Ode to My EMR.

Description Our EMRs should empower us, but unfortunately, they often bully and frustrate us. This poem is an expression of my frustration and disappointment with my own EMR. Creating it allowed me to channel my frustration and disappointment.

[Development and validation of risk prediction model for new-onset cardiovascular diseases among breast cancer patients: Based on regional medical data of Inner Mongolia].

OBJECTIVE: To develop and validate a three-year risk prediction model for new-onset cardiovascular diseases (CVD) among female patients with breast cancer. METHODS: Based on the data from Inner Mongolia Regional Healthcare Information Platform, female breast cancer patients over 18 years old who had received anti-tumor treatments were included. The candidate predictors were selected by Lasso regression after being included according to the results of the multivariate Fine & Gray model. Cox proportional hazard model, Logistic regression model, Fine & Gray model, random forest model, and XGBoost model were trained on the training set, and the model performance was evaluated on the testing set. The discrimination was evaluated by the area under the curve (AUC) of the receiver operator characteristic curve (ROC), and the calibration was evaluated by the calibration curve. RESULTS: A total of 19 325 breast cancer patients were identified, with an average age of (52.76±10.44) years. The median follow-up was 1.18 [interquartile range (IQR): 2.71] years. In the study, 7 856 patients (40.65%) developed CVD within 3 years after the diagnosis of breast cancer. The final selected variables included age at diagnosis of breast cancer, gross domestic product (GDP) of residence, tumor stage, history of hypertension, ischemic heart disease, and cerebrovascular disease, type of surgery, type of chemotherapy and radiotherapy. In terms of model discrimination, when not considering survival time, the AUC of the XGBoost model was significantly higher than that of the random forest model [0.660 (95%CI: 0.644-0.675) vs. 0.608 (95%CI: 0.591-0.624), P < 0.001] and Logistic regression model [0.609 (95%CI: 0.593-0.625), P < 0.001]. The Logistic regression model and the XGBoost model showed better calibration. When considering survival time, Cox proportional hazard model and Fine & Gray model showed no significant difference for AUC [0.600 (95%CI: 0.584-0.616) vs. 0.615 (95%CI: 0.599-0.631), P=0.188], but Fine & Gray model showed better calibration. CONCLUSION: It is feasible to develop a risk prediction model for new-onset CVD of breast cancer based on regional medical data in China. When not considering survival time, the XGBoost model and the Logistic regression model both showed better performance; Fine & Gray model showed better performance in consideration of survival time.

Development and validation of risk prediction model for new-onset cardiovascular diseases among breast cancer patients: Based on regional medical data of Inner Mongolia / 北京大学学报(医学版)

OBJECTIVE@#To develop and validate a three-year risk prediction model for new-onset cardiovascular diseases (CVD) among female patients with breast cancer.@*METHODS@#Based on the data from Inner Mongolia Regional Healthcare Information Platform, female breast cancer patients over 18 years old who had received anti-tumor treatments were included. The candidate predictors were selected by Lasso regression after being included according to the results of the multivariate Fine & Gray model. Cox proportional hazard model, Logistic regression model, Fine & Gray model, random forest model, and XGBoost model were trained on the training set, and the model performance was evaluated on the testing set. The discrimination was evaluated by the area under the curve (AUC) of the receiver operator characteristic curve (ROC), and the calibration was evaluated by the calibration curve.@*RESULTS@#A total of 19 325 breast cancer patients were identified, with an average age of (52.76±10.44) years. The median follow-up was 1.18 [interquartile range (IQR): 2.71] years. In the study, 7 856 patients (40.65%) developed CVD within 3 years after the diagnosis of breast cancer. The final selected variables included age at diagnosis of breast cancer, gross domestic product (GDP) of residence, tumor stage, history of hypertension, ischemic heart disease, and cerebrovascular disease, type of surgery, type of chemotherapy and radiotherapy. In terms of model discrimination, when not considering survival time, the AUC of the XGBoost model was significantly higher than that of the random forest model [0.660 (95%CI: 0.644-0.675) vs. 0.608 (95%CI: 0.591-0.624), P < 0.001] and Logistic regression model [0.609 (95%CI: 0.593-0.625), P < 0.001]. The Logistic regression model and the XGBoost model showed better calibration. When considering survival time, Cox proportional hazard model and Fine & Gray model showed no significant difference for AUC [0.600 (95%CI: 0.584-0.616) vs. 0.615 (95%CI: 0.599-0.631), P=0.188], but Fine & Gray model showed better calibration.@*CONCLUSION@#It is feasible to develop a risk prediction model for new-onset CVD of breast cancer based on regional medical data in China. When not considering survival time, the XGBoost model and the Logistic regression model both showed better performance; Fine & Gray model showed better performance in consideration of survival time.

