It combs through patients' medical data, including results from routine medical check-ups, to provide a diabetes risk assessment for each patient. Japanese researchers who developed the technology have said it identified thousands of new diabetes patients in trials. A method called machine learning could help predict whether people will get diabetes. 'Using machine learning, it could be possible to precisely identify high-risk groups of future diabetes patients better than using existing risk scores,' Dr Nomura said. The researchers said their algorithm had an overall accuracy of 94.9 per cent, and was able to identify a total of 4,696 new diabetes patients.

Source: Daily Mail March 31, 2020 13:51 UTC