Scientists Perfecting App That Predicts Glucose Levels

A new app developed by Columbia University researchers may help people with type 2 diabetes make healthier meal choices. The app, called Glucoracle, uses a personalized algorithm to anticipate the influence of particular foods on glucose levels.

Although it’s generally understood how different foods affect blood sugar, specific effects vary not only from one individual to another, but for each individual over time.

“Even with expert guidance, it's difficult for people to understand the true impact of their dietary choices, particularly on a meal-to-meal basis,” said lead author David Albers, PhD, associate research scientist at Columbia University Medical Center. “Our algorithm, integrated into an easy-to-use app, predicts the consequences of eating a specific meal before the food is eaten, allowing individuals to make better nutritional choices during mealtime.”

The app’s algorithm uses a technique called data assimilation. This technique constantly updates the mathematical model of a person’s glucose response. Users upload photos of their meals, nutritional estimates, and their glucose monitor’s readouts to the app. As the data are assimilated, the algorithm learns how each user responds to different foods.

Initially, Glucoracle was tested on three people with type 2 diabetes, plus two non-diabetic individuals. The app’s predictions were compared to those made by diabetes educators, and to actual post-meal blood sugar measurements.

The app’s forecasts for the non-diabetic subjects were commensurate with their glucose measurements. With the diabetes participants, Glucoracle was slightly less accurate than their glucose measurements, but comparable to the diabetes educators’ predictions.

“There's certainly room for improvement,” said Dr. Albers. “This evaluation was designed to prove that it's possible, using routine self-monitoring data, to generate real-time glucose forecasts that people could use to make better nutritional choices. We have been able to make an aspect of diabetes self-management that has been nearly impossible for people with type 2 diabetes more manageable. Now, our task is to make the data assimilation tool powering the app even better.”

The researchers are planning larger clinical trials, and anticipate the app will be ready for use within a couple years.

Source: Columbia University Medical Center Newsroom
Photo credit: Costculator