Nurses' Experiences After Implementation of an Organization-Wide Electronic Medical Record: Qualitative Descriptive Study.

BACKGROUND: Reports on the impact of electronic medical record (EMR) systems on clinicians are mixed. Currently, nurses' experiences of adopting a large-scale, multisite EMR system have not been investigated. Nurses are the largest health care workforce; therefore, the impact of EMR implementation must be investigated and understood to ensure that patient care quality, changes to nurses' work, and nurses themselves are not negatively impacted. OBJECTIVE: This study aims to explore Australian nurses' postimplementation experiences of an organization-wide EMR system. METHODS: This qualitative descriptive study used focus group and individual interviews and an open-ended survey question to collect data between 12 and 18 months after the implementation of an EMR across 6 hospital sites of a large health care organization in Victoria, Australia. Data were collected between November 2020 and June 2021, coinciding with the COVID-19 pandemic. Analysis comprised complementary inductive and deductive approaches. Specifically, reflexive thematic analysis was followed by framework analysis by the coding of data as barriers or facilitators to nurses' use of the EMR using the Theoretical Domains Framework. RESULTS: A total of 158 nurses participated in this study. The EMR implementation dramatically changed nurses' work and how they viewed their profession, and nurses were still adapting to the EMR implementation 18 months after implementation. Reflexive thematic analysis led to the development of 2 themes: An unintentional divide captured nurses' feelings of division related to how using the EMR affected nurses, patient care, and the broader nursing profession. This time, it's personal detailed nurses' beliefs about the EMR implementation leading to bigger changes to nurses as individuals and nursing as a profession than other changes that nurses have experienced within the health care organization. The most frequent barriers to EMR use by nurses were related to the Theoretical Domains Framework domain of environmental context and resources. Facilitators of EMR use were most often related to memory, attention, and decision processes. Most barriers and facilitators were related to motivation. CONCLUSIONS: Nurses perceived EMR implementation to have a mixed impact on the provision of quality patient care and on their colleagues. Implementing technology in a health care setting was perceived as a complex endeavor that impacted nurses' perceptions of their autonomy, ways of working, and professional roles. Potential negative consequences were related to nursing workforce retention and patient care delivery. Motivation was the main behavioral driver for nurses' adoption of EMR systems and hence a key consideration for implementing interventions or organizational changes directed at nurses.

Potential of Electronic Medical Record Data for National Quality Measurement.

National quality measurements with risk-adjusted provider comparison in health care nowadays usually require administrative or clinically measured data. However, both data sources have their limitations. Due to the digitalisation of institutions and the resulting switch to electronic medical records, the question arises as to whether these data can be made usable for risk-adjusted quality comparisons from both a content and a technical point of view. We found that most of the relevant information can be exported with little effort from the electronic medical records. In using this data source an even more sophisticated operationalization of the data of interest is needed.

Understanding nurses' perceptions of barriers and enablers to use of a new electronic medical record system in Australia: A qualitative study.

BACKGROUND: Electronic medical record system implementations impact nurses, their work and workflows. The aim of this study was to understand nurses' perceptions of barriers and enablers to using a new electronic medical record in an acute hospital environment. METHODS: Data were collected just prior to an organisation-wide new electronic medical record implementation at a large tertiary healthcare organization in Victoria, Australia. Sixty-three nurses from five hospital sites participated in 12 focus group interviews. Transcripts were transcribed and deductive content analysis used the 14-domain Theoretical Domains Framework to identify barriers and enablers. RESULTS: Coded data mapped to 13 of the 14 domains. Nurse motivation emerged as a dominant theme among both barriers and enablers. Nurses' most common perceived barriers related to emotions (24.1%) and environmental context and resources (21.3%). Conversely, the most common enablers related to social influences (21%) and reinforcement (20.8%). DISCUSSION: In addition to effecting changes in their work and workflows, the dominance of nurses' emotional responses reveals the potential for implementation of a new electronic medical record to negatively affect nurses' psychological well-being. Using data aligned to the Theoretical Domains Framework assisted identification of behavior change strategies to target the barriers and enablers perceived by nurses. Strategies aligned with nine behavioral intervention categories are recommended for successful implementation and optimization of an electronic medical record by nurses. CONCLUSIONS: Multifaceted strategies targeting multiple behaviors are required to support adoption of the electronic medical record by nurses, and reduce the risk for nurse attrition in the workforce.

