Comparison of machine learning models for the prediction of hypertension in transgender patients undergoing gynecologic surgery

Abstract

Transgender patients face a higher burden of cardiovascular morbidity due to structural and biological stressors, particularly in low-resource settings. No studies exist comparing machine learning model development strategies for this unique patient cohort and limited literature exists comparing data/outcomes between transgender and cisgender populations. We compare machine learning models trained solely on transgender patients against models developed on a size-matched and ratio-matched cohort of cisgender patients and a 300-fold larger, ratio-matched cohort of cisgender patients undergoing obstetric/gynecologic procedures in the National Surgical Quality Improvement Program from January 1, 2005 through December 31, 2019. All models were developed to predict the outcome of hypertension. Statistical significance between models was calculated using 5-by-2 fold cross validation hypothesis testing. Among 626,102 patients having an obstetric/gynecologic surgery, there are 1959 transgender patients of which 85,405 (13.7%) have hypertension requiring medication. Saliently, the logistic regression machine learning models trained selectively on the transgender cohort have an AUC of 0.865 (95% CI: 0.83–0.90), with an accuracy of 85% (95% CI: 0.80–0.87) compared to (p < 0.05) the logistic regression model trained on the 300-fold larger combined cohort which has an AUC of 0.861 (95% CI: 0.82–0.90), with an accuracy of 83% (95% CI: 0.80–0.87). Machine learning models can be trained on smaller, selectively transgender populations and may perform similarly or better to predict cardiovascular outcomes in transgender patients, than models developed on predominantly cisgender patients; this can be useful in lower-resource settings with smaller-volume transgender patients. Transgender patients face a higher burden of cardiovascular disease. Statistical models that predict cardiovascular disease-related outcomes, such as high blood pressure (hypertension), may be useful to clinicians to guide treatment, but existing models are mainly developed in cisgender populations. Here, we developed models to predict hypertension in patients undergoing surgery, and compared models developed using data from cisgender patients, transgender patients, or mixed populations to see if this affected how well these models could predict hypertension in the transgender population. We ultimately found that one of our models trained on a much smaller cohort of solely transgender patients outperformed the same model trained on a 300-times larger population of mixed cisgender and transgender patients. These findings might help to guide future efforts to develop statistical approaches to accurately predict health outcomes in transgender patients. Ganguli et al. compare the performance of machine learning models to predict hypertension in transgender patients undergoing gynecologic surgery. Logistic regression models trained on data from a cohort of transgender patients perform better than those trained on a predominantly cisgender cohort.