Back

Role of personalized predictions for people with prediabetes: disseminating patient-centered estimates of benefit

Olchanski, N.; Ciemins, E. L.; Colangelo, F.; Koenig, C.; Kent, D. M.

2024-12-08 endocrinology
10.1101/2024.12.03.24318396 medRxiv
Show abstract

BackgroundTo assess acceptability and feasibility of incorporating individualized risk prediction into clinical assessment, decision making, and communication of risk of type 2 diabetes and prevention recommendations. MethodsWe integrated a prediction model into the clinical workflow at a US health care organization. We conducted patient and provider focus groups and pre- and post-dissemination surveys and assessed the effect on referrals to and enrollment in the Diabetes Prevention Program, among 2,775 patients with prediabetes who had primary care visits between May 2018 and December 2020. ResultsAmong patients with prediabetes seen in primary care during the study period, 79% had a calculation with the risk prediction model completed. After implementation of the risk prediction model, prevention intervention rates increased, with 62.3% of high-risk patients receiving an intervention within 1 year. ConclusionsUsed at the point of care during a shared decision-making discussion between the patient and provider, the diabetes risk calculator helped providers prioritize patients for diabetes prevention interventions, facilitated communication, and successfully improved rates of engagement in their care among patients with prediabetes.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.