{"id":3943,"date":"2026-03-30T15:53:15","date_gmt":"2026-03-30T19:53:15","guid":{"rendered":"https:\/\/med.virginia.edu\/diabetes-technology\/?p=3943"},"modified":"2026-07-15T17:55:44","modified_gmt":"2026-07-15T21:55:44","slug":"cdt-researchers-find-the-future-of-diabetes-management-isnt-automation-its-human-machine-collaboration","status":"publish","type":"post","link":"https:\/\/med.virginia.edu\/diabetes-technology\/2026\/03\/30\/cdt-researchers-find-the-future-of-diabetes-management-isnt-automation-its-human-machine-collaboration\/","title":{"rendered":"CDT Researchers Find the Future of Diabetes Management Isn\u2019t Automation – It\u2019s Human-Machine Collaboration"},"content":{"rendered":"

How AI and Digital Twins Are Enabling Human\u2013Machine Co-Regulation in Diabetes Care<\/em><\/p>\n

\"Director

Dr. Boris Kovatchev<\/p><\/div>\n

March 30, 2026<\/strong> \u2013 In the keynote lecture opening the international conference Advanced Technologies and Treatments for Diabetes (ATTD) in Barcelona, Spain, Dr. Boris Kovatchev, proposed that there is a necessary fundamental transition in diabetes management from metabolic models to data-driven AI.<\/p>\n

Artificial intelligence (AI) is often described in sweeping, futuristic terms as machines that think, learn, and even replace human decision-making. But in diabetes care, the most promising role for AI may be far more collaborative: not replacing humans but working alongside them.<\/p>\n

\u201cThe question is no longer whether AI can make decisions,\u201d said Kovatchev. \u201cIt\u2019s whether AI can work with people to improve those decisions in real time.\u201d<\/p><\/blockquote>\n

At its core, AI is built on systems like neural networks, which are models that continuously learn by processing data, making predictions, and correcting errors. These systems power everything from image recognition to language processing. In healthcare, they are increasingly being applied to diagnose diseases, predict outcomes, and guide treatment decisions.<\/p>\n

Since 2018, nearly 5,000 research papers have explored applications of AI in diabetes. Much of this work has focused on diagnosis, detecting complications like retinopathy, optimizing decision support, and enhancing automated insulin delivery (AID) systems. Yet most of these applications are designed for clinicians, not for meaningful interaction with the person living with diabetes.<\/p>\n

\u201cWe\u2019ve built powerful tools for clinicians,\u201d Kovatchev explained. \u201cBut we haven\u2019t fully explored how AI can engage the person with diabetes as an active partner in their care.\u201d<\/p><\/blockquote>\n

This gap has led to a new concept: human\u2013machine co-regulation<\/strong>.<\/p>\n

\u201cDiabetes management is not a one-time decision, it\u2019s a continuous process,\u201d said Kovatchev. \u201cThat makes it the perfect setting for human\u2013machine collaboration.\u201d<\/p><\/blockquote>\n

Rather than replacing human decision-making, co-regulation creates a feedback loop, where AI and the individual continuously learn from and adapt to one another.<\/p>\n