Heart failure & cardiomyopathiesCross-sectional study
Advanced prediction of heart failure risk in elderly diabetic and hypertensive patients using nine machine learning models and novel composite indices: insights from NHANES 2003–2016
- Cross-sectional study
- machine learning prediction models
- NHANES 2003–2016
- Missing values imputed using random forest algorithms
- Feature importance by SHAP values
Authors' conclusion
The study demonstrates that novel composite indices like ABSI, AIP, BARD score, BFP, BRI, FLI, and PNI have significant potential in predicting HF risk among elderly diabetic and hypertensive patients.
Study context
- Population
- Elderly patients (aged 65 and above) with both diabetes and hypertension, NHANES 2003–2016of 71,058 NHANES subjects
- Participants
- 1,445 patients
- Outcome
- HF status
Main finding
As reported in the abstract
HF prediction
| Group | AUC |
|---|---|
| XGBoost | 0.96 |
Observational data: associations, not effects.
Original publication
Advanced prediction of heart failure risk in elderly diabetic and hypertensive patients using nine machine learning models and novel composite indices: insights from NHANES 2003–2016. Eur J Prev Cardiol. Published 27 February 2025. doi:10.1093/eurjpc/zwaf081
Summarised from the published abstract; every number is checked against it