IoT-Enabled Heart Disease Prediction: Harnessing Machine Learning for Proactive Healthcare

Advancement of IoT (Internet of Things) technology presents promising opportunities in healthcare, particularly in addressing the challenges of early detection and prognosis of Cardiovascular Diseases (CVD). This research findings introduce a new strategy which integrates sensors, machine learning algorithms, and IoT technologies to enhance diagnostic capabilities and prognostic accuracy. Leveraging temperature, pulse, and ECG sensors, alongside ML techniques, patient data is gathered and kept in the Thing Speak platform. The ECG sensor observes cardiac electrical activity, while the pulse sensor measures heart rate, offering crucial information about cardiovascular well-being. Machine learning models, trained on the UCI Repository dataset, encompassing various algorithms like LR (logistic regression), RF (random forests), KNN (K Nearest Neighbors), and SVM (Support Vector Machines), DT (Decision Tree used to distinguish symptoms indicative of cardiovascular diseases. Performance measures such as F-score, precision, recall, and accuracy evaluate the efficacy of these classifiers. By enabling early detection and prognostication, this comprehensive approach aims to facilitate timely intervention and ultimately enhance patient outcomes in cardiovascular health care.