Prediction of Influenza Complications: Development and Validation of a Machine Learning Prediction Model to Improve and Expand the Identification of Vaccine-Hesitant Patients at Risk of Severe Influen
Source check: Source checked. Not independent scientific confirmation.
Finding: XGBoost risk scores predicted influenza complications using population-scale electronic health records and compared performance with age/sex and CDC/WHO-inspired scores. The authors report test performance and blinded subgroup validation; this is a specific epidemiological risk-stratification result, with confounding and transportability limits.
Technology: XGBoost predicts influenza complications from electronic health-record features.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- XGBoost predicts influenza complications from electronic health-record features.
- Test and result
- XGBoost classifier developed from Geisinger EHR data (>641,000 unique individuals; final unvaccinated cohort 604,389), with 6-fold CV tuning, blinded random subsets and bootstrapped evaluation; GFlu-CxFlag AUC ~0.79, severe-complication cohort AUC ~0.828. Compared with CDC/WHO risk model and subgroup bias analysis.
- Limitation / still unknown
- XGBoost risk scores predicted influenza complications using population-scale electronic health records and compared performance with age/sex and CDC/WHO-inspired scores. The authors report test performance and blinded subgroup validation; this is a specific epidemiological risk-stratification result, with confounding and transportability limits.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://mdpi-res.com/d_attachment/jcm/jcm-11-04342/article_deploy/jcm-11-04342.pdf · https://pubmed.ncbi.nlm.nih.gov/35893436/
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.