Bit-Heart: Wearable Device for Healthcare Diagnosis Employing IOT and Machine Learning

In this rapidly changing world, timely and cost-effective medical diagnosis is of utmost importance. This article introduces BitHeart, an IoT-based wearable device that tracks health events over time by combining wearable technology with machine learning models. This study proposes two models: first Heart Health Model which is employing IoT sensors such as heart rate monitors, accelerometers, etc. and the K Nearest Neighbor (KNN) method to predict the probability of heart disease based on physical measurements, include heartbeat rate, step count, and calories burned. Another is the body fitness model driven by a classifier called Gradient Boosting Classifier (LightGBM) is used in the evaluation of the patient by examining parameters such as step count, number of thoughts, weight and sleep duration. The hybrid technology processes the data to eliminate uncertainty and increase accuracy. The web-based interface allows users to view health data in real time and gain insights. Experimental studies have shown that the heart health model has 77% accuracy, while the physical health model can classify functional levels with high confidence. These results demonstrate BitHeart’s potential to improve personalized healthcare by providing users with early disease detection and recommendations.