Fig. 4

Permutation-based feature importance for the logistic regression model. The permutation-based importance was implemented in Scikit-Learn as permutation_importance method. This method randomly shuffles each feature and computes the change in the model’s performance. The features which impact the performance the most are the most important ones. The score is how the variable compares to other variables in the model. Thus, a high score for any level of a categorical variable indicates the entire variable is important. For clinical sites, the reference group is Belagavi, India. For maternal age, the reference group is 20–35 years. For maternal education, the reference group is University + . For parity, the reference group is parity of 1. For socio-economic status, the reference group is 66 + . For previous livebirth, yes is the reference group. For antenatal care visits, the reference group is 4 + visits