New AI-Powered Technology Increases Accuracy of Hypoglycemia and Hyperglycemia Predictions and Introduces Alert Capability for People Using Continuous Glucose Monitors

The results of a recent study show that One Drop’s AI-powered glucose predictions are 91.9% accurate for hypoglycemia and 91.6% accurate for hyperglycemia


The digital therapeutics company One Drop today presented new results for continuous glucose monitor-based glucose predictions at The 13th International Conference on Advanced Technologies & Treatments for Diabetes in Madrid, Spain. These findings demonstrate increased accuracy of direct glucose, hypoglycemia, and hyperglycemia predictions across multiple time periods.

One Drop’s patent-pending machine learning model accurately predicts the probabilities that a user’s glucose will rise above 180 mg/dL or fall below 70 mg/dL. At 30 minutes, the predictions are 99.5% accurate, at 1 hour, 98.6% accurate, and at 4 hours, One Drop’s accuracy is 91.9%, which is higher than other published studies examining hypoglycemia prediction using continuous glucose monitor (CGM) data [1]. Sources for One Drop’s study included over 10 million hours of CGM data as well as self­-care data from a sample of over 3,000 users.

“One Drop’s breadth of data includes glucose, food, exercise, sleep, and heart rate, which allows us to surpass the accuracy of IBM Watson Health at four-hour hypoglycemia predictions,” says One Drop VP of Data Science, Dan Goldner. “For the first time, we have the capability to alert people at risk of experiencing severely high or low blood sugar. Our AI-powered alerts have the po­tential to help our millions of users worldwide exercise proactive, preventative self-care.”

The study results also indicate an increased level of accuracy for point predictions of blood glucose concentration at 30 minutes and one hour, as compared to a previous study submitted to the Diabetes Technology Society. The most substantial change occurred in the percentage of predictions with errors less than 30 mg/dL, which rose from 97.0% to 98.9% in 30-minute predictions and from 77.9% to 78.7% in one-hour predictions.

“As someone living with type 1 diabetes, I know how scary going low can be. It can literally be a matter of life or death,” says One Drop founder and CEO, Jeff Dachis. “Our increasingly accurate machine learning models take the fear and guesswork out of managing low blood sugar and prevent harmful overcorrections that often lead to hyperglycemia and increased A1C.”

One Drop provides users with AI-powered Predictive Insights and real-time advice on how to adjust their behavior (diet, physical activity, and more) for better outcomes without intervention from a health care provider. The machine learning models are trained on more than eight billion data points from three million users worldwide. Importantly, One Drop’s models do not require getting to know an individual over time. Unlike other predictive tools, One Drop’s models provide accurate predictions for one person based on the aggregate data of all people with similar health profiles. Within minutes of entering a single data point into the One Drop app, a user can receive their first prediction.


You may also like

  • Insulin Sensitivity Improves with Testosterone Therapy in Men with Type 2 Diabetes and Hypogonadism

    About a third of men with type 2 diabetes (T2D) also have hypogonadotropic hypogonadism (HH). This comorbidity makes that subgroup more insulin resistant, with increased adiposity and less lean mass, according to research published recently in The Journal of Clinical Endocrinology & Metabolism. A team led by Paresh Dandona, BSc, MB, BS, DPhil, FRCP, of…

  • Study Finds Dopamine, Biological Clock Link to Snacking, Overeating, and Obesity

    The pleasure center of the brain and the brain’s biological clock are linked, and high-calorie foods — which bring pleasure — disrupt normal feeding schedules, resulting in overconsumption, according to a study recently published in Current Biology. Researchers led by Ali Güler, PhD, a professor of biology at the University of Virginia demonstrate that the…