A new artificial intelligence model finds that X-ray images collected during routine medical care can provide warning signs for diabetes, even in patients who don’t meet the guidelines for elevated risk. The model could help physicians detect the disease earlier and prevent complications, says a multi-institutional team which published the findings in Nature Communications.
Applying the computational method known as deep learning to images and electronic health record data, the researchers developed a model that successfully flagged elevated diabetes risk in a retrospective analysis, often years before patients were diagnosed with the disease. That’s significant, the researchers say, given the prevalence of diabetes in the U.S. has more than doubled over the past 35 years.
Current guidelines suggest screening patients for type 2 diabetes if they are between 35 and 70 years old and have a body mass index (BMI) in the overweight to obese range.
Leave a reply