Can AI Improve Cardiomyopathy Detection in Pregnant Women?

Cardiomyopathy during pregnancy and postpartum is challenging to diagnose due to symptom overlap with normal pregnancy changes. AI-guided screening showed a significant improvement in diagnosis rates compared with usual care.

METHODOLOGY:

• Researchers conducted an open-label, randomized clinical trial involving 1232 pregnant and postpartum women in Nigeria.
• Participants were randomized to either AI-guided screening using digital stethoscopes and 12-lead ECGs or usual care.
• The primary outcome was the identification of LVSD confirmed by echocardiography.
• Secondary outcomes were AI model performance across subgroups and the effectiveness of AI in identifying various levels of LVSD.

TAKEAWAY:

• AI-guided screening using digital stethoscopes detected LVSD in 4.1% of participants compared with 2.0% of controls (P = .032).
• The 12-lead AI-ECG model detected LVSD in 3.4% of participants in the intervention arm compared with 2.0% of those in the control arm (P = .125).
• No serious adverse events related to study participation were reported.
• The study highlighted the potential of AI-guided screening to improve the diagnosis of pregnancy-related cardiomyopathy.

 

https://www.medscape.com/viewarticle/can-ai-improve-cardiomyopathy-detection-pregnant-women-2024a1000gl4