New Delhi, Feb 25 The National Institute of Technology (NIT) Rourkela on Tuesday said it has developed an advanced AI-driven model to improve blood sugar predictions for people with diabetes.
The model is designed to help individuals and healthcare providers make better and more personalised treatment decisions.
Unlike traditional forecasting methods, which often require manual adjustments and struggle with long-term glucose trends, this AI model automatically processes data to identify key patterns.
The model has outperformed existing techniques by offering more reliable predictions tailored to an individual’s unique glucose patterns.
Additionally, it has been optimised for use on devices like smartphones and insulin pumps, making it accessible for everyday diabetes management.
According to the research team led by Professor Mirza Khalid Baig, assistant professor of biotechnology and medical engineering, the AI-driven approach could significantly improve diabetes care.
“Our core innovation lies in using multi-head attention layers within a neural basis expansion network, which allows the model to focus on the most relevant data points while ignoring unnecessary noise,” Baig said.
He added that this results in better performance without the need for large amounts of training data or extensive computing power.
“By combining precision with efficiency, we aim to provide a practical tool that can be integrated into digital health solutions, helping patients and doctors manage diabetes more effectively,” Baig mentioned.
It has the potential to be integrated into smart insulin pumps for automated insulin delivery, mobile health apps for real-time glucose tracking, and clinical settings to assist doctors in creating personalised treatment plans.
Currently, the researchers are planning extensive clinical trials at hospitals in collaboration with senior diabetologists in Odisha.
The project has received support from the Department of Science and Technology (DST), the Department of Biotechnology (DBT), and NIT Rourkela.
Disclaimer: This post has been auto-published from an agency feed without any modifications to the text and has not been reviewed by an editor