Performance of machine learning algorithms for hysterectomy risk prediction among women with endometriosis in the United States

Hysterectomy risk prediction in endometriosis patients could enable more personalized clinical management, but the performance of machine learning algorithms for this prediction task in a large real-world endometriosis cohort had not been evaluated.

Target RWE researchers evaluated the performance of multiple machine learning algorithms for hysterectomy risk prediction among women with endometriosis using real-world clinical data, comparing ML approaches against traditional logistic regression.

Demonstrating that ML algorithms can predict hysterectomy risk in endometriosis provides evidence for precision medicine approaches in women's health, supporting pharma partners developing therapies who need patient risk stratification tools.

Machine learning hysterectomy risk prediction for endometriosis precision medicine and trial enrollment, Predictive analytics evaluation for women's health drug development patient stratification