Drug Prescription Profiles in Patients with Polypharmacy in Spain: A Large-Scale Pharmacoepidemiologic Study Using Real-World Data.

We aimed to identify and compare medication profiles in populations with polypharmacy between 2005 and 2015. We conducted a cross-sectional study using information from the Computerized Database for Pharmacoepidemiologic Studies in Primary Care (BIFAP, Spain). We estimated the prevalence of therapeutic subgroups in all individuals 15 years of age and older with polypharmacy (≥5 drugs during ≥6 months) using the Anatomical Therapeutic Chemical classification system level 4, by sex and age group, for both calendar years. The most prescribed drugs were proton-pump inhibitors (PPIs), statins, antiplatelet agents, benzodiazepine derivatives, and angiotensin-converting enzyme inhibitors. The greatest increases between 2005 and 2015 were observed in PPIs, statins, other antidepressants, and ß-blockers, while the prevalence of antiepileptics was almost tripled. We observed increases in psychotropic drugs in women and cardiovascular medications in men. By patient´s age groups, there were notable increases in antipsychotics, antidepressants, and antiepileptics (15-44 years); antidepressants, PPIs, and selective ß-blockers (45-64 years); selective ß-blockers, biguanides, PPIs, and statins (65-79 years); and in statins, selective ß-blockers, and PPIs (80 years and older). Our results revealed important increases in the use of specific therapeutic subgroups, like PPIs, statins, and psychotropic drugs, highlighting opportunities to design and implement strategies to analyze such prescriptions' appropriateness.

[Document standards for pathology reports in digital medicine]. / Dokumentenstandards für Pathologiebefundberichte in einer digitalisierten Medizin.

Pathology reports are important clinical documents for the diagnosis, treatment, and follow-up of often severe diseases. They are subject to a series of formal and substantive requirements that are anchored in several jurisdictions, which also apply to the digital form of these records. Only a few of the currently used digital document formats meet these requirements and are at the same time interoperable, regardless of the computer platforms used. Practically, they are only partially used in pathology laboratories, practice management, and hospital information systems. The consistent use of these standard formats for pathological findings reports provided a clear digital added value for both pathologists and clinicians as well as their patients.

Validity of a nationwide medication record system in the Netherlands.

Background In the Netherlands, a nationwide Medication Record System based on pharmacy dispensing data is used to obtain information about patients' actual medication use. However, it is not clear to what extent the information of the Nationwide Medication Record System corresponds to the medication information obtained with the Best Possible Medication History. Objective To examine the validity of medication dispensing records collected from the Nationwide Medication Record System by comparing them to the Best Possible Medication History. Method An observational study was performed. Patients from several hospital departments were included at admission. To obtain the Best Possible Medication History, pharmacy technicians performed medication reconciliation at admission, using dispensing records from the Nationwide Medication Record System and information from the patient himself. Primary outcome is percentage of patients with no discrepancies between the Nationwide Medication Record System and the Best Possible Medication History. Descriptive analysis was used. Results Eighty-two patients were approached and 66 (80%) were included, with in total 478 medicines in the Best Possible Medication History. Seventeen percent of the patients had no discrepancies and 33% (n = 156) of the medication records contained a discrepancy between the Nationwide Medication Record System and the Best Possible Medication History. Most common type of discrepancy was omission (44%). Conclusion Even with a Nationwide Medication Record System medication reconciliation with the patient remains essential to obtain complete information about patient's actual medication use.

Is a shift from research on individual medical error to research on health information technology underway? A 40-year analysis of publication trends in medical journals.

OBJECTIVE: In 1983, McIntyre and Popper underscored the need for more openness in dealing with errors in medicine. Since then, much has been written on individual medical errors. Furthermore, at the beginning of the 21st century, researchers and medical practitioners increasingly approached individual medical errors through health information technology. Hence, the question arises whether the attention of biomedical researchers shifted from individual medical errors to health information technology. We ran a study to determine publication trends concerning individual medical errors and health information technology in medical journals over the last 40 years. METHODS: We used the Medical Subject Headings (MeSH) taxonomy in the database MEDLINE. Each year, we analyzed the percentage of relevant publications to the total number of publications in MEDLINE. The trends identified were tested for statistical significance. RESULTS: Our analysis showed that the percentage of publications dealing with individual medical errors increased from 1976 until the beginning of the 21st century but began to drop in 2003. Both the upward and the downward trends were statistically significant (P < 0.001). A breakdown by country revealed that it was the weight of the US and British publications that determined the overall downward trend after 2003. On the other hand, the percentage of publications dealing with health information technology doubled between 2003 and 2015. The upward trend was statistically significant (P < 0.001). CONCLUSIONS: The identified trends suggest that the attention of biomedical researchers partially shifted from individual medical errors to health information technology in the USA and the UK.

