Scholarlink

Purpose of Review <p>Heart failure (HF) remains a major public health challenge, often diagnosed only after symptom onset. This review describes how artificial intelligence-enhanced electrocardiography (AI-ECG) can support scalable HF screening and risk stratification across diverse settings. We also identify priorities for clinical implementation and future research.</p> Recent Findings <p>AI-ECG augments conventional ECG interpretation by detecting subtle structural and functional abnormalities not apparent on visual inspection. Across cohorts, models using 12-lead ECG waveforms, ECG images, and wearable single-lead recordings identify HF precursors and predict new-onset HF risk with performance comparable to established risk scores. AI-ECG-enabled strategies can be cost-effective, particularly when deployed opportunistically in routine care or targeted community programs.</p> Summary <p>AI-ECG leverages the ubiquity of ECG testing to provide a practical platform for HF risk assessment and to guide confirmatory imaging, risk factor surveillance, and therapy decisions. Realizing this potential will require interoperable ECG standards, prospective validation, regulatory oversight, and performance monitoring for safe, equitable integration into HF care pathways.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Artificial Intelligence-enhanced Electrocardiography for Heart Failure Screening and Risk Stratification

  • 期刊论文

  • 发表日期：

    2026年3月16日

查看全文
  • Lovedeep S Dhingra,
  • Philip M Croon,
  • Bruno Batinica,
  • Arya Aminorroaya,
  • Aline F Pedroso,
  • Rohan Khera

摘要

Purpose of Review

Heart failure (HF) remains a major public health challenge, often diagnosed only after symptom onset. This review describes how artificial intelligence-enhanced electrocardiography (AI-ECG) can support scalable HF screening and risk stratification across diverse settings. We also identify priorities for clinical implementation and future research.

Recent Findings

AI-ECG augments conventional ECG interpretation by detecting subtle structural and functional abnormalities not apparent on visual inspection. Across cohorts, models using 12-lead ECG waveforms, ECG images, and wearable single-lead recordings identify HF precursors and predict new-onset HF risk with performance comparable to established risk scores. AI-ECG-enabled strategies can be cost-effective, particularly when deployed opportunistically in routine care or targeted community programs.

Summary

AI-ECG leverages the ubiquity of ECG testing to provide a practical platform for HF risk assessment and to guide confirmatory imaging, risk factor surveillance, and therapy decisions. Realizing this potential will require interoperable ECG standards, prospective validation, regulatory oversight, and performance monitoring for safe, equitable integration into HF care pathways.