AI, Diabetes Experts Combine Forces for Blood Sugar Management Study

To help the estimated 1.45 million Americans living with type 1 diabetes better manage their blood sugar levels, Oregon Health & Science University is combining the power of an artificial intelligence-driven smartphone app with the support of human experts.

The Leona M. and Harry B. Helmsley Charitable Trust has awarded OHSU more than $4.3 million to support this work. Leading the project are OHSU biomedical engineer Peter G. Jacobs, Ph.D., and OHSU endocrinologist Leah M. Wilson, M.D., who are organizing a randomized clinical trial to evaluate the impact of using their enhanced app in concert with diabetes education specialists.

People with type 1 diabetes cannot regulate their own blood sugar levels, and so they must take the drug insulin throughout the day. Diabetes that isn't controlled well can lead to serious complications, such as heart and kidney disease, nerve damage, vision and hearing loss, coma or even death.

To help those who manage type 1 diabetes by giving themselves insulin injections several times a day, Jacobs, Wilson and colleagues developed the DailyDose app, which uses an artificial intelligence, or AI, algorithm to evaluate blood sugar data, identify concerning trends and recommend steps to help patients keep their glucose levels within a healthy range.

During the last decade, federal approval of smaller, wearable technologies like continuous glucose monitors and automated insulin delivery systems have made type 1 diabetes management easier. But insulin delivery devices - which can cost thousands of dollars, depending on the model and insurance coverage - are out of financial reach for many patients. And while the number of diabetes apps have grown dramatically in recent years, none offer recommendations on how to modify insulin doses or behaviors like DailyDose.

Jacobs, Wilson and others published a 2020 study that showed their app’s recommendations largely matched those of physicians who specialize in diabetes care. In November 2022, the team published a follow-up study that found blood sugar levels significantly improved when people followed the app's recommendations, but those who followed the app’s recommendations less often didn’t have similar benefits.

"Our recent study found that some people didn't accept the recommended changes provided by the app because they didn't understand how the recommendations would improve their glucose management, or because they mistakenly thought that making the recommended changes would negatively impact their health," said Jacobs, an associate professor in the Department of Biomedical Engineering, OHSU School of Medicine.

"We also found that other barriers prevented some people from making changes to their glucose management," Jacobs added. "For example, if you're under a lot of stress or if you work multiple jobs, managing your glucose and taking the time to do something new can seem overwhelming or even impossible."

To nudge more people toward acting on the app's recommendations, the research team is taking a two-pronged approach: first, they're updating the app so it uses new glucose forecasting algorithms and an improved user interface, which should make its recommendations more transparent and easier to understand; and, second, the app will connect those who aren't able to improve their glucose control using the app alone with a diabetes educator or behavioral health clinician to help them overcome challenges that prevent them from making changes.

The clinical trial will first have participants use the DailyDose app, and only have them also receive coaching from a diabetes educator if necessary, because, while effective, one-on-one education can be costly and time-consuming. Researchers designed the approach to be affordable and scalable.

The multicenter clinical trial will follow a total of 93 people with type 1 diabetes for 38 weeks. After the first 12 weeks, study participants who do not benefit from using the app alone will also be connected with a diabetes educator or a psychologist. The OHSU team is also developing an online coaching platform that is designed to work with DailyDose to further help the diabetes educators and psychologists support the study participants.

"Some people struggling with glucose management may benefit from personalized coaching," said Wilson, an assistant professor in the Department of Medicine, Division of Endocrinology, Diabetes and Clinical Nutrition, OHSU School of Medicine. "But, knowing that coaching is resource-intensive, our study will only offer it to those who need it. We call this combined approach app-based certified diabetes education therapy, or AB-CDE."

The study will enroll participants beginning in 2024 through six institutions: Harold Schnitzer Diabetes Health Centerat OHSU, Joslin Diabetes Center at Harvard University, University of Southern California, University of California San Diego, Mount Sinai Hospital and Barbara Davis Center for Diabetes at the University of Colorado.

Castle JR, Wilson LM, Tyler NS, Espinoza AZ, Mosquera-Lopez CM, Kushner T, Young GM, Pinsonault J, Dodier RH, Hilts WW, Oganessian SM, Branigan DL, Gabo VB, Eom JH, Ramsey K, Youssef JE, Cafazzo JA, Winters-Stone K, Jacobs PG.
Assessment of a Decision Support System for Adults with Type 1 Diabetes on Multiple Daily Insulin Injections.
Diabetes Technol Ther. 2022 Dec;24(12):892-897. doi: 10.1089/dia.2022.0252

Most Popular Now

Philips Foundation 2024 Annual Report: E…

Marking its tenth anniversary, Philips Foundation released its 2024 Annual Report, highlighting a year in which the Philips Foundation helped provide access to quality healthcare for 46.5 million people around...

New AI Transforms Radiology with Speed, …

A first-of-its-kind generative AI system, developed in-house at Northwestern Medicine, is revolutionizing radiology - boosting productivity, identifying life-threatening conditions in milliseconds and offering a breakthrough solution to the global radiologist...

Scientists Argue for More FDA Oversight …

An agile, transparent, and ethics-driven oversight system is needed for the U.S. Food and Drug Administration (FDA) to balance innovation with patient safety when it comes to artificial intelligence-driven medical...

New Research Finds Specific Learning Str…

If data used to train artificial intelligence models for medical applications, such as hospitals across the Greater Toronto Area, differs from the real-world data, it could lead to patient harm...

Giving Doctors an AI-Powered Head Start …

Detection of melanoma and a range of other skin diseases will be faster and more accurate with a new artificial intelligence (AI) powered tool that analyses multiple imaging types simultaneously...

AI Agents for Oncology

Clinical decision-making in oncology is challenging and requires the analysis of various data types - from medical imaging and genetic information to patient records and treatment guidelines. To effectively support...

Patients say "Yes..ish" to the…

As artificial intelligence (AI) continues to be integrated in healthcare, a new multinational study involving Aarhus University sheds light on how dental patients really feel about its growing role in...

'AI Scientist' Suggests Combin…

An 'AI scientist', working in collaboration with human scientists, has found that combinations of cheap and safe drugs - used to treat conditions such as high cholesterol and alcohol dependence...

Brains vs. Bytes: Study Compares Diagnos…

A University of Maine study compared how well artificial intelligence (AI) models and human clinicians handled complex or sensitive medical cases. The study published in the Journal of Health Organization...

Start-ups in the Spotlight at MEDICA 202…

17 - 20 November 2025, Düsseldorf, Germany. MEDICA, the leading international trade fair and platform for healthcare innovations, will once again confirm its position as the world's number one hotspot for...