A systematic review of near real-time and point-of-care clinical decision support in anesthesia information management systems.

Anesthesia information management systems (AIMS) are sophisticated hardware and software technology solutions that can provide electronic feedback to anesthesia providers. This feedback can be tailored to provide clinical decision support (CDS) to aid clinicians with patient care processes, documentation compliance, and resource utilization. We conducted a systematic review of peer-reviewed articles on near real-time and point-of-care CDS within AIMS using the Preferred Reporting Items for Systematic Review and Meta-Analysis Protocols. Studies were identified by searches of the electronic databases Medline and EMBASE. Two reviewers screened studies based on title, abstract, and full text. Studies that were similar in intervention and desired outcome were grouped into CDS categories. Three reviewers graded the evidence within each category. The final analysis included 25 articles on CDS as implemented within AIMS. CDS categories included perioperative antibiotic prophylaxis, post-operative nausea and vomiting prophylaxis, vital sign monitors and alarms, glucose management, blood pressure management, ventilator management, clinical documentation, and resource utilization. Of these categories, the reviewers graded perioperative antibiotic prophylaxis and clinical documentation as having strong evidence per the peer reviewed literature. There is strong evidence for the inclusion of near real-time and point-of-care CDS in AIMS to enhance compliance with perioperative antibiotic prophylaxis and clinical documentation. Additional research is needed in many other areas of AIMS-based CDS.

The Analysis of Medical Adverse Events Related to Electronic Health Records in Nursing Services.

This pilot study investigated problems of electronic health records (EHR), which have been used by nurses as a clinical decision tool. The investigation was conducted based on case records retrieved from the national database of medical adverse events. Detailed data related to nursing services must continue to be collected to establish a clearer linkage of EHR data and scholary information.

Códigos QR y sus aplicaciones en las ciencias de la salud / QR codes and their uses in health sciences

El Código QR es un código bidimensional, fácilmente identificable por los tres cuadros ubicados en las esquinas superiores e inferior izquierda. Puede contener información de caracteres alfanuméricos, símbolos, Kanji, Hiragana, Katakana, códigos binarios y códigos de control. Es omnidireccional y su lectura puede realizarse desde un dispositivo móvil. Se realizó una revisión de artículos de las bases Scielo y Pubmed con el objetivo de indagar acerca de las aplicaciones de estos códigos en las ciencias de la salud y proponer algunas de estas para el Sistema Nacional de Salud cubano, cuya introducción ha sido paulatina, principalmente en la práctica y en la educación médica. Sin embargo, la diseminación y el uso es aún incipiente y existen muchas oportunidades. Un sistema de identificación nacional en salud permitiría una autentificación más fácil, rápida y efectiva, con un ahorro sustancial de recursos. Las empresas farmacéuticas podrían emplear un sistema similar, en este caso con informaciones de medicamentos. A pesar de sus limitaciones, son diversas las aplicaciones que poseen estos códigos en los servicios de salud. Esto, unido a la expansión tecnológica que vive hoy Cuba, permitirá en un futuro mediato la generalización y la difusión de estas tecnologías en beneficio de la sociedad(AU)

The QR code is a two-dimensional code easily identifiable by the three boxes located in the top corners and the bottom left corner. It may contain information in alphanumeric characters, symbols, Kanji, Hiragana, Katakana, binary codes and control codes. It is omnidirectional and may be read from a mobile device. A review was conducted of papers from the databases Scielo and Pubmed about the uses of these codes in health sciences so as to propose some of those to the Cuban National Health System, where their introduction has been gradual, mainly in medical practice and education. However, their spread and use is still incipient and many opportunities still lie ahead. A national identification system for the health sector would allow easy, fast, effective authentication with substantial resource savings. Pharmaceutical enterprises could use a similar system, in their case with information about drugs. Despite their limitations, these codes may be used for a variety of purposes in health services. This possibility, combined with the current technological expansion experienced by Cuba, will permit generalization and dissemination of these technologies in the near future for the benefit of society(AU)

Códigos QR y sus aplicaciones en las ciencias de la salud / QR codes and their uses in health sciences

