Logo

American Heart Association

  28
  0


Final ID:

Improved Identification of Near-Term Heart Failure Risk in Pooled Cohort Studies Using ECG-AI and PREVENT-HF

Abstract Body (Do not enter title and authors here): Background: FDA-cleared artificial intelligence algorithms applied to 12-lead ECGs (ECG-AI) offer a scalable, noninvasive approach for early detection of heart failure.

Hypothesis: We hypothesized that ECG-AI models would improve near-term identification of HF risk when compared to a previously validated clinical risk prediction tool.

Methods: We used baseline ECG and clinical data from the Multi-Ethnic Study of Atherosclerosis, Framingham Heart Study, and Cardiovascular Heart Study to estimate the risk of incident heart failure using dichotomous ECG-AI software-as-a-medical devices (SaMDs) designed to identify left ventricular diastolic dysfunction (ECG-AI DD) and low left ventricular ejection fraction (ECG-AI LEF). All subjects with adequate clinical and ECG data to estimate PREVENT-HF and ECG-AI scores were included for analysis. We assessed the utility of ECG-AI for identifying HF cases beyond those identified by the PREVENT-HF score. In this framework, a positive result on ECG-AI is treated as high risk regardless of underlying PREVENT-HF score. The C-statistic was used to assess discrimination of PREVENT-HF and PREVENT-HF plus ECG-AI and net reclassification improvement (NRI) was used to assess improvement in the identification of additional HF over PREVENT-HF for estimated risk at 3- and 10-years at the 10% and 20% thresholds.

Results: A total of 14,250 subjects from these cohorts with available data to generate both ECG-AI and PREVENT-HF scores were pooled for the analysis. The C-statistics for PREVENT-HF for identifying HF incidence in the pooled cohorts over 3- and 10-year timeframes were 0.858 (95%CI 0.841 - 0.875) and 0.881 (0.873 - 0.89). The corresponding C-statistics for PREVENT-HF with ECG-AI added were 0.898 (0.885 - 0.909) and 0.894 (0.887 - 0.902), respectively (Table 1). The corresponding NRI for ECG-AI-based up-risking relative to PREVENT-HF at 10% and 20% thresholds was 10.7% and 39.7% (3-year) and 8.3% and 32.7% (10-year), respectively (Table 2).

