Interpretable machine learning models for the prediction of all-cause mortality and time to death in hemodialysis patients.
Source check: Source checked. Not independent scientific confirmation.
Finding: The primary full-text record describes a 359-patient retrospective hemodialysis cohort and evaluated ML mortality/time-to-death predictions; this supports a specific clinical prediction study, not clinical benefit.
Technology: Random forest, support-vector machine and logistic-regression models predict all-cause mortality; random-forest regression estimates time to death, with SHAP factor interpretation.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Random forest, support-vector machine and logistic-regression models predict all-cause mortality; random-forest regression estimates time to death, with SHAP factor interpretation.
- Test and result
- In 359 hemodialysis patients, the optimized full-variable random forest had mortality AUROC 0.86±0.07 (sensitivity 0.86, specificity 0.75); a 22-variable model had AUROC 0.80±0.06.
- Limitation / still unknown
- Retrospective single-cohort prediction does not establish improved survival or generalization to other dialysis populations.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://pmc.ncbi.nlm.nih.gov/articles/PMC11879476/
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.
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 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.