Comparison of externally validated interpretable machine‐learning model with the United States Preventive Services Task Force approach to pre‐eclampsia risk assessment

The data that support the findings of this study are available from Foundation for Health Care Quality. Restrictions apply to the availability of these data, which were used under license for this study. Data are available from the author(s) with the permission of Foundation for Health Care Quality. Table S1 United States Preventive Services Task Force (USPSTF) risk assessment and matched variables available in research dataset used in present study Table S2 Population characteristics for 22 input variables used in explainable boosting machine model Figure S1 Receiver-operating-characteristics curve for prediction of preterm pre-eclampsia in external validation dataset for explainable boosting machine model using 22 features (10 used in the USPSTF approach plus an additional 12) which are routinely collected as part of clinical care in first trimester of pregnancy. Figure S2 Importance and contribution of top input variables in explainable boosting machine model. Distress quintile is from Economic Innovation Group's Distressed Communities Index ( https://eig.org/distressed-communities/). RUCA refers to Rural-Urban Commuting Area Codes ( https://depts.washington.edu/uwruca/ruca-uses.php). Please note: The publisher is not responsible for the content or functionality of any supporting information supplied by the authors. Any queries (other than missing content) should be directed to the corresponding author for the article.