Anumana, a leader in AI-powered cardiovascular diagnostics, unveiled groundbreaking clinical findings at the American Heart Association (AHA) Scientific Sessions 2025, demonstrating the transformative potential of artificial intelligence in predicting heart failure. The highlight was a late-breaking study published simultaneously in the Journal of the American College of Cardiology, showing that AI analysis of standard 12-lead electrocardiograms—known as ECG-AI—significantly improves near-term prediction of incident heart failure beyond traditional clinical risk models. The study, titled “Enhanced Prediction of Incident Heart Failure Using Artificial Intelligence-Driven Analysis of 12-Lead Electrocardiogram Waveforms: A HeartShare/AMP-HF Pooled Cohort Analysis,” analyzed data from over 14,000 individuals across three major longitudinal studies: the Framingham Heart Study, the Multi-Ethnic Study of Atherosclerosis, and the Cardiovascular Health Study. Researchers found that combining Anumana’s ECG-AI with the PREVENT-HF clinical risk score reclassified up to 12.5% of patients into higher-risk categories that would have been missed using clinical factors alone. Individuals with positive ECG-AI results were more than 20 times more likely to develop heart failure within three years compared to those with negative results. “This study shows that AI can detect subtle electrical changes in the ECG that signal early cardiac dysfunction—long before symptoms appear,” said Dr. Akshay S. Desai, Director of the Heart Failure Disease Management Program at Brigham and Women’s Hospital and lead investigator. “By identifying at-risk patients years in advance, ECG-AI opens the door to earlier preventive interventions, potentially improving long-term outcomes.” The research was conducted under the National Heart, Lung, and Blood Institute’s HeartShare/AMP Heart Failure Program using the BioData Catalyst platform, which enables secure, reproducible biomedical research through access to large, deeply phenotyped datasets and advanced analytics. Simos Kedikoglou, MD, President and COO of Anumana, emphasized the broader implications: “This marks a shift from AI as a diagnostic tool to AI as a preventive force. Our ECG-AI LEF algorithm can uncover hidden signs of heart failure, empowering clinicians to act earlier and more effectively.” Anumana’s ECG-AI LEF algorithm achieved an AUC of 0.944, with 90.2% sensitivity and 85.1% specificity, underscoring its high accuracy in identifying patients at risk for heart failure. In addition to the featured study, Anumana presented three other abstracts at AHA 2025, showcasing the versatility of its AI platform across a range of cardiovascular conditions. These studies further validate the company’s mission to integrate advanced AI into clinical workflows to enable earlier detection, better decision-making, and improved patient outcomes. Anumana, co-founded by nference and the Mayo Clinic, develops software-as-a-medical-device (SaMD) solutions that use multimodal AI to support early detection, clinical decision-making, and real-time guidance during procedures. Its FDA-cleared ECG-AI LEF algorithm is now available in the U.S. and eligible for reimbursement as of January 2025. For more information or to schedule a demo, visit www.anumana.ai. Follow Anumana on LinkedIn and X for the latest updates.