Key result
Machine learning outperforms traditional models in predicting HFmrEF mortality and rehospitalization with a 0.83 C-index.
Why the study?
Heart failure with mildly reduced ejection fraction is recognized as a unique phenotype, but risk stratification models for mortality and HF re-hospitalization are lacking.
Do machine learning models improve risk prediction for mortality and re-hospitalization in patients with HFmrEF compared to traditional models?
Observational (n=519)
Yes
Do machine learning models improve risk prediction for mortality and re-hospitalization in patients with HFmrEF compared to traditional models?
Machine learning models, particularly LASSO Cox regression and random forest, outperform traditional models in predicting mortality and re-hospitalization in patients with HFmrEF, highlighting the prognostic importance of KCCQ scores.
Answers are grounded in this paper and cite their sources.
ML models may aid HFmrEF risk stratification; leaves open prospective validation before clinical adoption.
Objective: Heart failure with mildly reduced ejection fraction (HFmrEF) has been recently recognized as a unique phenotype of heart failure (HF) in current practical guideline. However, risk stratification models for mortality and HF re-hospitalization are still lacking. This study aimed to develop and validate a novel machine learning (ML)-derived model to predict the risk of mortality and re-hospitalization for HFmrEF patients. Methods: We assessed the risks of mortality and HF re-hospitalization in HFmrEF (45-49%) patients enrolled in the TOPCAT trial. Eight ML-based models were constructed, including 72 candidate variables. The Harrell concordance index (C-index) and DeLong test were used to assess discrimination and the improvement in discrimination between models, respectively. Calibration of the HF risk prediction model was plotted to obtain bias-corrected estimates of predicted versus observed values. Results: Least absolute shrinkage and selection operator (LASSO) Cox regression was the best-performing model for 1- and 6-year mortality, with a highest C-indices at 0.83 (95% CI: 0.68-0.94) over a maximum of 6 years of follow-up and 0.77 (95% CI: 0.64-0.89) for the 1-year follow-up. The random forest (RF) showed the best discrimination for HF re-hospitalization, scoring 0.80 (95% CI: 0.66-0.94) and 0.85 (95% CI: 0.71-0.99) at the 6- and 1-year follow-ups, respectively. For risk assessment analysis, Kansas City Cardiomyopathy Questionnaire (KCCQ) subscale scores were the most important predictor of readmission outcome in the HFmrEF patients. Conclusion: ML-based models outperformed traditional models at predicting mortality and re-hospitalization in patients with HFmrEF. The results of the risk assessment showed that KCCQ score should be paid increasing attention to in the management of HFmrEF patients.
No takes yet. Share an insight, caveat, or question.
Zhao et al. (2022) conducted an observational in Heart failure with mildly reduced ejection fraction (HFmrEF) (n=519). Machine learning models (LASSO Cox regression and Random Forest) vs. Traditional statistical models was evaluated on 6-year all-cause mortality prediction (LASSO Cox regression) (C-index 0.83, 95% CI 0.68-0.94). Machine learning models outperformed traditional models in predicting mortality and heart failure re-hospitalization in patients with mildly reduced ejection fraction, with LASSO Cox regression achieving a C-index of 0.83 for 6-year mortality.
Synapse has enriched 10 related papers. Consider them for comparative context: