DCM-PROGRESS: predicting end-stage heart failure in non-ischemic dilated cardiomyopathy patients

Area of Science:

• Cardiology
• Medical Informatics
• Predictive Analytics

Background:

• Non-ischemic dilated cardiomyopathy (DCM) patients face significant risk of end-stage heart failure (HF).
• Accurate risk prediction is crucial for timely intervention and personalized patient management.
• Current risk stratification tools may require enhancement for DCM-specific populations.

Approach:

• A risk-prediction model was developed using lasso and support vector machine (SVM) algorithms.
• Data from Dutch (n=293) and Czech (n=235) DCM cohorts were used for derivation and external validation.
• Predictors included clinical, ECG, echocardiographic, and biochemical parameters.

Key Points:

• The lasso-derived model identified NYHA class, heart rate, systolic blood pressure, height, R-axis, and TAPSE as key predictors.
• The model demonstrated high discriminative performance (c-statistic 0.85 in derivation, 0.75 in validation).
• Performance surpassed the MAGGIC score (c-statistic 0.69), indicating superior predictive accuracy.

Conclusions:

• A validated, highly discriminative risk-prediction model for end-stage HF in DCM patients was successfully developed.
• The DCM-PROGRESS model shows potential to significantly enhance clinical decision-making and patient monitoring strategies.
• International validation suggests broad applicability in diverse clinical settings.