Previously submitted to: JMIR Medical Informatics (no longer under consideration since Oct 22, 2026)
Date Submitted: Oct 21, 2026
Open Peer Review Period: Oct 22, 2026 - Oct 22, 2026
(closed for review but you can still tweet)
NOTE: This is an unreviewed Preprint
Warning: This is a unreviewed preprint (What is a preprint?). Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn (a note "no longer under consideration" will appear above).
Peer review me: Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period (in this case, a "Peer Review Me" button to sign up as reviewer is displayed above). All preprints currently open for review are listed here. Outside of the formal open peer-review period we encourage you to tweet about the preprint.
Citation: Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
Final version: If our system detects a final peer-reviewed "version of record" (VoR) published in any journal, a link to that VoR will appear below. Readers are then encourage to cite the VoR instead of this preprint.
Settings: If you are the author, you can login and change the preprint display settings, but the preprint URL/DOI is supposed to be stable and citable, so it should not be removed once posted.
Submit: To post your own preprint, simply submit to any JMIR journal, and choose the appropriate settings to expose your submitted version as preprint.
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Beyond NEWS2: A Machine Learning Early Warning Model for Clinical Deterioration with Multi-Site Validation and Operational Impact
ABSTRACT
Background:
Threshold-based early warning scores like NEWS2 contribute to severe alert fatigue and have limited discrimination in acute care settings. Rich clinical data captured in electronic health records offer an opportunity to improve early risk stratification.
Objective:
We aimed to develop and externally validate a non-proprietary XGBoost early warning model for predicting clinical deterioration within 24 hours across multiple acute care hospitals and compare its performance directly against the existing NEWS2 score.
Methods:
In a retrospective cohort study across three Singapore hospitals (116,952 adult inpatient encounters; 2022-2025), an XGBoost model using 30 routine clinical variables was compared against NEWS2 and logistic regression. The primary composite outcome was ICU/high-dependency unit admission, code blue, or death within 24 hours. Performance was evaluated across 100 bootstrap samples using AUROC, AUPRC, and Prediction Efficiency Curves.
Results:
Across external validation sites, the XGBoost clinical model achieved AUROCs of 0.884-0.895 (an 8-13 percentage point improvement over NEWS2) and AUPRC improvements of 45-135%. At a 1% alert threshold matching baseline prevalence, the model detected 45-88% more deterioration cases than NEWS2 at identical alert volumes. Alternatively, it required 33-55% fewer alerts to achieve 50% sensitivity. Discrimination and calibration remained consistent across Chinese, Malay, and Indian ethnic subgroups despite excluding ethnic group as a predictor.
Conclusions:
An XGBoost model utilising routinely available clinical variables significantly outperforms NEWS2 across diverse acute care settings, substantially reducing clinical alert burden while improving deterioration detection.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.