AI-Enhanced ECG Screenings: An Alternative to Traditional Questionnaires for Ischaemic Heart Disease

Area of Science:

• Cardiology
• Medical Artificial Intelligence
• Public Health

Background:

• Ischaemic heart disease (IHD) is the primary global cause of mortality.
• Traditional risk scores (e.g., FRS, SCORE) have limitations in accuracy, generalizability, and detecting subclinical disease, especially in low- and middle-income countries (LMICs).

Purpose of the Study:

• To explore the potential of artificial intelligence-enhanced electrocardiogram (AI + ECG) analysis as a superior alternative for IHD risk stratification.
• To advocate for policy changes and large-scale validation of AI + ECG in diverse global populations.

Main Methods:

• Review of existing evidence on traditional IHD screening tools.
• Exploration of AI + ECG technology leveraging objective electrophysiological data.
• Analysis of AI + ECG's potential for cost-effectiveness and accessibility.

Main Results:

• AI + ECG analysis shows promise for more accurate, automated, and cost-effective IHD risk stratification.
• Evidence suggests AI + ECG models outperform traditional methods in diagnostic tasks.
• Significant need for validation in diverse global populations, particularly LMICs, remains.

Conclusions:

• AI + ECG represents a potentially transformative approach to early IHD detection, especially in resource-constrained settings.
• Urgent large-scale validation trials, ethical frameworks, and sustained funding are necessary to implement AI + ECG screenings globally.
• Policy shifts are needed to democratize IHD detection and reduce global cardiovascular mortality.