Artificial intelligence-based screening for cardiomyopathy in an obstetric population: A pilot study.

Area of Science:

• Cardiology
• Maternal-Fetal Medicine
• Artificial Intelligence in Healthcare

Background:

• Cardiomyopathy is a significant cause of pregnancy-related mortality and a leading cause of death in the postpartum period.
• Delayed diagnosis of cardiomyopathy in obstetric patients is linked to severe adverse outcomes.

Purpose of the Study:

• To assess the diagnostic performance of an artificial intelligence-enhanced electrocardiogram (AI-ECG) and an AI-enabled digital stethoscope for detecting left ventricular systolic dysfunction in obstetric patients.
• To evaluate the effectiveness of AI-powered tools in identifying cardiac dysfunction during pregnancy and postpartum.

Main Methods:

• A prospective, single-arm study involving 100 pregnant and postpartum women.
• Participants underwent standard 12-lead ECG, AI-ECG, digital stethoscope ECG and phonocardiogram recordings, and transthoracic echocardiogram within 24 hours.
• Diagnostic performance was quantified using the area under the curve (AUC).

Main Results:

• The AI-ECG model demonstrated near-perfect classification performance (AUC: 1.0) for detecting cardiomyopathy.
• The AI-enabled digital stethoscope showed high performance (AUC: 0.98 and 0.97) for detecting left ventricular dysfunction.
• Both AI tools achieved 100% sensitivity in identifying cardiac dysfunction.

Conclusions:

• AI-ECG and AI-enabled digital stethoscopes are effective in detecting cardiac dysfunction in the obstetric population.
• These AI technologies show potential for early identification of cardiomyopathy in pregnant and postpartum women.
• Further research, including studies on clinical outcome impact, is warranted.