Performance of digital early warning score (NEWS2) in a cardiac specialist setting: retrospective cohort study.

INTRODUCTION: Patients with cardiovascular diseases (CVD) are at significant risk of developing critical events. Early warning scores (EWS) are recommended for early recognition of deteriorating patients, yet their performance has been poorly studied in cardiac care settings. Standardisation and integrated National Early Warning Score 2 (NEWS2) in electronic health records (EHRs) are recommended yet have not been evaluated in specialist settings. OBJECTIVE: To investigate the performance of digital NEWS2 in predicting critical events: death, intensive care unit (ICU) admission, cardiac arrest and medical emergencies. METHODS: Retrospective cohort analysis. STUDY COHORT: Individuals admitted with CVD diagnoses in 2020; including patients with COVID-19 due to conducting the study during the COVID-19 pandemic. MEASURES: We tested the ability of NEWS2 in predicting the three critical outcomes from admission and within 24 hours before the event. NEWS2 was supplemented with age and cardiac rhythm and investigated. We used logistic regression analysis with the area under the receiver operating characteristic curve (AUC) to measure discrimination. RESULTS: In 6143 patients admitted under cardiac specialties, NEWS2 showed moderate to low predictive accuracy of traditionally examined outcomes: death, ICU admission, cardiac arrest and medical emergency (AUC: 0.63, 0.56, 0.70 and 0.63, respectively). Supplemented NEWS2 with age showed no improvement while age and cardiac rhythm improved discrimination (AUC: 0.75, 0.84, 0.95 and 0.94, respectively). Improved performance was found of NEWS2 with age for COVID-19 cases (AUC: 0.96, 0.70, 0.87 and 0.88, respectively). CONCLUSION: The performance of NEWS2 in patients with CVD is suboptimal, and fair for patients with CVD with COVID-19 to predict deterioration. Adjustment with variables that strongly correlate with critical cardiovascular outcomes, that is, cardiac rhythm, can improve the model. There is a need to define critical endpoints, engagement with clinical experts in development and further validation and implementation studies of EHR-integrated EWS in cardiac specialist settings.

Clinical deployment environments: Five pillars of translational machine learning for health.

Machine Learning for Health (ML4H) has demonstrated efficacy in computer imaging and other self-contained digital workflows, but has failed to substantially impact routine clinical care. This is no longer because of poor adoption of Electronic Health Records Systems (EHRS), but because ML4H needs an infrastructure for development, deployment and evaluation within the healthcare institution. In this paper, we propose a design pattern called a Clinical Deployment Environment (CDE). We sketch the five pillars of the CDE: (1) real world development supported by live data where ML4H teams can iteratively build and test at the bedside (2) an ML-Ops platform that brings the rigour and standards of continuous deployment to ML4H (3) design and supervision by those with expertise in AI safety (4) the methods of implementation science that enable the algorithmic insights to influence the behaviour of clinicians and patients and (5) continuous evaluation that uses randomisation to avoid bias but in an agile manner. The CDE is intended to answer the same requirements that bio-medicine articulated in establishing the translational medicine domain. It envisions a transition from "real-world" data to "real-world" development.

Variables associated with unplanned general adult ICU admission in hospitalised patients: protocol for a systematic review.

BACKGROUND: Failure to promptly identify deterioration in hospitalised patients is associated with delayed admission to intensive care units (ICUs) and poor outcomes. Existing vital sign-based Early Warning Score (EWS) algorithms do not have a sufficiently high positive predictive value to be used for automated activation of an ICU outreach team. Incorporating additional patient data might improve the predictive power of EWS algorithms; however, it is currently not known which patient data (or variables) are most predictive of ICU admission. We describe the protocol for a systematic review of variables associated with ICU admission. METHODS/DESIGN: MEDLINE, EMBASE, CINAHL and the Cochrane Library, including Cochrane Database of Systematic Reviews and the Cochrane Central Register of Controlled Trials (CENTRAL) will be searched for studies that assess the association of routinely recorded variables associated with subsequent unplanned ICU admission. Only studies involving adult patients admitted to general ICUs will be included. We will extract data relating to the statistical association between ICU admission and predictor variables, the quality of the studies and the generalisability of the findings. DISCUSSION: The results of this review will aid the development of future models which predict the risk of unplanned ICU admission. SYSTEMATIC REVIEW REGISTRATION: PROSPERO: CRD42015029617.

Trainee update.

The new trainee section of the Acute Medicine journal gives us an excellent opportunity to keep trainees up-to-date with the latest news. We will provide you with a summary of relevant information coming directly from both the Society for Acute Medicine and the Acute Medicine Specialty Advisory Committee (SAC).