The Predictive Value of the Pan-Immune-Inflammation Value for Atrial Fibrillation Risk in Patients with Coronary Artery Disease: A Multicenter Machine Learning Study.
Source check: Source checked. Not independent scientific confirmation.
Finding: In a retrospective multicenter cohort of patients with coronary heart disease, pan-immune-inflammation value was higher in patients with atrial fibrillation and was selected with age and diabetes as an independent predictor in logistic regression. XGBoost achieved AUC 0.79 in training and 0.73 in testing, outperforming the multilayer perceptron (0.75 and 0.69). This establishes association and prediction within the study, not causation or clinical benefit.
Technology: XGBoost and multilayer-perceptron risk models with SHAP interpretation
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- The learned models estimated atrial-fibrillation risk from clinical and laboratory data; SHAP assessed feature contributions, while logistic regression identified PIV, age and diabetes as predictors.
- Test and result
- The study compared XGBoost and a multilayer perceptron using patients from two tertiary hospitals. It reports training/test AUCs of 0.79/0.73 for XGBoost and 0.75/0.69 for MLP; PIV was the most influential XGBoost feature.
- Limitation / still unknown
- The retrospective model does not establish that PIV causes atrial fibrillation or improves clinical outcomes; prospective external evaluation is not reported.
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/PMC13012144/ · https://pubmed.ncbi.nlm.nih.gov/41883473/
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 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.