Real-Time Liver Health Monitoring System Using Deep Learning and Wearable Sensors

Abstract

This paper presents a novel real-time liver health monitoring system integrating wearable sensors, deep learning, and cloud computing for continuous, non-invasive assessment of liver function. Utilizing a convolutional neural network (CNN), the system analyses physiological data streams from wearable devices to predict liver health status with high accuracy. The implementation leverages a scalable cloud-based architecture and a mobile application for user feedback, addressing challenges in data accuracy, latency, and privacy. Compared to traditional diagnostic methods, this system offers timely anomaly detection and enhanced accessibility. Experimental results demonstrate a classification accuracy of 92%, surpassing existing statistical models. This work provides a robust framework for preventive liver healthcare, with potential for widespread adoption.