Rajesh Mohanty, OP
Rourkela: At a time when effective management of diabetes has become a major challenge, a team of researchers at National Institute of Technology Rourkela (NITR) has developed an artificial intelligence (AI) model that significantly enhances the accuracy of blood glucose level prediction, helping individuals and healthcare providers make better and personalised treatment decisions.
The team led by assistant professor of Biotechnology and Medical Engineering at NITR Mirza Khalid Baig focused on improving glucose forecasting using deep learning techniques.
According to reports, use of AI offers a way to improve diabetes care and reduce costs. However, these models, especially predictive AI models, have their own drawbacks as their predictions are difficult to comprehend. Furthermore, traditional models, such as statistical methods or basic neural networks, often fail to recognise long-term glucose fluctuations and require complex fine-tuning.
The researchers have incorporated a specialised AI model that learns from past blood sugar trends and predicts future levels more accurately than existing methods. This model processes glucose data automatically, identifying key patterns and making precise predictions.
Also Read: Berhampur University VC duped of Rs14 lakh
Baig said, “Our core innovation allows the model to focus on the most relevant data points while ignoring unnecessary noise. 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.”
The model developed by NIT Rourkela outperformed existing forecasting techniques by providing more reliable blood sugar predictions which in turn helps make timely and personalised adjustments to future insulin doses, meals, and physical activity, he said. Moreover, the model is optimised to work efficiently on devices like smartphones and insulin pumps, making it more accessible for everyday diabetes management.
Currently, the researchers are planning on testing the technology through extensive clinical trials at hospitals, in collaboration with senior diabetologists in Odisha such as Jayanta Kumar Panda and his team.
Co-authored by Baig and his research scholar Deepjyoti Kalita, the findings of this study have been published in the IEEE Journal of Biomedical and Health Informatics.
With a number of diabetes cases expected to reach 124.9 million by 2045, its effective management has remained a daunting task. Controlling blood sugar levels requires regular glucose monitoring to prevent dangerous spikes (hyperglycemia) and drops (hypoglycemia) in blood sugar levels.
PNN