Finger ID Health Analyzer: Predicting Blood Group and ECG Analyzer

This paper presents a new multi-modal healthcare monitoring and disease prediction system that combines real-time biomedical sensor data, deep learning, and a user-focused advisory module. The system allows for continuous health monitoring and predictive diagnostics using a mix of non-invasive techniques and smart analysis. At the heart of the system is a fingerprint-based module for non-invasive blood group detection. It processes user-uploaded fingerprint images through enhancement and feature extraction before sending them to a deep learning model for accurate blood group prediction. This method avoids the need for traditional invasive testing. At the same time, an IoT-based hardware component collects vital physiological parameters. A ESP8266 NodeMCU connects with an AD8232 sensor for ECG, a MAX30102 sensor for blood oxygen saturation (SpOâ‚‚) and pulse rate, and a DS18B20 sensor for body temperature. The data is transmitted wirelessly to the ThingSpeak cloud platform for real-time visualization and ongoing monitoring. For assessing cardiovascular risk, a trained deep learning model examines user data, including age, gender, blood pressure, cholesterol, and lifestyle factors, to predict the likelihood of cardiac conditions. The platform also includes a chatbot that processes symptom inputs and offers automated health advice, such as possible cures, nearby doctor recommendations, and daily health challenges to boost user engagement. All insights and reports, including PDF generation, are available through a single web dashboard. This integrated solution provides an affordable, scalable, and effective preventive healthcare option, especially for remote and underserved communities.