Development and validation of machine learning-augmented algorithm for insulin sensitivity assessment in the community and primary care settings: a population-based study in China.

Objective: Insulin plays a central role in the regulation of energy and glucose homeostasis, and insulin resistance (IR) is widely considered as the "common soil" of a cluster of cardiometabolic disorders. Assessment of insulin sensitivity is very important in preventing and treating IR-related disease. This study aims to develop and validate machine learning (ML)-augmented algorithms for insulin sensitivity assessment in the community and primary care settings. Methods: We analyzed the data of 9358 participants over 40 years old who participated in the population-based cohort of the Hubei center of the REACTION study (Risk Evaluation of Cancers in Chinese Diabetic Individuals). Three non-ensemble algorithms and four ensemble algorithms were used to develop the models with 70 non-laboratory variables for the community and 87 (70 non-laboratory and 17 laboratory) variables for the primary care settings to screen the classifier of the state-of-the-art. The models with the best performance were further streamlined using top-ranked 5, 8, 10, 13, 15, and 20 features. Performances of these ML models were evaluated using the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPR), and the Brier score. The Shapley additive explanation (SHAP) analysis was employed to evaluate the importance of features and interpret the models. Results: The LightGBM models developed for the community (AUROC 0.794, AUPR 0.575, Brier score 0.145) and primary care settings (AUROC 0.867, AUPR 0.705, Brier score 0.119) achieved higher performance than the models constructed by the other six algorithms. The streamlined LightGBM models for the community (AUROC 0.791, AUPR 0.563, Brier score 0.146) and primary care settings (AUROC 0.863, AUPR 0.692, Brier score 0.124) using the 20 top-ranked variables also showed excellent performance. SHAP analysis indicated that the top-ranked features included fasting plasma glucose (FPG), waist circumference (WC), body mass index (BMI), triglycerides (TG), gender, waist-to-height ratio (WHtR), the number of daughters born, resting pulse rate (RPR), etc. Conclusion: The ML models using the LightGBM algorithm are efficient to predict insulin sensitivity in the community and primary care settings accurately and might potentially become an efficient and practical tool for insulin sensitivity assessment in these settings.

Not performing an OGTT results in underdiagnosis, inadequate risk assessment and probable cost increases of (pre)diabetes in Han Chinese over 40 years: a population-based prospective cohort study.

OBJECTIVE: To explore the influence by not performing an oral glucose tolerance test (OGTT) in Han Chinese over 40 years. DESIGN: Overall, 6682 participants were included in the prospective cohort study and were followed up for 3 years. METHODS: Fasting plasma glucose (FPG), 2-h post-load plasma glucose (2h-PG), FPG and 2h-PG (OGTT), and HbA1c testing using World Health Organization (WHO) or American Diabetes Association (ADA) criteria were employed for strategy analysis. RESULTS: The prevalence of diabetes is 12.4% (95% CI: 11.6-13.3), while the prevalence of prediabetes is 34.1% (95% CI: 32.9-35.3) and 56.5% (95% CI: 55.2-57.8) using WHO and ADA criteria, respectively. 2h-PG determined more diabetes individuals than FPG and HbA1c. The testing cost per true positive case of OGTT is close to FPG and less than 2h-PG or HbA1c. FPG, 2h-PG and HbA1c strategies would increase costs from complications for false-positive (FP) or false-negative (FN) results compared with OGTT. Moreover, the least individuals identified as normal by OGTT at baseline developed (pre)diabetes, and the most prediabetes individuals identified by HbA1c or FPG using ADA criteria developed diabetes. CONCLUSIONS: The prevalence of isolated impaired glucose tolerance and isolated 2-h post-load diabetes were high, and the majority of individuals with (pre)diabetes were undetected in Chinese Han population. Not performing an OGTT results in underdiagnosis, inadequate developing risk assessment and probable cost increases of (pre)diabetes in Han Chinese over 40 years and great consideration should be given to OGTT in detecting (pre)diabetes in this population. Further population-based prospective cohort study of longer-term effects is necessary to investigate the risk assessment and cost of (pre)diabetes.