Wearable Sensors, Data Processing, and Artificial Intelligence in Pregnancy Monitoring: A Review.

Area of Science:

• Biomedical Engineering
• Digital Health
• Maternal-Fetal Medicine

Background:

• Maternal deaths remain a global concern, with traditional hospital check-ups posing burdens for pregnant women.
• Home-based, non-invasive long-term pregnancy monitoring is a critical research area.
• Advancements in wearable sensors and data processing enhance convenience in pregnancy care.

Purpose of the Study:

• To review recent research on wearable sensors, physiological data processing, and AI for pregnancy monitoring.
• To highlight the potential of AI in early detection and smart diagnosis during pregnancy.
• To propose future improvements for remote pregnancy health monitoring.

Main Methods:

• Review of literature on wearable sensors for physiological signals (ECG, UC, FM).
• Analysis of data processing techniques including transmission, pre-processing, and AI-based algorithms.
• Examination of multimodal pregnancy-monitoring systems.

Main Results:

• Wearable sensors effectively capture key physiological signals like electrocardiogram (ECG), uterine contraction (UC), and fetal movement (FM).
• Artificial intelligence (AI) demonstrates significant capabilities in early detection and smart diagnosis for pregnancy.
• Multimodal systems integrating various sensors show promise for comprehensive monitoring.

Conclusions:

• Smart wearables and AI offer remarkable potential for improving pregnancy monitoring, making it more accessible and convenient.
• Challenges such as accuracy, data privacy, and user compliance need to be addressed for widespread adoption.
• Future research should focus on enhancing these technologies for robust and reliable remote maternal and fetal health surveillance.