The Use of Machine Learning and Internet of Things Technologies in Maternal Healthcare: A Systematic Review

Abstract

Background and Purpose: There has been an increase in the use of the Internet of Things (IoT) and machine learning (ML) technologies in maternal healthcare recently. These technologies have aided in the design of wearable medical devices that can remotely monitor pregnant women and provide early warning on impending pregnancy complications. This would necessitate appropriate care to be provided in good time to improve the health status of pregnant women. This review attempts to understand the current trends and gaps in the use of integrated technologies of IoT and machine learning in maternal healthcare with the view of providing recommendations on the design of suitable models that can improve personalized maternal care.

Methods: We adopted the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines for systematic reviews to analyze 50 articles published between 2017 and 2024 covering the use of IoT and ML in maternal healthcare.

Results: We established that there is a need for further studies to guide the design of IoT and ML frameworks that could be used to capture both fetal and maternal vitals and transmit the captured data directly to the cloud without using an intermediary like a smartphone. Furthermore, the use of tinyML technology that allows on-device sensor data analytics in real-time monitoring requires further consideration in maternal healthcare applications.

Conclusions: This review utilized PRISMA guidelines to analyze the trends in the use of the integrated technologies of ML and IoT in maternal healthcare. The evaluation highlighted the existing gaps in the design of the devices for continuous monitoring of maternal and fetal vitals and predicting pregnancy complications. The review provides recommendations for further research work in the design of these intelligent devices.