AI-Derived Score to Predict Effort Intolerance and Adverse Outcome across the Heart Failure Spectrum.

AIMS: To develop and externally validate an artificial intelligence (AI)-driven model to predict effort intolerance (i.e., peak oxygen uptake [VO₂] <16 mL/kg/min) in patients at risk or with established heart failure (HF). METHODS: We enrolled a consecutive sample of adults referred for dyspnea or suspected HF. The derivation cohort (Pisa, Italy) included 1,333 participants - 351 with reduced (<50%, HFrEF), 371 with preserved (≥50%, HFpEF) left ventricular ejection fraction (LVEF), and 611 with cardiovascular risk factors and/or structural heart disease without overt HF (Stages A-B); the external validation cohort (Hasselt, Belgium) included 1,101 participants. All participants underwent clinical evaluation, laboratory test, rest echocardiography, and cardiopulmonary exercise testing. RESULTS: A neural network including age, sex, body mass index (BMI), haemoglobin, left ventricular systolic mitral annulus tissue velocity (LV S'), systolic pulmonary artery pressure (sPAP), and β-blocker therapy achieved the best discrimination (AUC 0.86±0.01 in derivation; 0.76±0.06 in validation). A simplified four-variable AI-VO₂ score (BMI, haemoglobin, LV S', sPAP) showed good performance (AUC 0.79±0.05) and independently predicted HF hospitalization or all-cause death (adjusted HR 1.06 per point; 95% CI 1.03-1.10) in the derivation cohort. External validation confirmed the predictive and prognostic performance (AUC 0.73±0.02; unadjusted HR 1.18 per point, 95% CI 1.13-1.24). Score-based risk strata (<10, low; 10-13, intermediate; >13, high) showed a significant prognostic gradient (log-rank χ² = 36.8, p<0.001). CONCLUSION: The AI-VO₂ score is a clinically interpretable, externally validated tool for identifying patients with effort intolerance and adverse outcomes across the HF spectrum, supporting personalized risk stratification and management.