A logistic model for the prediction of endometriosis

Abstract

To develop a model that uses individual and lesion characteristics to help surgeons choose lesions that have a high probability of containing histologically confirmed endometriosis. Secondary analysis of prospectively collected information. Government research hospital in the United States. Healthy women 18-45 years of age, with chronic pelvic pain and possible endometriosis, who were enrolled in a clinical trial. All participants underwent laparoscopy, and information was collected on all visible lesions. Lesion data were randomly allocated to a training and test data set. Predictive logistic regression, with the outcome of interest being histologic diagnosis of endometriosis. After validation, the model was applied to the complete data set, with a sensitivity of 88.4% and specificity of 24.6%. The positive predictive value was 69.2%, and the negative predictive value was 53.3%, equating to correct classification of a lesion of 66.5%. Mixed color; larger width; and location in the ovarian fossa, colon, or appendix were most strongly associated with the presence of endometriosis. This model identified characteristics that indicate high and low probabilities of biopsy-proven endometriosis. It is useful as a guide in choosing appropriate lesions for biopsy, but the improvement using the model is not great enough to replace histologic confirmation of endometriosis.