ADA: Twin Health’s AI tech leads to Type 2 diabetes remissions, study finds

It may not be able to pass the Turing test, but a “digital twin” created by Twin Health’s artificial intelligence could help its human counterpart reverse the symptoms of Type 2 diabetes and significantly cut back on medications for the condition, including insulin.

That’s according to the results of a clinical trial of the technology, which were presented Saturday at the American Diabetes Association’s annual scientific sessions in New Orleans.

Twin Health’s Whole Body Digital Twin platform collects thousands of data points each day from wearable sensors, then combines those readings with the results of blood tests and self-reported questionnaires to build a computer model of each patient. The AI continuously updates and analyzes the model to spot problem areas in a patient’s individual metabolism and suggest potential changes and improvements for their nutrition, activity, sleep and breathing, all with the ultimate goal of reversing diabetes symptoms.

The technology is meant to be used for at least a year, split into three phases of several months each: normalizing the metabolism, addressing the AI-detected issues and sustaining any gains. Users can keep track of their progress and the AI’s predictions through a connected mobile app.

The company's clinical trial analyzed 199 patients who had been diagnosed with diabetes for an average of almost four years, and who began the study with a average A1C of 9%.

After six months, researchers found that with sustained use of the digital twin technology, almost 95% saw A1C levels drop below 6.5%. They reported an average drop of 3.3 points compared to improvements of just 0.39 in the trial’s control group, which received the current standard of care for Type 2 diabetes.

The digital twin group was able to achieve that drop without relying on any medications besides metformin. In addition, all nine of the patients who had been using insulin were able to stop injections before the 90-day point.

In total, nearly 84% of the group who followed their digital twin’s guidance for six months were determined to be in remission by the end of that period, per the ADA's standards—meaning they maintained normal blood glucose levels for at least three months without taking diabetes medication.

Additionally, lead author Paramesh Shamanna, M.D., said in a statement, “The impact of the program on patient satisfaction, quality of life and total cost of care is substantial and holds significant promise for large populations suffering from metabolic disease globally.”

The promising clinical results arrive shortly after Twin Health raked in a similarly promising series C funding round.

The financing, which the Silicon Valley startup announced last October, totaled $140 million. With the support from a cadre of VC backers—including ICONIQ Growth, Sequoia Capital India, Perceptive Advisors, Corner Ventures, LTS Investments, Helena and Sofina—Twin Health said at the time that it would direct the funds toward continued development of the Whole Body Digital Twin platform, including an expansion into new disease areas.