Enhancing Health Risk Monitoring: An Explainable Human-Centric Approach Using Wearable Data and Sensor Integration

This paper presents the development of an Explainable AI (XAI) approach designed for first responders (FRs) to monitor and predict health risks based on real-time data from wearable devices. The tool integrates Machine Learning models to analyze vital signs, such as heart rate, respiratory rate, and skin temperature, providing predictions for conditions like exhaustion, stress levels, and respiratory issues. To ensure transparency and trustworthiness, the tool incorporates XAI techniques, including SHAP and LIME, offering clear and interpretable explanations for the model’s predictions. The main goal of this research is to introduce to the users the capabilities of integrated XAI in real-time monitoring, alert generation, and interactive visualizations, enhancing first responders’ ability to make informed decisions in high-stress environments, as well as highlighting important vitals as features to be implemented in wearable technologies. Additionally, the tool adheres to strict data privacy regulations and is designed for scalability and seamless integration with existing monitoring systems. This innovative approach, as part of this project, aims to improve the safety and efficiency of first responders by providing actionable insights and transparent explanations of health risks.