> ## Content Index
> Fetch the complete content index at: https://www.coios.me/llms.txt
> Use this file to discover other available public pages before exploring further.

# NEWS early warning score and machine learning give similar net benefit for 24 h mortality
- URL: https://www.coios.me/news-early-warning-score-and-machine-learning-give-similar/
- Published: 2026-11-08T13:18:35.000Z
- Updated: 2026-11-08T14:06:35.000Z
- Description: A gradient-boosting model flagged at most 1·9 more 24 h deaths per 10 000 patients than NEWS, in Danish hospitals.
- Author: Daniel Ryan
- Tags: Data, models and systems, AI in medicine, Denmark, #peer-reviewed, #refines, #item, #source-2026-11, #score-78

This retrospective cohort compared the National Early Warning Score (NEWS) with simplified NEWS, a demographic score and a gradient-boosting model. It covered 2·08 million adult encounters at 15 Danish hospitals, 2018–2023, with 24 h mortality as the outcome. Treatment within 24 h, such as ICU admission or an operation, can avert predicted deaths and bias validation. This intervention bias was handled by setting treated encounters aside and weighting the rest by propensity scores. Overall, the model added at most 1·9 correct identifications per 10 000 over NEWS, and NEWS 1·5 over simplified NEWS. The design is retrospective, and unmeasured factors behind treatment decisions may bias the weighted estimates.

*Why it is interesting: Most validations report discrimination, but this one counts extra deaths correctly flagged. The gain over NEWS was under 2 per 10 000 overall, but 78·1 when initial NEWS was 7 or more.*

Source

[The Lancet Digital Health, 5 November 2026](https://doi.org/10.1016/j.landig.2026.101067?ref=coios.me)

Paper

Development and validation of early warning scores predicting 24 h mortality addressing intercurrent medical interventions in Denmark: a multicentre retrospective cohort study of 2·08 million hospital encounters

Authors

Katsiferis A, Scheidwasser N, Nguyen TL, Lange T, Khurana MP, Nielsen PB et al.

DOI

10.1016/j.landig.2026.101067

Full text

[Open copy](https://curis.ku.dk/ws/files/539588102/2025.10.12.25337794v1.full.pdf?ref=coios.me) (submitted version, before peer review, repository)

Type

Peer-reviewed article

Design

Multicentre retrospective cohort, 15 Danish hospitals, 2,080,765 encounters / 825,200 patients, Oct 2018–Oct 2023; propensity-weighted net benefit, AUROC, calibration

Verdict

Refines prior evidence

Driver

[AI in medicine](https://www.coios.me/d-ai-medicine/)