Chinese AI System Designed to Predict Diabetes Years in Advance

The model named Ruining Knows Sugar, or Ruining Zhitang in Chinese, has achieved an accuracy rate of 88% in tests.

Designed to identify those most at risk of developing type 2 diabetes within the next three years, the system also provided risk forecasts for the next nine and 15 years as a reference. For the tests, the new system used medical information from 170,000 individuals from across the country, some of who had diabetes and others did not. The data collected by the hospital’s diabetes research team between 2010 and 2013 included gender, height, weight, blood sugar levels, smoking and drinking history, and education levels. The AI algorithm then used that information to make its predictions and “learned” from the results.

The use of AI to help predict and monitor diabetes is growing. For instance, in June 2018, medical device company Medtronic along with IBM Waston Health released its Sugar.IQ app, which evaluates how a user’s blood sugar levels respond to variables such as food intake, insulin dosing and other daily routines.

Related Links:
4 Paradigm
Ruijin Hospital