It’s hard to deny that technology advances are improving the lives of people with diabetes worldwide. From smart insulin pumps that integrate with continuous glucose monitors (CGMs) to various applications with predictive features and alarms, the diabetes tech world continues to evolve rapidly.
One company, January.ai, has recently announced its new artificial intelligence (AI) platform can accurately predict blood glucose responses to various meals. The company was founded in 2017 by Silicon Valley veteran and CEO Noosheen Hashemi and Mike Snyder, the Director of Genomics and Personalized Medicine at Stanford, with the vision of improving lives by providing comprehensive health data. The concept was recently validated, and the company has developed a user-friendly app to help people with diabetes learn more about what affects their blood glucose levels and improve outcomes.
How It Works
The new algorithm relies on machine learning approaches to predict individual blood glucose responses to different meals and activities. To achieve this, the algorithm considers the users’ heart rate, and logs of their food and medication data, developing a personalized model for each patient to predict glycemic outcomes. The initial “training” period takes four days, and does incorporate data from a CGM; however, no CGM data is needed to make the predictions past the initial training period.
As per the recent press release,
“The company developed a series of underlying technologies including derived nutritional values, glycemic index and glycemic load, which estimates how a person’s blood sugar will rise based on the food they eat, for 16 million foods. January.ai built its own mobile application to capture and unify various data points into one AI platform, collecting nearly 25 million data points for the study.”
At the American Diabetes Association (ADA) 80th Scientific Sessions, the research team presented the outcomes of this algorithm in predicting the glycemic responses of over 1,000 participants. Some were diagnosed with pre-diabetes or type 2 diabetes, while others represented healthy participants.
Participants wore a CGM as well as a heart rate monitor for ten days. They also tracked their activity levels, specific food and water intake, as well as their medication doses. Following the four-day learning period., the algorithm developed an “individualized model” for each participant. Next, the system’s ability to accurately predict blood sugar responses without using any CGM data was put to the test. Excitingly, the predictive values were in close accord with the actual CGM readings, which were used to validate the accuracy of the predictions.
Rahili S. et al. 2020 (Presented at the ADA 80th Scientific Sessions) The above slide shows the model’s glucose prediction for a 33-hour period based on a participant’s heart rate, food, and medication data, compared to their actual glucose levels.
The App
The team has applied their state-of-the-art algorithm to develop an app that enables users to track their heart rate and blood sugar levels, as well as get a comprehensive picture of how factors like specific foods and exercise patterns affect them, personally. Moreover, due to the machine learning features, patients can also be alerted to potential pitfalls before they even consume a particular meal. The app also features various data displays, related explanations, suggestions, and offers rewards for making improvements.
Image source: January.ai
Summary
The ability to accurately predict changes in blood sugar levels using just heart rate data, and food and medication logs, can offer a more affordable and non-invasive way for those with diabetes to learn about how different foods affect their blood sugar levels.
Noosheen Hashemi, Founder and CEO of January.ai had this to say about what their product could do for those living with diabetes:
“Despite extensive efforts, the healthcare community has not been able to slow the rapid rise of diabetes, nor develop effective treatments. We believe that by applying AI to a mix of biological and behavioral data, we can empower people with the personalized insights and specific recommendations they need to enjoy better health.”
What are your thoughts on this technology? Please comment below, we love hearing from our readers!
Post Views: 2