Purpose: The purpose of this study is to explore the independent-influencing factors from normal people to prediabetes and from prediabetes to diabetes and use different prediction models to build diabetes prediction models.
Methods: The original data in this retrospective study are collected from the participants who took physical examinations in the Health Management Center of Peking University Shenzhen Hospital. Regression analysis is individually applied between the populations of normal and prediabetes, as well as the populations of prediabetes and diabetes, for feature selection. Afterward,the independent influencing factors mentioned above are used as predictive factors to construct a prediction model.
Results: Selecting physical examination indicators for training different ML models through univariate and multivariate logistic regression, the study finds Age, PRO, TP, and ALT are four independent risk factors for normal people to develop prediabetes, and GLB and HDL.C are two independent protective factors, while logistic regression performs best on the testing set (Acc: 0.76, F-measure: 0.74, AUC: 0.78). We also find Age, Gender, BMI, SBP, U.GLU, PRO, ALT, and TG are independent risk factors for prediabetes people to diabetes, and AST is an independent protective factor, while logistic regression performs best on the testing set (Acc: 0.86, F-measure: 0.84, AUC: 0.74).
Conclusion: The discussion of the clinical relationships between these indicators and diabetes supports the interpretability of our feature selection. Among four prediction models, the logistic regression model achieved the best performance on the testing set.
Keywords: machine learning; physical examination; prediabetes; prediction model; regression analysis.
© 2024 Chen et al.