Background: Early warning scores (EWS) have been developed as clinical prognostication tools to identify acutely deteriorating patients. In the past few years, there has been a proliferation of studies that describe the development and validation of novel machine learning-based EWS. Systematic reviews of published studies which focus on evaluating performance of both well-established and novel EWS have shown conflicting conclusions. A possible reason is the heterogeneity in validation methods applied. In this review, we aim to examine the methodologies and metrics used in studies which perform EWS validation. Methods: A systematic review of all eligible studies from the MEDLINE database and other sources, was performed. Studies were eligible if they performed validation on at least one EWS and reported associations between EWS scores and inpatient mortality, intensive care unit (ICU) transfers, or cardiac arrest (CA) of adults. Two reviewers independently did a full-text review and performed data abstraction by using standardized data-worksheet based on the TRIPOD (Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) checklist. Meta-analysis was not performed due to heterogeneity. Results: The key differences in validation methodologies identified were (1) validation dataset used, (2) outcomes of interest, (3) case definition, time of EWS use and aggregation methods, and (4) handling of missing values. In terms of case definition, among the 48 eligible studies, 34 used the patient episode case definition while 12 used the observation set case definition, and 2 did the validation using both case definitions. Of those that used the patient episode case definition, 18 studies validated the EWS at a single point of time, mostly using the first recorded observation. The review also found more than 10 different performance metrics reported among the studies. Conclusions: Methodologies and performance metrics used in studies performing validation on EWS were heterogeneous hence making it difficult to interpret and compare EWS performance. Standardizing EWS validation methodology and reporting can potentially address this issue.

Background Early warning scores (EWS) have been developed as clinical prognostication tools to identify acutely deteriorating patients. With recent advancements in machine learning, there has been a proliferation of studies that describe the development and validation of novel EWS. Systematic reviews of published studies which focus on evaluating performance of both well-established and novel EWS have shown conflicting conclusions. A possible reason for this is the lack of consistency in the validation methods used. In this review, we aim to examine the methodologies and performance metrics used in studies which describe EWS validation.Methods A systematic review of all eligible studies in the MEDLINE database from inception to 22-Feb-2019 was performed. Studies were eligible if they performed validation on at least one EWS and reported associations between EWS scores and mortality, intensive care unit (ICU) transfers, or cardiac arrest (CA) of adults within the inpatient setting. Two reviewers independently did a full-text review and performed data abstraction by using standardized data-worksheet based on the TRIPOD (Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) checklist. Meta-analysis was not performed due to heterogeneity.Results The key differences in validation methodologies identified were (1) validation population characteristics, (2) outcomes of interest, (3) case definition, intended time of use and aggregation methods, and (4) handling of missing values in the validation dataset. In terms of case definition, among the 34 eligible studies, 22 used the patient episode case definition while 10 used the observation set case definition, and 2 did the validation using both case definitions. Of those that used the patient episode case definition, 11 studies used a single point of time score to validate the EWS, most of which used the first recorded observation. There were also more than 10 different performance metrics reported among the studies.Conclusions Methodologies and performance metrics used in studies performing validation on EWS were not consistent hence making it difficult to interpret and compare EWS performance. Standardizing EWS validation methodology and reporting can potentially address this issue.

Coordination and consolidation of care provided in acute care hospitals need reconfiguration and reorganization to meet the demand of large number of acute admissions. We report on the effectiveness of an Acute Medical Ward AMW (AMW) receiving cases that were suspected to have infection related diagnosis on admission by Emergency Department (ED), addressing this in a large tertiary hospital in South East Asia. Mean Length of Stay (LOS) was compared using Gamma Generalized Linear Models with Log-link while odds of readmissions and mortality were compared using logistic regression models. The LOS (mean: 5.8 days, SD: 9.1 days) of all patients admitted to AMW was similar to discharge diagnosis-matched general ward (GW) patients admitted before AMW implementation, readmission rates were lower (15-day: 5.3%, 30-day: 8.1%). Bivariate and multivariate models revealed that mean LOS after AMW implementation was not significantly different from before AMW implementation (Ratio: 0.99, p=0.473). Our AMW had reduced readmission rates for patients with infection but has not made an overall impact on the LOS and readmission rates for the epartment as a whole.

Introduction: The National Early Warning Score (NEWS) is well established in acute medical units to identify acutely deteriorating patients and is shown to have good prognostic value. NEWS, however, has only been used in the Emergency Department as a triage tool. We aimed to evaluate the validity of NEWS in Acute Medical Ward (AMW) that treats predominantly acute infection-related conditions to the Internal Medicine service. Materials and Methods: We undertook a retrospective cohort study and analysed NEWS records of all patients admitted to AMW at Singapore General Hospital between 1 August 2015 and 30 July 2017. The outcome was defined as deterioration that required transfer to Intermediate Care Area (ICA), Intensive Care Unit (ICU) or death within 24 hours of a vital signs observation set. Results: A total of 298,743 vital signs observation sets were obtained from 11,300 patients. Area under receiver operating characteristic curve for any of the 3 outcomes (transfer to ICA, ICU or death) over a 24-hour period was 0.896 (95% confidence interval, 0.890-0.901). Event rate was noted to be high above 0.250 when the score was >9. In the medium-risk group (score of 5 or 6), event rate was <0.125. Conclusion: NEWS accurately triages patients according to the likelihood of adverse outcomes in infection-related acute medical settings. Key words: Death, Infection, Intensive care, Intermediate care

Background Early warning scores (EWS) have been developed as clinical prognostication tools to identify acutely deteriorating patients. With recent advancements in machine learning, there has been a proliferation of studies that describe the development and validation of novel EWS. Systematic reviews of published studies which focus on evaluating performance of both well-established and novel EWS have shown conflicting conclusions. A possible reason for this is the lack of consistency in the validation methods used. In this review, we aim to examine the methodologies and performance metrics used in studies which describe EWS validation. Methods A systematic review of all eligible studies in the MEDLINE database from inception to 22-Feb-2019 was performed. Studies were eligible if they performed validation on at least one EWS and reported associations between EWS scores and mortality, intensive care unit (ICU) transfers, or cardiac arrest (CA) of adults within the inpatient setting. Two reviewers independently did a full-text review and performed data abstraction by using standardized data-worksheet based on the TRIPOD (Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) checklist. Meta-analysis was not performed due to heterogeneity. Results The key differences in validation methodologies identified were (1) validation population characteristics, (2) outcomes of interest, (3) case definition, intended time of use and aggregation methods, and (4) handling of missing values in the validation dataset. In terms of case definition, among the 34 eligible studies, 22 used the patient episode case definition while 10 used the observation set case definition, and 2 did the validation using both case definitions. Of those that used the patient episode case definition, 11 studies used a single point of time score to validate the EWS, most of which used the first recorded observation. There were also more than 10 different performance metrics reported among the studies. Conclusions Methodologies and performance metrics used in studies performing validation on EWS were not consistent hence making it difficult to interpret and compare EWS performance. Standardizing EWS validation methodology and reporting can potentially address this issue.