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

<div>Predictive values for participants with and without GDM in the cohorts. (a) Distribution of predictive value and its relationship with the observed GDM in the combined cohort (development and validation cohort). (b) Distribution of predictive values in the development and validation cohort. Data are presented as median and interquartile ranges.</div>

Journal of Diabetes Research

fig5

Figure 5

Figure 5: Comparison of Machine Learning Methods and Conventional Logistic Regressions for Predicting Gestational Diabetes Using Routine Clinical Data: A Retrospective Cohort Study 

Figure 5 | Comparison of Machine Learning Methods and Conventional Logistic Regressions for Predicting Gestational Diabetes Using Routine Clinical Data: A Retrospective Cohort Study 