We use cancer care research to illustrate our points. To fill the gaps in the existing data infrastructure, additional steps are required to foster collaboration among institutions, researchers, and public and private components of the health care sector. Without such effort, independent researchers, governmental agencies, and nonprofit organizations are likely to continue building upon a fragmented and costly system with limited access. Discussion. Without the development and support for emerging information technologies across multiple health care settings, the potential for data collected for clinical and transactional purposes to benefit the research community and, ultimately, the patient population may go unrealized. The current environment is characterized by budget and technical challenges, but investments in data infrastructure are arguably cost-effective given the need to reform our health care system and to monitor the impact of health reform initiatives.
Article
This paper is a report of a study to investigate the effect of guided clinical reasoning. This method was chosen as a follow-up educational measure (refresher) after initial implementation of standardized language. Research has demonstrated nurses' need for education in diagnostic reasoning to state and document accurate nursing diagnoses, and to choose effective nursing interventions to attain favourable patient outcomes. In a cluster randomized controlled experimental study, nurses from three wards received guided clinical reasoning, an interactive learning method. Three wards, receiving classic case discussions, functioned as control group. Data were collected in 2004-2005. The quality of 225 randomly selected nursing records, containing 444 documented nursing diagnoses, corresponding interventions and outcomes was evaluated by applying 18 Likert-type items with a 0-4 scale of the instrument Quality of Nursing Diagnoses, Interventions and Outcomes. The effect of guided clinical reasoning was tested against classic case discussions using T-tests and mixed effects model analyses. The mean scores for nursing diagnoses, interventions and outcomes increased significantly in the intervention group. Guided clinical reasoning led to higher quality of nursing diagnosis documentation; to aetiology-specific interventions and to enhanced nursing-sensitive patient outcomes. In the control group, the quality was unchanged. Guided clinical reasoning supported nurses' abilities to state accurate nursing diagnoses, to select effective nursing interventions and to reach and document favourable patient outcomes. The results support the use of the North American Nursing Diagnosis Association, Nursing Interventions Classification and Nursing Outcomes Classification classifications and demonstrate implications for the electronic nursing documentation.
Article
The purpose of this study was to develop and validate the Nursing Severity Index, a new method used to measure the admission severity of illness of hospital patients using nursing diagnoses, which categorize biologic, functional, cognitive, and psychosocial abnormalities. This retrospective cohort study with independent development and testing phases was conducted at a U.S. academic medical center. In the development phase, data regarding 14,183 adult medicalsurgical patients admitted to the medical center in 1985 and 1986 was used. In the testing phase, data regarding 7,302 patients admitted in 1987 and 1988 was used. Primary nurses prospectively recorded the presence or absence of 61 nursing diagnoses on admission. Demographic and clinical data were obtained from hospital data bases. In the development phase, the number of admission nursing diagnoses was highly related (P < 0.001) to in-hospital mortality. Using multiple logistic regression, 34 nursing diagnoses were identified as independent predictors of mortality; the Nursing Severity Index equals the number of these 34 diagnoses. In the testing phase of 7,302 patients, the Nursing Severity Index was related (P < 0.001) to mortality rates, which were 0.5%, 1%, 2%, 6%, 13%, 22%, and 31% in seven hierarchical strata defined by the Index. The Index was as accurate in predicting mortality as MedisGroups (receiver-operatingcharacteristic curve areas, 0.814 +/- 0.016 vs. 0.845 +/- 0.015, respectively, P = 0.12). Furthermore, the Nursing Severity Index and MedisGroups together (receiver operating caracteristic curve area 0.880 +/- 0.014), were more accurate (P < 0.01) than either measure alone. The Nursing Severity Index assesses multiple dimensions of illness, can be easily measured during routine patient care, accurately predicts the risk of in-hospital death, and has similar prognostic accuracy as MedisGroups. Its usefulness in outcomes assessment, quality assurance, and case management merits further study.
Article
Diagnostic systems of several kinds are used to distinguish between two classes of events, essentially "signals" and "noise". For them, analysis in terms of the "relative operating characteristic" of signal detection theory provides a precise and valid measure of diagnostic accuracy. It is the only measure available that is uninfluenced by decision biases and prior probabilities, and it places the performances of diverse systems on a common, easily interpreted scale. Representative values of this measure are reported here for systems in medical imaging, materials testing, weather forecasting, information retrieval, polygraph lie detection, and aptitude testing. Though the measure itself is sound, the values obtained from tests of diagnostic systems often require qualification because the test data on which they are based are of unsure quality. A common set of problems in testing is faced in all fields. How well these problems are handled, or can be handled in a given field, determines the degree of confidence that can be placed in a measured value of accuracy. Some fields fare much better than others.
