CLEVELAND: New Cleveland Clinic-led research has shown that a bundled system of technology-driven interventions – leveraging artificial intelligence (AI) to deliver personalized health insights and lifestyle recommendations – can improve glycemic control in adults with Type 2 diabetes.
Findings published today in the New England Journal of Medicine Catalyst showed that 71% of study participants using the bundled intervention system met the primary endpoint of achieving an A1C of 6.5% with fewer medications. Kevin M. Pantalone, D.O., Director of Diabetes Initiatives at Cleveland Clinic and a professor of medicine at Cleveland Clinic Lerner College of Medicine, served as the primary investigator for this study.
Developed by Twin Health, the bundled intervention system (called Twin Precision Treatment) monitors real-time health metrics collected from a patient’s wearable sensors and Bluetooth-connected devices and includes human telecoaching. The system continuously tracks real-time health metrics – such as blood glucose levels, weight, blood pressure, physical activity and sleep – using data from wearable sensors and Bluetooth-connected devices (including a continuous glucose monitor). Through a smartphone app interface, these insights provide highly tailored nutrition and exercise guidance, in real-time, encouraging patients to make sustainable health improvements. The specific app-generated dietary recommendations were based on AI-enabled predictions of each patient’s blood glucose responses to specific meals.
For the clinical trial, Dr. Pantalone collaborated with a team of 13 Cleveland Clinic primary care physicians to recruit 150 patients – 100 were assigned to the bundled intervention group and 50 to the standard of care group. On average, patients were 58.5 years old, had been living with Type 2 diabetes for about nine years, and presented with a mean body mass index (BMI) of 35.1 and an average A1C level of 7.2%. The study authors set out to explore whether this bundled intervention system could help individuals with Type 2 diabetes, treated in a primary care setting, reach their blood sugar goals – while also reducing their need for glucose-lowering medications.
“In routine clinical practice, Type 2 diabetes is often treated with a one-size-fits-all approach where individuals are prescribed medications and told to ‘watch their diet and stay active,’” said Dr. Pantalone. “By leveraging personalized lifestyle modifications to understand each patient’s unique metabolic profile, the tool enabled individuals to make impactful lifestyle choices. The results show that with the right tools, we can not only manage Type 2 diabetes more effectively but also reduce dependence on glucose-lowering medications.”
All study participants were prescribed Metformin, a common diabetes medication, with dosages adjusted as needed throughout the study. The primary endpoint was to see how many participants reached an A1C below 6.5% after 12 months without needing any glucose-lowering medications except for metformin.
Results from the 71% of participants enrolled in the bundled intervention group lowered their A1C levels below the 6.5% threshold – while taking only metformin. By comparison, only 2.4% of participants receiving standard care achieved the same result.
Participants in the bundled intervention group also lost more weight (8.6% vs. 4.6%) while significantly reducing their reliance on glucose-lowering medications:
- GLP-1 Receptor Agonist medication use decreased from 41% to 6% among participants
- SGLT-2 Inhibitor use decreased from 27% to 1% of participants
- Dipeptidyl peptidase-4 (DPP-4) inhibitor use decreased from 33% to 3% in participants
- Insulin: Insulin use decreased from 24% to 13% among participants
The quality-of-life scores and treatment satisfaction were notably better for those using the intervention, highlighting its potential as a highly effective and sustainable option for diabetes management.
According to the Centers for Disease Control and Prevention, nearly 1 in 10 Americans have diabetes, and approximately 90% of these cases are Type 2 diabetes. The longer a person lives with the disease and has persistently high blood sugar levels, the greater the risk of serious complications, including heart disease, kidney disease, stroke and death.
“Overall, our study demonstrated the AI-enabled, bundled system of sensors and coaching facilitated significant improvements in glycemic control, weight loss, and quality of life versus usual care, while allowing marked de-escalation of glucose-lowering pharmacotherapy. Interventions like this system can help patients make informed, lasting lifestyle changes to control their blood sugar,” said Dr. Pantalone.
The study also highlights the critical role of primary care physicians in driving clinical research and patient outcomes.
“The trusted relationships between primary care physicians and their patients were instrumental in identifying, engaging and enrolling participants,” Dr. Pantalone added. “This collaboration underscores the importance of clinical research beginning in the exam room, where meaningful conversations and change can take root.”