Use of artificial intelligence for detecting left ventricular dysfunction and predicting incident heart failure risk

Area of Science:

• Cardiology
• Artificial Intelligence
• Preventive Medicine

Background:

• Effective medications exist for heart failure (HF) prevention.
• Patient engagement and adherence to preventive therapies for those at risk remain challenging.
• Identifying individuals with subclinical cardiac dysfunction is crucial for targeted, intensive management programs.

Purpose of the Study:

• To explore the potential of artificial intelligence (AI) in facilitating community-based heart failure screening.
• To investigate how AI can enhance the identification of at-risk individuals within the aging population.
• To assess AI's role in improving the accessibility and interpretation of cardiac diagnostic tools.

Main Methods:

• Literature review on AI applications in cardiovascular risk assessment and screening.
• Analysis of AI's potential to augment electrocardiography (ECG) and echocardiography.
• Exploration of AI-driven pathways for community-based HF screening.

Main Results:

• AI can identify clinical risk factors and select high-risk individuals.
• AI can enhance the diagnostic value of ECG and facilitate non-expert echocardiography.
• AI-informed screening pathways can maximize access and minimize costs for HF detection.

Conclusions:

• AI offers a promising solution to overcome challenges in large-scale HF screening.
• AI-powered tools can empower non-experts in cardiac assessment, expanding screening reach.
• Implementing AI in community settings can optimize heart failure prevention strategies.