Article
There are no nursing centric data in the hospital discharge abstract. This study investigates whether adding nursing data in the form of nursing diagnoses to medical diagnostic data in the discharge abstract can improve overall explanation of variance in commonly studied hospital outcomes. A retrospective analyses of 123,241 sequential patient admissions to a university hospital in a Midwestern city was performed. Two data sets were combined: (1) a daily collection of patient assessments by nurses using nursing diagnosis terminology (NDX); and (2) the summary discharge information from the hospital discharge abstract including diagnosis-related group (DRG) and all payer refined DRG (APR-DRG). Each of 61 daily NDX observations were collapsed as frequency of occurrence for the hospital stay and inserted into the discharge abstract. NDX was then compared to both DRG and APR-DRG across 5 hospital outcome variables using multivariate regression or logistic regression. In all statistical models, DRG, APR-DRG, and NDX were significantly associated with the 5 hospital outcome variables (P <.0001). When NDX was added to models containing either the DRG or the APR-DRG, explanatory power (R2) and model discrimination (c statistic) improved by 30% to 146% across the outcome variables of hospital length of stay, ICU length of stay, total charges, probably of death, and discharge to a nursing home (P <.0001). The findings support the contention that nursing care is an independent predictor of patient hospital outcomes. These nursing data are not redundant with the medical diagnosis, in particular, the DRG. The findings support the argument for including nursing care data in the hospital discharge abstract. Further study is needed to clarify which nursing data are the best fit for the current hospital discharge abstract data collection scheme.
Nursing diagnoses as predictors of hospital length of stay: a prospective observational study
  • F Agostino
  • E Vellone
  • A Cocchieri
  • J Welton
  • M Maurici
  • B Polistena
  • F Spandonaro
  • M Zega
  • R Alvaro
  • G Sanson
F. D'Agostino, E. Vellone, A. Cocchieri, J. Welton, M. Maurici, B. Polistena, F. Spandonaro, M. Zega, R. Alvaro, G. Sanson, Nursing diagnoses as predictors of hospital length of stay: a prospective observational study, J. Nurs. Scholarsh. 51 (2019) 96-105.
The hospital standardized mortality ratio fallacy: a narrative review
  • Y R Van Gestel
  • V E Lemmens
  • H F Lingsma
  • I H De Hingh
  • H J Rutten
  • J W Coebergh
Y.R. van Gestel, V.E. Lemmens, H.F. Lingsma, I.H. de Hingh, H.J. Rutten, J.W. Coebergh, The hospital standardized mortality ratio fallacy: a narrative review, Med. Care 50 (2012) 662-667.
Physician nurse care: a new use of UMLS to measure professional contribution: are we talking about the same patient a new graph matching algorithm?
  • A D Boyd
  • K D Lopez
  • C Lugaresi
  • T Macieira
  • V Sousa
  • S Acharya
  • A Balasubramanian
  • K Roussi
  • G M Keenan
  • Y A Lussier
A.D. Boyd, K.D. Lopez, C. Lugaresi, T. Macieira, V. Sousa, S. Acharya, A. Balasubramanian, K. Roussi, G.M. Keenan, Y.A. Lussier, Physician nurse care: a new use of UMLS to measure professional contribution: are we talking about the same patient a new graph matching algorithm? Int. J. Med. Inform. 113 (2018) 63-71.
Nursing Diagnoses: Definitions and Classification
  • H Herdman
H. Herdman, Nursing Diagnoses: Definitions and Classification. 2015-2017, Wiley-Blackwell, Oxford, 2014.
Prevalence of nursing diagnoses as a measure of nursing complexity in a hospital setting
  • F Agostino
  • G Sanson
  • A Cocchieri
  • E Vellone
  • J Welton
  • M Maurici
  • R Alvaro
  • M Zega
F. D'Agostino, G. Sanson, A. Cocchieri, E. Vellone, J. Welton, M. Maurici, R. Alvaro, M. Zega, Prevalence of nursing diagnoses as a measure of nursing complexity in a hospital setting, J. Adv. Nurs. 73 (2017) 2129-2142.
Development of a computerized system using standard nursing language for creation of a nursing minimum data set
  • F Agostino
  • E Vellone
  • F Tontini
  • M Zega
  • R Alvaro
F. D'Agostino, E. Vellone, F. Tontini, M. Zega, R. Alvaro, Development of a computerized system using standard nursing language for creation of a nursing minimum data set, Prof. Inferm. 65 (2012) 103-109.
International Classification of Diseases, 9th Revision -Italian Version
Centers for Disease Control and Prevention, International Classification of Diseases, 9th Revision -Italian Version, (2007).
Internal validation of predictive models: efficiency of some procedures for logistic regression analysis
  • E W Steyerberg
  • F E Harrell
  • G J Borsboom
  • M Eijkemans
  • Y Vergouwe
  • J D F Habbema
E.W. Steyerberg, F.E. Harrell Jr, G.J. Borsboom, M. Eijkemans, Y. Vergouwe, J.D.F. Habbema, Internal validation of predictive models: efficiency of some procedures for logistic regression analysis, J. Clin. Epidemiol. 54 (2001) 774-781.
  • W Paans
  • M Müller-Staub
W. Paans, M. Müller-Staub, Standardized Nursing Language in Intelligent Electronic Healthcare Documentation, HIMMS, Europe, 2012.
  • W Paans
  • M Müller-Staub
W. Paans, M. Müller-Staub, Standardized Nursing Language in Intelligent Electronic Healthcare Documentation, HIMMS, Europe, 2012.