Non-Invasive Predictive Model may Help in Early Detection of Endometriosis in Infertile Women: Study

The study divided patients into a training set (n=910) for model development and a validation set (n=455) for confirmation. This in depth evaluation included sensitivities, specificities, AUCs, the Hosmer-Lemeshow goodness of fit test, NRIs, and IDIs. The final model demonstrated high accuracy by incorporating BMI, dysmenorrhea, dyspareunia, uterosacral tenderness, and serum CA-125. Sensitivities of 87.7% and 93.3%, specificities of 68.6% and 66.4%, and AUCs of 0.84 and 0.85 were recorded for the training and validation sets, respectively.

Uterosacral tenderness emerged as a pivotal predictor and the nomogram underscored good calibration and clinical value. This innovative model promises a cost-effective and less invasive means of identifying minimal or mild endometriosis, a significant factor in infertility.

This study delivers a reliable tool for clinicians as a crucial step towards personalized infertility care. Early identification is a key to prompt intervention which potentially revolutionize the landscape of infertility treatment. This is a significant advancement in empowering healthcare providers with a tool to enhance the diagnosis and treatment of infertility in women.

Source:

Zhang, J., Wang, J., Zhang, J., Liu, J., Xu, Y., Zhu, P., Dai, L., Shu, L., Liu, J., Hou, Z., Diao, F., Liu, J., & Mao, Y. (2023). Developing a predictive model for minimal or mild endometriosis as a clinical screening tool in infertile women: uterosacral tenderness as a key predictor. In Journal of Minimally Invasive Gynecology. Elsevier BV. https://doi.org/10.1016/j.jmig.2023.12.008