Improving the Predictive Accuracy of the National Early Warning Score 2: Protocol for Algorithm Refinement
Bibliographic record
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
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.140 | 0.240 |
| Meta-epidemiology (narrow) | 0.004 | 0.004 |
| Meta-epidemiology (broad) | 0.004 | 0.007 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.003 | 0.003 |
| Scholarly communication | 0.005 | 0.003 |
| Open science | 0.005 | 0.005 |
| Research integrity | 0.006 | 0.010 |
| Insufficient payload (model declined to judge) | 0.061 | 0.015 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".