Conclusion: ECG-AI LEF and ECG-AI DD significantly enhance PREVENT-HF in identifying patients at high short-term risk for heart failure. These findings support ECG-AI as a scalable, actionable tool that complements standard risk scores and enables targeted HF prevention.
  • Desai, Akshay  ( BRIGHAM WOMENS HOSPITAL , Boston , Massachusetts , United States )
  • Pandey, Ambarish  ( UT Southwestern Medical Center , Dallas , Texas , United States )
  • Suratekar, Rohit  ( Anumana, Inc. , Boston , Massachusetts , United States )
  • Alger, Heather  ( Anumana, Inc , Cambridge , Massachusetts , United States )
  • Awasthi, Samir  ( Anumana, Inc. , Boston , Massachusetts , United States )
  • Ahmad, Faraz  ( NORTHWESTERN UNIV SCHOOL MEDICINE , Chicago , Illinois , United States )
  • Oh, Jae  ( MAYO CLINIC , Rochester , Minnesota , United States )
  • Khan, Sadiya  ( Northwestern University , Chicago , Illinois , United States )
  • Shah, Sanjiv  ( NORTHWESTERN UNIVERSITY , Chicago , Illinois , United States )
  • Author Disclosures:
    Akshay Desai: DO have relevant financial relationships ; Research Funding (PI or named investigator):Abbott:Past (completed) ; Consultant:River2Renal:Active (exists now) ; Consultant:Roche:Active (exists now) ; Consultant:Regeneron:Active (exists now) ; Consultant:New Amsterdam:Active (exists now) ; Consultant:Novartis:Past (completed) ; Consultant:Merck:Past (completed) ; Consultant:Medtronic:Past (completed) ; Consultant:Medpace:Active (exists now) ; Consultant:GlaxoSmithKline:Past (completed) ; Consultant:Endotronix:Active (exists now) ; Consultant:CVS:Active (exists now) ; Consultant:Boston Scientific:Active (exists now) ; Researcher:Biofourmis:Active (exists now) ; Consultant:Bayer:Active (exists now) ; Consultant:Axon Therapies:Past (completed) ; Consultant:Avidity Biopharma:Active (exists now) ; Consultant:AstraZeneca:Active (exists now) ; Consultant:Alnylam:Active (exists now) ; Consultant:Abbott:Active (exists now) ; Research Funding (PI or named investigator):Pfizer:Active (exists now) ; Research Funding (PI or named investigator):Novartis:Past (completed) ; Research Funding (PI or named investigator):Bayer:Active (exists now) ; Research Funding (PI or named investigator):AstraZeneca:Active (exists now) ; Research Funding (PI or named investigator):Alnylam:Active (exists now) | Ambarish Pandey: DO have relevant financial relationships ; Consultant:Tricog:Active (exists now) ; Consultant:Sarfez Therapeutics, Edwards Lifesciences, Merck, Bayer, Anumana, Alleviant, Pfizer, Abbott, Axon Therapies, Kilele Health, Acorai, Kardigan, Novartis, Idorsia Pharma, and Science37:Active (exists now) ; Consultant:Rivus:Active (exists now) ; Consultant:iRhythm:Active (exists now) ; Researcher:SQ innovations:Active (exists now) ; Research Funding (PI or named investigator):SC Pharma:Active (exists now) ; Consultant:Astra Zeneca:Active (exists now) ; Research Funding (PI or named investigator):Ultromics:Active (exists now) ; Research Funding (PI or named investigator):Roche:Active (exists now) ; Consultant:Ultromics:Active (exists now) ; Consultant:Roche:Active (exists now) ; Consultant:Lilly:Active (exists now) ; Consultant:Bayer:Active (exists now) ; Consultant:Novo Nordisk:Active (exists now) | Rohit Suratekar: DO have relevant financial relationships ; Employee:nference:Past (completed) ; Employee:Anumana:Active (exists now) | Heather Alger: DO have relevant financial relationships ; Employee:Anumana, Inc:Active (exists now) ; Consultant:American Heart Association:Active (exists now) ; Employee:nference, Inc:Past (completed) | Samir Awasthi: DO have relevant financial relationships ; Employee:Anumana:Active (exists now) | Faraz Ahmad: DO have relevant financial relationships ; Research Funding (PI or named investigator):Pfizer:Past (completed) ; Consultant:AstraZeneca:Past (completed) ; Speaker:AstraZeneca:Past (completed) ; Speaker:Alnylam:Past (completed) ; Consultant:Alnylam Pharmceuticals:Active (exists now) ; Research Funding (PI or named investigator):Abiomed/Johnson and Johnson:Active (exists now) ; Research Funding (PI or named investigator):AstraZeneca:Active (exists now) ; Research Funding (PI or named investigator):Atman Health:Past (completed) ; Research Funding (PI or named investigator):Tempus:Active (exists now) ; Research Funding (PI or named investigator):Atman Health :Past (completed) | Jae Oh: DO have relevant financial relationships ; Royalties/Patent Beneficiary:Anumana:Active (exists now) ; Consultant:Medtronic:Active (exists now) | Sadiya Khan: DO NOT have relevant financial relationships | Sanjiv Shah: DO NOT have relevant financial relationships
Meeting Info:

Scientific Sessions 2025

2025

New Orleans, Louisiana

Session Info:

Trials and Deployments of Artificial Intelligence in Cardiology

Saturday, 11/08/2025 , 03:15PM - 04:30PM

Featured Science

More abstracts from these authors:
You have to be authorized to contact abstract author. Please, Login
Not Available