Artificial Intelligence-Augmented Clinical Decision Support Systems for Pregnancy Care: Systematic Review

Area of Science:

• Obstetrics and Gynecology
• Medical Informatics
• Artificial Intelligence

Background:

• Clinical decision support systems (CDSS) are increasingly used in pregnancy care.
• The role of artificial intelligence (AI) in pregnancy-specific CDSS remains understudied.
• This review addresses the gap in understanding AI's integration into CDSS for maternal health.

Approach:

• A systematic review of empirical studies examining AI-augmented CDSS in pregnancy care was conducted.
• Studies were retrieved from PubMed/MEDLINE, Embase, and ACM Digital Library (inception to 2022).
• Eligibility criteria focused on empirical studies developing or testing AI methods, CDSS, or components within pregnancy care.

Key Points:

• 30 distinct studies were identified from 684 initial records.
• AI-augmented CDSS applications span prenatal, early pregnancy, obstetric, and postpartum care.
• CDSS functionalities include diagnostic support, clinical prediction, therapeutics recommendation, and knowledge base development.

Conclusions:

• Recent advances include early diagnosis of prenatal abnormalities and improved prenatal ultrasound support.
• Key gaps exist in decision support for childbirth using observational data, identifying biases (e.g., social determinants of health), and bridging the gap between model validation and clinical implementation.
• Future research should address these limitations to enhance AI-driven CDSS in pregnancy care.