Anumana Pioneers AI-Driven Cardiovascular Diagnostics with Breakthrough Heart Failure Study and Key Findings at AHA 2025
Anumana, a trailblazer in AI-powered cardiovascular diagnostics, has unveiled groundbreaking clinical data at the American Heart Association (AHA) Scientific Sessions 2025. Among the highlights was a late-breaking featured science presentation, simultaneously published in the prestigious Journal of the American College of Cardiology. This study demonstrates how artificial intelligence applied to electrocardiograms (ECG-AI) can significantly enhance the near-term prediction of incident heart failure, surpassing traditional clinical risk models. Anumana also showcased three additional abstracts at the conference, further solidifying its leadership in leveraging AI for cardiovascular care.
Revolutionizing Heart Failure Risk Assessment with ECG-AI
The featured 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 participants across three major longitudinal cohorts: the Framingham Heart Study, Multi-Ethnic Study of Atherosclerosis, and Cardiovascular Health Study. The findings revealed that integrating Anumana’s ECG-AI with the PREVENT-HF clinical risk equation substantially improved short-term heart failure risk prediction. Notably, the AI-driven approach reclassified up to 12.5% of individuals into higher-risk categories—individuals who were not identified by clinical factors alone. Participants with positive ECG-AI results were more than 20 times as likely to develop heart failure within three years compared to those with negative results.
Dr. Akshay S. Desai, MD, MPH, Director of the Heart Failure Disease Management Program at Brigham and Women’s Hospital and the study’s lead investigator, emphasized the significance of these findings. “AI analysis of standard 12-lead electrocardiograms (ECG-AI) allows us to detect subtle electrical changes that signal early cardiac dysfunction. These results suggest that ECG-AI can enhance the detection of patients at risk for heart failure when combined with standard clinical risk assessments like the PREVENT-HF score. The implication is profound: ECG-AI may enable clinicians to identify at-risk patients years before symptoms appear, opening the door to earlier preventive therapy and better long-term outcomes.”
Collaborative Research and Cutting-Edge Technology
The study was conducted in collaboration with the National Heart, Lung, and Blood Institute’s HeartShare/AMP Heart Failure Program, utilizing the BioData Catalyst platform. This platform accelerates reproducible biomedical research and facilitates access to deeply phenotyped, longitudinal cohorts, enabling robust evaluations of ECG-AI for predicting early heart failure risk. The rigorous methodology underscores the reliability and potential impact of Anumana’s technology.
“This publication marks meaningful progress toward a future where AI helps prevent disease rather than merely detecting it,” said Simos Kedikoglou, MD, President and COO of Anumana. “Our ECG-AI LEF algorithm uncovers early signs of heart failure, empowering clinicians to identify at-risk patients sooner and deliver more proactive care.”
Performance Metrics of the ECG-AI LEF Algorithm
Anumana’s ECG-AI™ Left Ventricular Ejection Fraction (LEF) algorithm analyzes standard 12-lead ECGs to identify patients with reduced LEF, a critical indicator of heart failure. The algorithm demonstrated exceptional performance, achieving an area under the curve (AUC) of 0.944, with a sensitivity of 90.2% and specificity of 85.1%. These metrics highlight its strong ability to detect patients at risk for heart failure, making it a valuable tool for early intervention.
Expanding Applications of AI Across Cardiovascular Conditions
Beyond the featured study, Anumana presented three additional abstracts showcasing the versatility of its AI technology across various cardiovascular conditions:
- Multicenter Study of ECG-AI for Pulmonary Hypertension
In a multicenter study involving five U.S. health systems, ECG-AI detected pulmonary hypertension with 84% sensitivity and 72% specificity. These results support the potential for earlier identification of this life-threatening condition, enabling timely interventions. - AI ECG for Early Identification of Pulmonary Arterial and Chronic Thromboembolic Pulmonary Hypertension
A retrospective real-world data analysis found that more than 74% of patients evaluated between symptom onset and diagnosis had at least one ECG flagged as positive by ECG-AI. This finding suggests the technology could reduce diagnostic delays and improve patient outcomes. - Parity and Takotsubo Cardiomyopathy
Researchers developed a novel methodology to determine the lifetime number of pregnancies from electronic health record data, exploring potential associations between parity and the risk of Takotsubo cardiomyopathy. This innovative approach highlights the potential of AI to uncover new insights into cardiovascular conditions.
Advancing Cardiovascular Care Through Innovation
Together, these studies underscore Anumana’s commitment to translating advanced AI models into clinically actionable solutions. By enabling earlier detection, targeted interventions, and improved cardiovascular outcomes, Anumana is redefining the landscape of cardiovascular care. Its ECG-AI technology represents a transformative leap forward, offering clinicians powerful tools to identify at-risk patients and intervene proactively.
As Anumana continues to push the boundaries of AI-driven diagnostics, its work holds immense promise for preventing heart failure and other cardiovascular diseases. By harnessing the power of AI, the company is paving the way for a future where predictive medicine becomes the cornerstone of healthcare, ultimately saving lives and improving patient well-being.
For more information about Anumana’s groundbreaking research and innovations, visit their official website or explore the full findings presented at AHA 2025.
About Anumana
Anumana is an AI-driven health technology company committed to transforming cardiovascular care. Co-founded by nference and Mayo Clinic, Anumana develops software-as-a-medical-device (SaMD) solutions that apply multimodal AI to support early detection, clinical decision-making, and intraoperative guidance across the continuum of care. The company’s portfolio includes ECG-based algorithms, generative imaging applications, and real-time procedural support tools designed to improve outcomes in both diagnostic and perioperative settings. The company’s FDA-cleared ECG-AI™ LEF algorithm is currently available in the U.S. and eligible for reimbursement as of January 2025. To learn more or schedule a demo, visit ECG-AI LEF. Please visit www.anumana.ai for more information and follow Anumana on LinkedIn and X for company updates.
