Diabetes is a costly and dangerous disease that ranks among the top five chronic diseases in the U.S., so it’s not surprising that an increasing number of AI stakeholders are focusing their efforts on helping patients and providers grapple with it.
For example, Yes Health, a tech start-up that focuses on promoting healthy lifestyles through better nutrition, fitness and well-being support, recently partnered with Gympass, a corporate wellness benefits platform, to provide Gympass clients with “an all-mobile diabetes prevention program . . . with in-the-moment coaching that combines automation, AI and human support.”
"As fitness platforms rethink their business models, there is an opportunity to add, in a low-cost fashion and without much overhead, nutrition programs and well-being programs for holistic chronic disease prevention,” said Alexander Petrov, founder and CEO of Yes Health, in an interview. “This partnership is a symbol of that. We have a chronic disease prevention tech company and a fitness platform going beyond traditional boundaries to collaborate and I hope that is a starting point for others.”
The California-based company delivers personalized therapy for members directly to their smartphones to enhance human health coaching.
"Members want feedback and advice when they are making a nutrition or fitness decision, not after the fact," Petrov said. "Providing coaches in the moment delivers faster adoption and more sustainable lifestyle change.”
According to Petrov, recent studies have shown that most U.S. employers now are willing to provide their workforce with digital tools that can improve health.
“By adding Yes Health to the Gympass network, members now have a single place on their mobile devices where they can go for quick, easy-to-use and personalized care plans that includes diabetes prevention, nutrition counseling, fitness coaching, sleep, wellbeing support and much more," he said.
Meanwhile, on the research side of the diabetes battle, researchers have developed an advanced AI algorithm that predicts the onset of type 2 diabetes using routinely collected health administrative data.
In a report published at JAMA Network Open, the researchers said “the main purpose of our model was to inform population health planning and management for the prevention of diabetes that incorporates health equity. It was not our goal for this model to be applied in the context of individual patient care. . . . We created our model with the intention that it could be used on data that are routinely collected by governments or health insurance systems, thereby offering efficient, population-level applicability while maintaining robust performance.”
The team’s algorithm was trained with data from more than 1.6 million patients, validating with data from more than 243,000 patients and tested with data from more than 236,000 patients. The two-year medical histories of each patient—including their demographic information, prescription medication history and any lab results—were all used to fine-tune the algorithm.
“Because our machine learning model included social determinants of health that are known to contribute to diabetes risk, our population-wide approach to risk assessment may represent a tool for addressing health disparities,” the researchers wrote.
Photo by monsitj/Getty Images