Leveraging Machine Learning for Personalized Medical Expense Insights

Abstract

Using connected sensors, this proposed system continuously monitors vital health parameters, including heart rate, body temperature, and SpO₂ levels. These real-time data are processed locally on the Arduino Uno, employing a Random Forest regression model to predict healthcare costs with high accuracy. By performing computations directly on the device, the system ensures enhanced data privacy, reduced latency, and operational scalability, making it suitable for diverse healthcare environments. The proposed solution is poised to improve the precision of healthcare cost predictions significantly, benefiting healthcare providers and insurance companies by facilitating more accurate and timely financial planning.