Differential effect of interventions in patients with prediabetes stratified by a machine learning‐based diabetes progression prediction model.

Aim: To investigate whether stratifying participants with prediabetes according to their diabetes progression risks (PR) could affect their responses to interventions. Methods: We developed a machine learning‐based model to predict the 1‐year diabetes PR (ML‐PR) with the least predictors. The model was developed and internally validated in participants with prediabetes in the Pinggu Study (a prospective population‐based survey in suburban Beijing; n = 622). Patients from the Beijing Prediabetes Reversion Program cohort (a multicentre randomized control trial to evaluate the efficacy of lifestyle and/or pioglitazone on prediabetes reversion; n = 1936) were stratified to low‐, medium‐ and high‐risk groups using ML‐PR. Different effect of four interventions within subgroups on prediabetes reversal and diabetes progression was assessed. Results: Using least predictors including fasting plasma glucose, 2‐h postprandial glucose after 75 g glucose administration, glycated haemoglobin, high‐density lipoprotein cholesterol and triglycerides, and the ML algorithm XGBoost, ML‐PR successfully predicted the 1‐year progression of participants with prediabetes in the Pinggu study [internal area under the curve of the receiver operating characteristic curve 0.80 (0.72–0.89)] and Beijing Prediabetes Reversion Program [external area under the curve of the receiver operating characteristic curve 0.80 (0.74–0.86)]. In the high‐risk group pioglitazone plus intensive lifestyle therapy significantly reduced diabetes progression by about 50% at year l and the end of the trial in the high‐risk group compared with conventional lifestyle therapy with placebo. In the medium‐ or low‐risk group, intensified lifestyle therapy, pioglitazone or their combination did not show any benefit on diabetes progression and prediabetes reversion. Conclusions: This study suggests personalized treatment for prediabetes according to their PR is necessary. ML‐PR model with simple clinical variables may facilitate personal treatment strategies in participants with prediabetes. [ABSTRACT FROM AUTHOR]