A logistic model for the prediction of endometriosis

ObjectiveTo develop a model that uses individual and lesion characteristics to help surgeons choose lesions that have a high probability of containing histologically confirmed endometriosis.DesignSecondary analysis of prospectively collected information.SettingGovernment research hospital in the United States.Patient(s)Healthy women 18–45 years of age, with chronic pelvic pain and possible endometriosis, who were enrolled in a clinical trial.Intervention(s)All participants underwent laparoscopy, and information was collected on all visible lesions. Lesion data were randomly allocated to a training and test data set.Main Outcome Measure(s)Predictive logistic regression, with the outcome of interest being histologic diagnosis of endometriosis.Result(s)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.Conclusion(s)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. 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.