Development and validation of a new diabetes index for the risk classification of present and new-onset diabetes: multicohort study

Abstract

In this study, we aimed to propose a novel diabetes index for the risk classification based on machine learning techniques with a high accuracy for diabetes mellitus. Upon analyzing their demographic and biochemical data, we classified the 2013–16 Korea National Health and Nutrition Examination Survey (KNHANES), the 2017–18 KNHANES, and the Korean Genome and Epidemiology Study (KoGES), as the derivation, internal validation, and external validation sets, respectively. We constructed a new diabetes index using logistic regression (LR) and calculated the probability of diabetes in the validation sets. We used the area under the receiver operating characteristic curve (AUROC) and Cox regression analysis to measure the performance of the internal and external validation sets, respectively. We constructed a gender-specific diabetes prediction model, having a resultant AUROC of 0.93 and 0.94 for men and women, respectively. Based on this probability, we classified participants into five groups and analyzed cumulative incidence from the KoGES dataset. Group 5 demonstrated significantly worse outcomes than those in other groups. Our novel model for predicting diabetes, based on two large-scale population-based cohort studies, showed high sensitivity and selectivity. Therefore, our diabetes index can be used to classify individuals at high risk of diabetes.

Development and validation of a machine learning-augmented algorithm for diabetes screening in community and primary care settings: A population-based study

“…Recent studies indicate that diabetes prediction models developed based on images, electronic health records, or structured data obtained from their societies, using machine learning algorithms such as Decision Tree, Naive Bayes, SVM, ANN, etc., achieve superior performance and demonstrate their potential to be helpful for diabetes screening ( 38 , 39 ). We employed seven ML algorithms for diabetes screening using data from our population-based study in China, including LGBM, ANN, SVM, RF, KNN, CDKNN and LR, which are reported to have good performances in developing predictive models with high accuracy in recent studies ( 40 – 44 ). Our results indicated that the LGBM model had the best predictive accuracy among the models developed with the five algorithms in our societies.…”

Development and validation of a type 2 diabetes machine learning classification model for clinical decision support framework

“…Fasting plasma glucose level serves in our model as one of the outcome predictors and as an outcome-defining feature (see Methods). Some studies avoid doing this because of possible bias [12]. However, multiple evidence suggests that glucose and glycated hemoglobin (HbA1c), being two main diagnostic criteria for diabetes, are not as explicit in diagnostic value and need to be interpreted correctly in the context of patient's medical history, previous glycemic status, complaints, etc.…”

Classification Model for Diabetic Foot, Necrotizing Fasciitis, and Osteomyelitis

“…Although typical backward stepwise elimination sequentially removes a feature with the most insignificant result one by one, our modified backward elimination method subtracted all features exhibiting insignificant finding ( p < 0.1 in multivariate LR) at once. The modified backward elimination method used in our study has been attempted in previous studies [ 22 , 23 , 26 ].…”

“…Lee and Lee [ 27 ] integrated multiple statistical methods, such as the t -test and correlation method (i.e., the biweight midcorrelation method), to identify features. Moon et al [ 26 ] initially screened risk factors based on expert knowledge and finally determined predictors using multiple steps of statistical methods, including logistic regression (LR). LR is a frequently used approach for predicting DFU infections [ 28 , 29 ].…”