El Código QR es un código bidimensional, fácilmente identificable por los tres cuadros ubicados en las esquinas superiores e inferior izquierda. Puede contener información de caracteres alfanuméricos, símbolos, Kanji, Hiragana, Katakana, códigos binarios y códigos de control. Es omnidireccional y su lectura puede realizarse desde un dispositivo móvil. Se realizó una revisión de artículos de las bases Scielo y Pubmed con el objetivo de indagar acerca de las aplicaciones de estos códigos en las ciencias de la salud y proponer algunas de estas para el Sistema Nacional de Salud cubano, cuya introducción ha sido paulatina, principalmente en la práctica y en la educación médica. Sin embargo, la diseminación y el uso es aún incipiente y existen muchas oportunidades. Un sistema de identificación nacional en salud permitiría una autentificación más fácil, rápida y efectiva, con un ahorro sustancial de recursos. Las empresas farmacéuticas podrían emplear un sistema similar, en este caso con informaciones de medicamentos. A pesar de sus limitaciones, son diversas las aplicaciones que poseen estos códigos en los servicios de salud. Esto, unido a la expansión tecnológica que vive hoy Cuba, permitirá en un futuro mediato la generalización y la difusión de estas tecnologías en beneficio de la sociedad.

The QR code is a two-dimensional code easily identifiable by the three boxes located in the top corners and the bottom left corner. It may contain information in alphanumeric characters, symbols, Kanji, Hiragana, Katakana, binary codes and control codes. It is omnidirectional and may be read from a mobile device. A review was conducted of papers from the databases Scielo and Pubmed about the uses of these codes in health sciences so as to propose some of those to the Cuban National Health System, where their introduction has been gradual, mainly in medical practice and education. However, their spread and use is still incipient and many opportunities still lie ahead. A national identification system for the health sector would allow easy, fast, effective authentication with substantial resource savings. Pharmaceutical enterprises could use a similar system, in their case with information about drugs. Despite their limitations, these codes may be used for a variety of purposes in health services. This possibility, combined with the current technological expansion experienced by Cuba, will permit generalization and dissemination of these technologies in the near future for the benefit of society.

Usability of Academic Electronic Medical Record Application for Nursing Students' Clinical Practicum.

OBJECTIVES: Nursing curricula for undergraduate nursing students need to reflect the information technology used in current nursing practice. A smart-device Academic Electronic Medical Record (AEMR) application can help nursing students access and document records for the clinical practicum. We conducted a pilot study to evaluate the usability of an AEMR application before applying it to the clinical nursing practicum. METHODS: A previously developed EMR application was modified as an AEMR to access patient information at bedside and to practice documentation. We added several features to the current EMR application to create an AEMR environment. We created a series of document forms and several useful scales on an external application, which included nursing admission notes, vital signs, and intake/output. The case scenarios and tasks were created by a research team to evaluate aspects of AEMRs, including their usability and functionality. Five nursing students completed 15 tasks using a think-aloud method with a tablet device. RESULTS: Minor usability issues were identified and rectified. All participants indicated that they became familiar with the application with little effort. They said that the application icons were intuitive, which helped them find patient information more quickly and accurately. CONCLUSIONS: The application will improve timely access to patient data and documentation for nursing students. We are confident that this AEMR application will enhance nursing students' experience with their clinical practicum, and help them to better understand patient conditions and document them with ideal accessibility.

The use of natural language processing of infusion notes to identify outpatient infusions.

PURPOSE: Outpatient infusions are commonly missing in Veterans Health Affairs (VHA) pharmacy dispensing data sets. Currently, Healthcare Common Procedure Coding System (HCPCS) codes are used to identify outpatient infusions, but concerns exist if they correctly capture all infusions and infusion-related data such as dose and date of administration. We developed natural language processing (NLP) software to extract infusion information from medical text infusion notes. The objective was to compare the sensitivity of three approaches to identify infliximab administration dates and infusion doses against a reference standard established from the Veterans Affairs rheumatoid arthritis (VARA) registry. METHODS: We compared the sensitivity and positive predictive value (PPV) of NLP to that of HCPCS codes in identifying the correct date and dose of infliximab infusions against a human extracted reference standard. RESULTS: The sensitivity was 0.606 (0.585-0.627) for HCPCS alone, 0.858 (0.842-0.873) for NLP alone, and 0.923 (0.911-0.934) for the two methods combined, with a PPV of 0.735 (0.716-0.754), 0.976 (0.969-0.983), and 0.957 (0.948-0.965) for each method, respectively. The mean dose of infliximab was 433 mg in the reference standard, 337 mg from HCPCS, 434 mg from NLP, and 426 mg from the combined method. CONCLUSIONS: HCPCS codes alone are not sufficient to accurately identify infliximab infusion dates and doses in the VHA system. The use of NLP significantly improved the sensitivity and PPV for estimating infusion dates and doses, especially when combined with HCPCS codes.

