Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Incidentalomas is the subject of a report. According to news originatingfrom Beijing, People’s Republ ic of China, by NewsRx correspondents, research stated, “To assess the diagnosti c value of combining plasma steroid profiling with machine learning (ML) in diff erentiatingbetween mild autonomous cortisol secretion (MACS) and nonfunctioning adenoma (NFA) in patients withadrenal incidentalomas. The plasma steroid profi les data in the laboratory information system werescreened from January 2021 to December 2023.”Our news journalists obtained a quote from the research from Peking Union Medica l College Hospital,“EXtreme Gradient Boosting (XGBoost) was applied to establis h diagnostic models using plasma 24-steroid panels and/or clinical characteristi cs of the subjects. The SHapley Additive exPlanation (SHAP)method was used for explaining the model. 76 patients with MACS and 86 patients with NFA were included in the development and internal validation cohort while the external validati on cohort consisted of 27MACS and 21 NFA cases. Among five ML models evaluated, XGBoost demonstrated superior performancewith an AUC of 0.77 using 24 steroid hormones. The SHAP method identified five steroids that exhibitedoptimal perfor mance in distinguishing MACS from NFA, namely dehydroepiandrosterone (DHEA), 11-deoxycortisol, 11b-hydroxytestosterone, testosterone, and dehydroepiandrosterone sulfate (DHEAS). Uponincorporating clinical features into the model, the AUC in creased to 0.88, with a sensitivity of 0.77and specificity of 0.82. Furthermore , the results obtained through SHAP revealed that lower levels oftestosterone, DHEA, LDL-c, BMI, and ACTH along with higher level of 11-deoxycortisol significa ntlycontributed to the identification of MACS in the model. We have elucidated the utilization of ML-basedsteroid profiling to discriminate between MACS and N FA in patients with adrenal incidentalomas.”
NETL
NSTL