COMPOSER sepsis model flags unfamiliar cases instead of guessing
COMPOSER, a deep-learning early sepsis predictor, reached AUCs of 0.925-0.953 in ICU and 0.938-0.945 in ED across six cohorts (515,720 patients) from two US health systems. About 20% of non-septic and 8% of septic prediction windows were marked indeterminate, and the model gave a median early warning of 12.2 hours in ICU and 2.1 hours in ED before the first antibiotics order. The abstract reports no prospective deployment or patient-outcome results.
Technology: COMPOSER deep-learning model with uncertainty-based indeterminate output
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
Result, AI contribution and limits
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
- Publication status: Peer-reviewed paper
- Test type: retrospective or benchmark
- Tested: COMPOSER's AUCs were measured across six cohorts (515,720 patients) from two US health systems in ICU and ED settings, with the share of predictions marked indeterminate and early-warning time before the first antibiotics order.
- Still unknown: The abstract reports no prospective deployment or patient-outcome results; data come from only two US health systems.
- AI role: A deep-learning model predicted early sepsis and marked unfamiliar cases as indeterminate rather than guessing.
Evidence sources: https://www.ebi.ac.uk/europepmc/webservices/rest/search?query=DOI:10.1038/s41746-021-00504-6&resultType=core&format=json
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review scope and date are not recorded; source checked does not establish full-text review.
Citations: in the top 1% of works of the same type, year and subfield (OpenAlex work metrics, 147 citations; as of 15 Nov 2026). Attention, not a measure of correctness; not part of the score.
Editorial assessment: Impact 4/5 · Validation 2/5 · Novelty 4/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.
Follow-up and relationships
No follow-up recorded; this is not a claim that no follow-up exists.
Follow-up review scope and date are not recorded.
No source-supported relationships recorded.