Usability of Academic Electronic Medical Record Application for Nursing Students' Clinical Practicum / 대한의료정보학회지

OBJECTIVES: Nursing curricula for undergraduate nursing students need to reflect the information technology used in current nursing practice. A smart-device Academic Electronic Medical Record (AEMR) application can help nursing students access and document records for the clinical practicum. We conducted a pilot study to evaluate the usability of an AEMR application before applying it to the clinical nursing practicum. METHODS: A previously developed EMR application was modified as an AEMR to access patient information at bedside and to practice documentation. We added several features to the current EMR application to create an AEMR environment. We created a series of document forms and several useful scales on an external application, which included nursing admission notes, vital signs, and intake/output. The case scenarios and tasks were created by a research team to evaluate aspects of AEMRs, including their usability and functionality. Five nursing students completed 15 tasks using a think-aloud method with a tablet device. RESULTS: Minor usability issues were identified and rectified. All participants indicated that they became familiar with the application with little effort. They said that the application icons were intuitive, which helped them find patient information more quickly and accurately. CONCLUSIONS: The application will improve timely access to patient data and documentation for nursing students. We are confident that this AEMR application will enhance nursing students' experience with their clinical practicum, and help them to better understand patient conditions and document them with ideal accessibility.

Global trends in the use of nationwide big data for solving healthcare problems

While Korea had the highest rate of increase in per capita health expenditures from 1997 to 2007 among The Organization for Economic Cooperation and Development (OECD) countries, it is necessary in all countries to establish sustainable health care systems that efficiently use the existing effective treatment methods. For dealing with the overwhelming health care crisis, the European Union and the United States (US) have launched Health Technology Assessment (HTA) and Comparative Effectiveness Research (CER) programs, respectively. Further, the Federal Coordinating Council for Comparative Effectiveness Research in US has considered the development of the CER data infrastructure to be the primary investment needed in order to reform the national health care system. The main reason is that investment in data infrastructure can potentially generate significant additional investment in CER. In addition, the Council stressed the need for coordination between CER and health information technology through a distributed network of electronic health records. These directions and decisions on driving CER in the US may provide an invaluable lesson on solving some healthcare problems in Korea. However, barriers to the potential contribution of the existing databases to CER must be overcome, including interoperability, privacy protection and confidentiality, and active participation of the holders of the related databases.

Diagnostic performance of electronic syndromic surveillance systems in acute care: a systematic review.

CONTEXT: Healthcare Electronic Syndromic Surveillance (ESS) is the systematic collection, analysis and interpretation of ongoing clinical data with subsequent dissemination of results, which aid clinical decision-making. OBJECTIVE: To evaluate, classify and analyze the diagnostic performance, strengths and limitations of existing acute care ESS systems. DATA SOURCES: All available to us studies in Ovid MEDLINE, Ovid EMBASE, CINAHL and Scopus databases, from as early as January 1972 through the first week of September 2012. STUDY SELECTION: Prospective and retrospective trials, examining the diagnostic performance of inpatient ESS and providing objective diagnostic data including sensitivity, specificity, positive and negative predictive values. DATA EXTRACTION: Two independent reviewers extracted diagnostic performance data on ESS systems, including clinical area, number of decision points, sensitivity and specificity. Positive and negative likelihood ratios were calculated for each healthcare ESS system. A likelihood matrix summarizing the various ESS systems performance was created. RESULTS: The described search strategy yielded 1639 articles. Of these, 1497 were excluded on abstract information. After full text review, abstraction and arbitration with a third reviewer, 33 studies met inclusion criteria, reporting 102,611 ESS decision points. The yielded I2 was high (98.8%), precluding meta-analysis. Performance was variable, with sensitivities ranging from 21% -100% and specificities ranging from 5%-100%. CONCLUSIONS: There is significant heterogeneity in the diagnostic performance of the available ESS implements in acute care, stemming from the wide spectrum of different clinical entities and ESS systems. Based on the results, we introduce a conceptual framework using a likelihood ratio matrix for evaluation and meaningful application of future, frontline clinical decision support systems.