Comparison of Machine Learning Methods and Conventional Logistic Regressions for Predicting Gestational Diabetes Using Routine Clinical Data: A Retrospective Cohort Study

<div>Predictive performance of the GBDT model. (a) AUCs of the development and validation cohorts. (b) The graph presents the calibration curve of the GBDT model by showing the relationships between observed and predicted GDM using the GBDT model. Data are presented as mean and 95% CIs.</div>

Journal of Diabetes Research

fig4

Figure 4

Figure 4: Comparison of Machine Learning Methods and Conventional Logistic Regressions for Predicting Gestational Diabetes Using Routine Clinical Data: A Retrospective Cohort Study 

Figure 4 | Comparison of Machine Learning Methods and Conventional Logistic Regressions for Predicting Gestational Diabetes Using Routine Clinical Data: A Retrospective Cohort Study 