NuraLogix researchers announce AI models that can predict blood biomarker risk
TORONTO, August 30, 2022 /PRNewswire/ – Researchers from NuraLogix, a global leader in AI HealthTech, today announced that they have developed AI models capable of predicting a person’s risk of HbA1C and fasting glucose levels are above a clinically significant threshold for prediabetes. This is important because it will one day allow people to screen themselves using any device with a camera, such as a smartphone or tablet.
The researchers trained their machine learning-based models on the facial blood flow patterns of tens of thousands of subjects who had recently received a blood test for HbA1C (glycated hemoglobin) and fasting blood sugar. The models were able to predict whether a subject’s HbA1C is above 5.7% or if their fasting blood sugar is above 5.5 mmol/L. In both cases, the models predicted with AUC > 0.80. Compare this with the classic Framingham model for predicting cardiovascular disease which had an AUC of around 0.70.
“What’s important about this research is that we’ve demonstrated that we can use the technology that most people already have access to – their smartphones – to get early indications of diabetes risk,” said Dr. . Keith Thompson, primary care physician for over 30 years and chief medical officer at NuraLogix. “For people with pre-diabetes, 90% are unaware that they have this disease and of these people, 70% will develop diabetes and all its associated complications. We can consider training our models to recognize different thresholds for HbA1c and fasting Blood glucose, and after regulatory approval, could become a powerful tool for population screening and possibly even monitoring of diabetic patients using HbA1c and fasting blood glucose .”
“Our models are groundbreaking because we can now predict the likelihood of a person being above a pre-diabetes risk threshold with significant accuracy,” said Dr. Naresh Vempala, research director at NuraLogix. “It’s exciting that our machine learning-based classifiers are non-contact and have learned the relationships between facial blood flow patterns and diabetes risk. This was unimaginable and non-existent in AI until now. Potentially , our AI models can enable people to monitor their own health on a daily basis, enabling early detection and prevention.”
NuraLogix is the creator of the world’s first non-contact blood pressure measurement technology. The company’s patented technology can measure more than 30 health and wellness parameters using Transdermal Optical Imaging (TOI™), a proprietary technique developed by the company in which a conventional video camera is used to extract facial blood flow information from human face. This is demonstrated in the company’s revolutionary applications Anura™ and Anura Lite™.
Note: in United States, this product is intended for experimental use only. The performance characteristics of this product have not been established.