Enhancing Patient Monitoring System: IoT and ML Integration for Detecting Distortions in Paramedical Readings

The integration of the (IoT) with Machine Learning (ML) has revolutionized patient monitoring systems, ensuring real-time anomaly detection and timely medical intervention. This study proposes a robust framework that leverages wearable sensors and environmental data to enhance the accuracy and reliability of paramedical readings. A comprehensive data preprocessing pipeline is implemented to address missing values, noise, and outliers, improving data integrity before analysis. ML models including Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Extreme Gradient Boosting (XGBoost)-are employed to classify patient data and detect anomalies with high precision. The proposed system is evaluated using a real-world cancer treatment dataset extracted from Kaggle, consisting of 6,795 patient records covering various cancer types, treatment responses (chemotherapy, radiation, immunotherapy), tumor size, genetic markers, and vital parameters. Experimental results demonstrate superior performance in early anomaly detection, with XGBoost achieving the highest accuracy of 97.47%. Additionally, the system is designed for scalability and real-time monitoring across various healthcare environments, including hospitals and remote patient monitoring setups over a Real-Time Wide Area Network (RTWAN). The results indicate that ML-driven IoT frameworks can significantly improve patient monitoring, leading to enhanced diagnostic accuracy and better clinical decision-making