Machine-Learning Model to Predict Core Body Temperature with Real-Time Monitoring

 

2025-061
Representative image for Machine-Learning Model to Predict Core Body Temperature with Real-Time Monitoring
   
Technology Overview

Dr. Rupak Banerjee, a professor in the Department of Biomedical Engineering at the University of Cincinnati, and his team have developed an effective machine learning model that precisely predicts core body temperature in real-time. This surrogate model is trained using physics-based simulations that account for a wide range of physiological and external parameters. Unlike traditional models, this system adapts seamlessly to diverse worker profiles and operational environments, enhancing its utility across industries. This innovation opens the door for workers to use wearable, non-invasive health monitoring tools that can help manage thermal stress and improve safety in extreme environments.

Background

Nearly half of all frontline workers, such as firefighters, construction crews, and utility personnel, perform their jobs in outdoor environments where they face extreme heat or cold conditions. Exposure to extreme hot and cold temperature environments has caused many workers discomfort and illness from the exertion of thermal stresses on the body. Current methods for measuring core body temperature are either invasive, expensive, or less reliable, as the data algorithms used in existing models do not account for all worker types.

Advantages and Benefits
  • Non-invasive
  • Scalable for various environments
  • Cost-effective
  • Precise and accurate
  • Versatile applications across industries
  •  
Patents
Serial No. File Date Patent No. Issued Date
Other Media
Inventor(s)
  • Rupak Banerjee
  • Sai Vejendla
  • Israel Ajiboye
Contact
Patrick Brown
Director, Commercialization
Lead Inventor