IoT-Based Remote Patient Health Monitoring System Using Raspberry Pi and Machine Learning

Abstract

This paper presents an IoT-based remote patient health monitoring system designed using Raspberry Pi 4 Model B. The system integrates MAX30100 (pulse oximeter and heart rate), AD8232 (ECG), and DHT11 (temperature and humidity) sensors to collect vital signs. A 16x2 LCD display is used for real-time visualization. Data is uploaded to ThingSpeak for cloud monitoring, while alerts are triggered using Twilio (SMS) and Mailgun (email). A Random Forest machine learning model is implemented in Python to detect anomalies in patient vitals, enabling early alerts. The project demonstrates a low-cost, scalable, and intelligent remote healthcare solution.

Introduction

This project focuses on building a real-time, non-contact health monitoring system using IoT and embedded systems, designed to support home-based care. It measures vital signs and alerts caregivers in case of anomalies.

System Overview:

• Controller: Raspberry Pi 4 Model B

• Sensors:

  • MAX30100 – Measures heart rate and SpO?

  • AD8232 – Captures ECG signals

  • DHT11 – Monitors temperature and humidity

• Display: 16x2 LCD shows live readings

• Connectivity:

  • Wi-Fi (ThingSpeak): Sends data for cloud-based real-time plotting

  • Twilio & Mailgun: Trigger SMS and email alerts during health anomalies

Machine Learning Integration:

• A Random Forest model is trained on labeled vital sign data.

• It detects abnormal patterns (e.g., irregular ECG or low oxygen).

• Anomalies prompt automatic alerts to caregivers.

Results:

• The system demonstrated accurate anomaly detection

• Real-time updates were visualized on ThingSpeak

• Alerts were successfully delivered via SMS and email

Conclusion

The proposed system effectively integrates IoT and machine learning for smart patient monitoring. Future work includes integrating more sensors, improving model accuracy, and developing a mobile app for caregivers.

References

[1] MAX30100 Pulse Oximeter Datasheet [2] AD8232 ECG Sensor Datasheet [3] DHT11 Temperature Sensor Datasheet [4] ThingSpeak API Documentation [5] Twilio SMS API Guide [6] Scikit-learn: Random Forest Classifier

Copyright

Copyright © 2025 Buvaneshwari S. 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.