A smart Healthcare System: Reducing False Predictions of Chronic Diseases Using IoT and Machine Learning

The book "Smart Healthcare Systems: Reducing False Predictions of Chronic Diseases Using IoT and Machine Learning" presents an innovative, cost-effective IoT-based Ambulatory Blood Pressure Monitoring (IABPM) system aimed at real-time tracking and early detection of Chronic Heart Disease (CHD). It leverages wearable sensors and cloud integration to record blood pressure and pulse data throughout the day, enhancing patient mobility and care. The system applies ML algorithms like Naïve Bayes, KNN, Decision Tree, SVM, and XGBoost to clinical datasets (SMHRCE and Kaggle) to predict Early Warning Scores (EWS). The proposed model shows high accuracy (up to 99.85%) and helps reduce healthcare costs, support proactive intervention, and improve diagnostic precision. The project bridges gaps in traditional ABPM systems by offering continuous monitoring, automated alerts, and cloud accessibility—paving the way for improved chronic disease management through technology integration.