In recent years, heat-related illnesses have become a significant public health concern, particularly during periods of hot weather. The alarming increase in heat-related cases calls for effective measures to mitigate the risks associated with heat stress. This study presents the development of a predictive model using machine learning techniques to analyze heat stress patterns. The detection tool comprises of Arduino Nano 33 BLE Sense, equipped with a heartrate sensor, a skin temperature sensor, and an environment temperature and humidity sensor. These sensors provide real-time data on physiological parameters and environmental conditions, enabling the tool to accurately assess heat stress levels. The machine learning algorithms employed in the predictive model analyze the collected data to identify patterns and correlations between physiological responses and heat stress. The tool aims to support public health authorities in implementing proactive interventions to prevent heat stress. By providing timely and accurate information on heat stress patterns, this tool enables the identification of high-risk areas and populations, allowing for targeted interventions, public awareness campaigns, and resource allocation.
