Improving the Predictive Accuracy of the National Early Warning Score 2: Protocol for Algorithm Refinement.

Abstract

Background: The National Early Warning Score 2 (NEWS2) has been widely adopted for predicting patient deterioration in health care settings using routinely collected physiological observations. The use of NEWS2 has been shown to reduce in-hospital mortality, but it has limited accuracy in the prediction of clinically important outcomes, especially over longer time periods.

Objective: This project aims to improve the predictive accuracy of the NEWS2 scoring system, particularly its accuracy over more than 24 hours and its predictive value in older patients and children. It will investigate whether using the currently collected data differently and the inclusion of additional data would result in an improved algorithm.

Methods: The study will use historical patient data from the Newcastle upon Tyne Hospitals NHS Foundation Trust, including observational data (eg, vital signs), BMI- related data, and other outcome-related variables (eg, mortality rates) to train and test an algorithm to predict the risk of key clinical outcomes, including mortality, intensive therapy unit admission, sepsis, and cardiac arrest, to demonstrate a proof of concept for a modified scoring system. The algorithm's performance will be assessed based on its accuracy, precision, F₁-score, area under the curve, and receiver operating characteristic curve.

Results: The study is expected to start in April 2025. The findings are expected to be produced by the end of 2026 and will be disseminated at symposia, conferences, and in journal publications.

Conclusions: The refined NEWS2 algorithm will address limited accuracy in predicting clinical deterioration beyond 24 hours in the original system by incorporating additional variables. Improved accuracy in the early detection of deterioration can lead to timely interventions, potentially reducing mortality and adverse clinical events. The enhanced algorithm also has the potential to be integrated into existing clinical decision support systems to facilitate health care professionals' decision-making.

International registered report identifier (irrid): PRR1-10.2196/70303.