Identifying people with a high risk of developing diabetes among those with prediabetes may facilitate the implementation of a targeted lifestyle and pharmacological interventions. We aimed to establish machine learning models based on demographic and clinical characteristics to predict the risk of incident diabetes. We used data from the free medical examination service project for elderly people who were 65 years or older to develop logistic regression (LR), decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost) machine learning models for the follow-up results of 2019 and 2020 and performed internal validation. The receiver operating characteristic (ROC), sensitivity, specificity, accuracy, and F1 score were used to select the model with better performance. The average annual progression rate to diabetes in prediabetic elderly people was 14.21%. Each model was trained using eight features and one outcome variable from 9607 prediabetic individuals, and the performance of the models was assessed in 2402 prediabetes patients. The predictive ability of four models in the first year was better than in the second ye­ar. The XGBoost model performed relatively efficiently (ROC: 0.6742 for 2019 and 0.6707 for 2020). We established and compared four machine learning models to predict the risk of progression from prediabetes to diabetes. Although there was little difference in the performance of the four models, the XGBoost model had a relatively good ROC value, which might perform well in future exploration in this field.

Colorectal cancer poses a serious threat worldwide. Although early screening has been proved to be the most effective way to prevent and control colorectal cancer, the current situation of colorectal cancer screening remains not optimistic. The aim of this article is to apply the protection motivation theory (PMT) to examine the influencing factors on screening intention of colorectal cancer (CRC). This cross-sectional survey was launched in five communities in Wuhan, China. All the eligible urban Chinese were recruited and interviewed using paper-and-pencil questionnaires. The intention of colorectal cancer screening (CRCS) was measured using six PMT subconstructs, including perceived risk, perceived severity, fear arousal, response efficacy, response cost, and self-efficacy. Data on sociodemographic variables and knowledge of CRC were also collected. The structural equation modeling (SEM) method was used for data analysis. Among all the 569 respondents, 83.66% expressed willingness to participate in CRCS. Data of the research fit the proposed SEM model well (Chi-square/df = 2.04, GFI = 0.93, AGFI = 0.91, CFI = 0.91, IFI = 0.91, RMSEA = 0.04). Two subconstructs of PMT (response efficacy and self-efficacy) and CRC knowledge were directly and positively associated with screening intention. Age, social status, medical history, physical activity, and CRC knowledge were indirectly related to the screening intention through at least one of the two PMT subconstructs (response efficacy and self-efficacy). The findings of this study suggest the significance of enhancing response efficacy and self-efficacy in motivating urban Chinese adults to participate in CRC screening. Knowledge of CRC is significantly associated with screening intention. This study can provide useful information for the formulation and improvement of colorectal cancer screening strategies and plans.

Early identification of individuals at high risk of diabetes is crucial for implementing early intervention strategies. However, algorithms specific to elderly Chinese adults are lacking. The aim of this study is to build effective prediction models based on machine learning (ML) for the risk of type 2 diabetes mellitus (T2DM) in Chinese elderly. A retrospective cohort study was conducted using the health screening data of adults older than 65 years in Wuhan, China from 2018 to 2020. With a strict data filtration, 127,031 records from the eligible participants were utilized. Overall, 8298 participants were diagnosed with incident T2DM during the 2-year follow-up (2019–2020). The dataset was randomly split into training set (n = 101,625) and test set (n = 25,406). We developed prediction models based on four ML algorithms: logistic regression (LR), decision tree (DT), random forest (RF), and extreme gradient boosting (XGBoost). Using LASSO regression, 21 prediction features were selected. The Random under-sampling (RUS) was applied to address the class imbalance, and the Shapley Additive Explanations (SHAP) was used to calculate and visualize feature importance. Model performance was evaluated by the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. The XGBoost model achieved the best performance (AUC = 0.7805, sensitivity = 0.6452, specificity = 0.7577, accuracy = 0.7503). Fasting plasma glucose (FPG), education, exercise, gender, and waist circumference (WC) were the top five important predictors. This study showed that XGBoost model can be applied to screen individuals at high risk of T2DM in the early phrase, which has the strong potential for intelligent prevention and control of diabetes. The key features could also be useful for developing targeted diabetes prevention interventions.