Smart Maternal and Child Health Monitoring System Using IoT and Machine Learning

Authors: Sunitha Tappari, Aare Medha Sree, B. Rakshitha, N. Sreshta, A. Hinduja Reddy

DOI Link: https://doi.org/10.22214/ijraset.2026.79168

Abstract

Pregnancy is a critical period, and the timely detection of physiological changes helps in the early prevention of complications. Wearable sensors measure essential parameters like heart rate, temperature, and SpO?, transmitting the data to the ThingSpeak cloud via Wi-Fi. It is analysed for the differentiation of normal and abnormal conditions via a Random Forest algorithm, which generates alerts in case of deviations. This allows for early intervention, reducing risks and enhancing maternal safety. It is low cost, compact, and user-friendly, thus allowing home-based monitoring without repeated visits to the hospital. It supports real-time visualization, record storage, and remote sharing of data with healthcare providers through cloud integration. Prototype testing confirms correct sensor readings and reliable ML predictions.

Introduction

The proposed Smart Maternal and Child Health Monitoring System integrates Internet of Things (IoT) and Machine Learning (ML) to enable continuous monitoring of pregnant women, particularly in rural and remote areas where healthcare access is limited. The system uses sensors to measure vital physiological parameters such as heart rate, body temperature, blood oxygen (SpO?), galvanic skin response (GSR), and fetal movement. These readings are collected through an Arduino-based microcontroller, transmitted to a cloud platform, and analyzed using a Long Short-Term Memory (LSTM) deep learning model to predict health risks. Based on the analysis, the system classifies maternal health into low, moderate, or high-risk categories and generates real-time alerts through a buzzer and remote notifications when abnormal conditions are detected. Experimental evaluation using performance metrics such as accuracy, precision, F1-score, confusion matrix, and accuracy-loss graphs demonstrated effective risk prediction and reliable monitoring. By combining IoT, cloud computing, and intelligent data analysis, the proposed system offers a cost-effective, real-time, and scalable solution that supports early detection of pregnancy complications, improves maternal and fetal safety, and enhances healthcare accessibility in underserved regions.

Conclusion

The suggested health monitoring system is a successful strategy of constant monitoring and forecast of health risks based on the combination of sensor technology, Internet of Things (IoT) communication, and machine learning methods. The system will be programmed to measure vital physiological values like the temperature, pulse rate, galvanic skin response (GSR), blood oxygen saturation (SpO2), and fetal movement by measuring sensor modules which will be attached to a microcontroller. These parameters are important indicators of the health condition of a person and are useful in monitoring and analysis. The microcontroller processes the gathered physiological data and sends it to a cloud platform where health information and remote monitoring can be monitored and stored. The cloud connectivity will enable healthcare providers and caretakers to get the data anywhere, which will be a guarantee of the uninterrupted observation of the health status of the person using it. This ability to monitor remotely enhances accessibility and assists in offering timely medical care in case abnormal conditions are realized. The obtained results of the experimental assessment prove that the proposed system can be used to monitor physiological parameters effectively and predict the risk of health issues with a high degree of accuracy. However, by combining IoT technology with machine learning algorithms, the system will be able to analyze health data in real time and offer credible risk classification. The system also considers a warning mechanism which alerts the user or caregiver in case of abnormal conditions by providing a quick response to any emergencies in relation to health conditions. In general, the suggested health monitoring system offers a valid and effective solution of real-time health monitoring and predictive healthcare. The system will help enhance the healthcare management and enable the prompt detection of the health risks by integrating sensor-based monitoring with cloud communication and intelligent data analysis. The deployment of this type of systems may be of great value in improving the monitoring of patients and the ability to come up with smarter healthcare solutions.

