Predicting the severity of COVID-19 using machine learning methods.
Source check: Source checked. Not independent scientific confirmation.
Finding: Among 816 hospitalized patients in one Iranian province, retrospective models classified COVID-19 severity from blood tests; random forest and XGBoost reached AUCs of 0.91 and 0.90, with D-dimer a strong predictor.
Technology: Support vector machine, least-squares support vector machine, random forest and XGBoost models classified COVID-19 severity from routine blood-test records.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Support vector machine, least-squares support vector machine, random forest and XGBoost models classified COVID-19 severity from routine blood-test records.
- Test and result
- A retrospective study of 816 hospitalized patients in Hamadan Province used WHO-based severe/non-severe labels. Random forest and XGBoost AUCs were 0.91 and 0.90, with mean sensitivities of 76% and at least 74%; D-dimer was a leading predictor.
- Limitation / still unknown
- The study is a retrospective classification from one province. External validation, prospective clinical performance and benefit from model-guided care are not established.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://link.springer.com/article/10.1186/s12911-026-03411-6
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.