A Review Paper on: Heart Disease Prediction Using ML and IoT

Abstract

This project delivers an end-to-end system for early cardiac-risk screening by fusing IoT vitals monitoring with machine-learning inference. Wearable/bedside sensors capture ECG, heart rate, SpO₂, and body temperature, stream them to a cloud backend (Firebase Realtime Database), and run continuous analytics to detect anomalies. A trained ML model classifies current risk as Low, Medium, or High, enabling rapid triage instead of delayed, manual interpretation. A unified web and Android (Java/XML) dashboard provides live plots, historical trends, and automated alerts to patients and clinicians when thresholds are crossed. By shifting from episodic checks to real-time, data-driven surveillance, the system strengthens preventive care, prompts timely intervention, and helps lower the probability of severe cardiac events.