Machine learning predicts persistent fever after antibiotics in two cancer cohorts
Source check: Source checked. Not independent scientific confirmation.
Finding: Using routine clinical records, the study predicted persistent fever after antibiotic treatment in two cancer cohorts. The best point-estimate model achieved AUROC 0.82 in the internal cohort and 0.78 at an external hospital. This retrospective prediction study does not establish effects on antibiotic use or patient outcomes.
Technology: TabPFN and comparator machine-learning models
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- TabPFN and comparator learners estimate persistent-fever risk from clinical records.
- Test and result
- Models predicted the case-defined persistent-fever outcome from routine records in two retrospective cohorts; the best AUROCs were 0.82 internally and 0.78 at an external hospital.
- Limitation / still unknown
- The study does not establish improved antibiotic use or patient outcomes; evaluation is retrospective.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://www.nature.com/articles/s41746-026-03449-w
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 date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
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.
Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.