References

[1] M. Ahmed and M. A. Kashem, \"IoT Based Risk Level Prediction Model for Maternal Health Care in the Context of Bangladesh,\" Proc. IEEE Symposium on Technology, 2020, i:10.1109/STI50764.2020.9350320. [2] Ammireddy Supraja, Aravapalli Divya Vasavi & K. V. Karthikeyan, “Pregnant Women Health Monitoring System,” 2023. [3] Mohammed Elkahlout et al., “IoT-Based Healthcare and Monitoring Systems for the Elderly: A Literature Survey Study,” 2020. [4] Jigna Hathaliya et al., “Blockchain-Based Remote Patient Monitoring in Healthcare 4.0,” 2019. [5] Paritosh Mittal et al., “Propositions for Smart Healthcare Systems,” 2022. [6] Sandesh Warbhe & Swapnili Karmore, “Wearable Healthcare Monitoring System: A Survey,” 2022. [7] Abdiakhmetova et al., “Intelligent Monitoring System Based on Atmega Microcontrollers in Healthcare with Stress Reduce Effect,” 2024. [8] Delsi Robinsha S. & Amutha B., “IoT Revolutionizing Healthcare: A Survey of Smart Healthcare System Architectures,” 2023. [9] Islam et al., “A Mobile Health (mHealth) Technology for Maternal Depression and Stress Assessment and Intervention during Pregnancy,” 2022. [10] Batani et al., “A Deep Learning-Based Chatbot to Enhance Maternal Health Education.” [11] B. Godi et al., \"E Healthcare Monitoring System Using IoT with Machine Learning Approaches,\" Proc. IEEE ICCSEA, 2020, doi:10.1109/ICCSEA49143.2020.9132937. [12] R. Ettiyan and V. Geetha, \"A Survey of Healthcare Monitoring System for Maternity Women Using Internet of Things,\" Proc. IEEE ICISS, 2020, doi:10.1109/ICISS49785.2020.9315950. [13] R. K. Megalingam et al., \"Assistive Technology for Pregnant Women Healthcare in Rural Areas,\" IEEE GHTC-SAS, 2013, doi:10.1109/GHTC-SAS.2013.6629909. [14] B. Priyanka et al., “IoT Based Pregnancy Women Health Monitoring System for Prenatal Care,” 2021, doi:10.1109/ICACCS51430.2021.9441677. [15] Suman Kumar, Yashi Gupta, and Vijay Mago, “Health Monitoring of Pregnant Women: Design Requirements and Proposed Reference Architecture,” 2019, doi:10.1109/CCNC.2019.8651768. [16] Xin Zhao et al., “An IoT-Based Wearable System Using Accelerometers and Machine Learning for Fetal Movement Monitoring,” 2019, doi:10.1109/ICPHYS.2019.8780301. [17] João Alexandre Lobo Marques et al., “IoT-Based Smart Health System for Ambulatory Maternal and Fetal Monitoring,” 2020, doi:10.1109/JIOT.2020.3037759. [18] Quinlivan, Julie A., Sarah Lyons, and Rodney W. Petersen, “Attitudes of Pregnant Women Towards Medical Record Systems: A Survey Study,” Telemedicine and e-Health, 2014. [19] Nazari, Mojdeh, et al., “Design and Analysis of a Telemonitoring System for High-Risk Pregnant Women,” BMC Pregnancy and Childbirth, 2024. [20] Veena, S., and D. John Aravindhar, “Remote Monitoring System for Detection of Prenatal Risk,” Wireless Personal Communications, 2021. [21] Hossain, Mohammad Mobarak, et al., “A Medical Cyber-Physical System for Predicting Maternal Health Using Machine Learning,” Healthcare Analytics, 2024. [22] K. Shankar et al., “Deep Learning-Based Smart Healthcare System for Predicting Maternal Health Risks,” IEEE Access, 2021. [23] S. Rajalakshmi and R. Mahalakshmi, “IoT-Based Smart Health Monitoring System for Pregnant Women Using Machine Learning,” International Journal of Engineering Research & Technology, 2020. [24] P. Verma and S. K. Sood, “Cloud-Centric IoT Based Student Healthcare Monitoring Framework,” Journal of Ambient Intelligence and Humanized Computing, 2018.

Copyright

Copyright © 2026 Sunitha Tappari, Aare Medha Sree, B. Rakshitha, N. Sreshta, A. Hinduja Reddy. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Download Paper

Paper Id : IJRASET79168

Publish Date : 2026-03-31

ISSN : 2321-9653

Publisher Name : IJRASET

DOI Link : Click Here