Search

Objective: Distant metastasis often indicates a poor prognosis, so early screening and diagnosis play a significant role. Our study aims to construct and verify a predictive model based on machine learning (ML) algorithms that can estimate the risk of distant metastasis of newly diagnosed follicular thyroid carcinoma (FTC). Design: This was a retrospective study based on the Surveillance, Epidemiology, and End Results (SEER) database from 2004 to 2015. Patients: A total of 5809 FTC patients were included in the data analysis. Among them, there were 214 (3.68%) cases with distant metastasis. Method: Univariate and multivariate logistic regression (LR) analyses were used to determine independent risk factors. Seven commonly used ML algorithms were applied for predictive model construction. We used the area under the receiver‐operating characteristic (AUROC) curve to select the best ML algorithm. The optimal model was trained through 10‐fold cross‐validation and visualized by SHapley Additive exPlanations (SHAP). Finally, we compared it with the traditional LR method. Results: In terms of predicting distant metastasis, the AUROCs of the seven ML algorithms were 0.746–0.836 in the test set. Among them, the Extreme Gradient Boosting (XGBoost) had the best prediction performance, with an AUROC of 0.836 (95% confidence interval [CI]: 0.775–0.897). After 10‐fold cross‐validation, its predictive power could reach the best [AUROC: 0.855 (95% CI: 0.803–0.906)], which was slightly higher than the classic binary LR model [AUROC: 0.845 (95% CI: 0.818–0.873)]. Conclusions: The XGBoost approach was comparable to the conventional LR method for predicting the risk of distant metastasis for FTC. [ABSTRACT FROM AUTHOR]

Objective: To assess the efficacy and safety of prenatal dexamethasone treatment in offspring at risk for congenital adrenal hyperplasia. Methods: MEDLINE, EMBASE, the Cochrane Library, the clinicaltrials.gov website databases were systematically searched from inception through March 2019. WMD and SMD with 95%CIs were calculated using random or fixed effects models. Results: There was a significant reduction in virilization in the DEX‐treated group (WMD: −2.39, 95%CI: −3.31,‐1.47). No significant differences were found in newborn physical outcomes for birth weight (WMD: 0.09, 95%CI: −0.09, 0.27) and birth length (WMD = 0.27, 95%CI: −0.68, 1.21). Concerning cognitive functions, no significant differences in the domains of psychometric intelligence (SMD: 0.05, 95%CI: −0.74, 0.83), verbal memory (SMD: −0.17, 95%CI: −0.58, 0.23), visual memory (SMD: 0.10, 95%CI: −0.14, 0.34), learning (SMD: −0.02, 95%CI: −0.27, 0.22) and verbal processing (SMD: −0.38, 95%CI: −0.93, 0.17). Regarding behavioural problems, no significant differences in the domains of internalizing problems (SMD: 0.16, 95%CI: −0.49, 0.81), externalizing problems (SMD: 0.07, 95%CI: −0.30, 0.43) and total problems (SMD: 0.14, 95%CI: −0.23, 0.51). With respect to temperament, no significant differences in the domains of emotionality (SMD: 0.13, 95%CI: −0.79, 1.05), activity (SMD: 0.04, 95%CI: −0.32, 0.39), shyness (SMD: 0.25, 95%CI: −0.70, 1.20) and sociability (SMD: −0.23, 95%CI: −0.90, 0.44). Conclusions: Prenatal DEX treatment reduced virilization with no significant differences in newborn physical outcomes, cognitive functions, behavioural problems and temperament. The results need to be interpreted cautiously due to the existence of limitations. [ABSTRACT FROM AUTHOR]