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

<div>Results of discrimination and calibration metrics of machine learning and logistic regressions in the validation cohort. The AUC (a) and mean absolute error (b) are presented in each model as mean and 95% confidence intervals.</div>

Journal of Diabetes Research

fig2

Figure 2

Figure 2: Comparison of Machine Learning Methods and Conventional Logistic Regressions for Predicting Gestational Diabetes Using Routine Clinical Data: A Retrospective Cohort Study 

Figure 2 | Comparison of Machine Learning Methods and Conventional Logistic Regressions for Predicting Gestational Diabetes Using Routine Clinical Data: A Retrospective Cohort Study 