CT-Based Radiomics Analysis of Different Machine Learning Models for Discriminating the Risk Stratification of Pheochromocytoma and Paraganglioma: A Multicenter Study.

RATIONALE AND OBJECTIVES: Using different machine learning models CT-based radiomics to integrate clinical radiological features to discriminating the risk stratification of pheochromocytoma/paragangliomas (PPGLs). MATERIALS AND METHODS: The present study included 201 patients with PPGLs from three hospitals (training set: n = 125; external validation set: n = 45; external test set: n = 31). Patients were divided into low-risk and high-risk groups using a staging system for adrenal pheochromocytoma and paraganglioma (GAPP). We extracted and selected CT radiomics features, and built radiomics models using support vector machines (SVM), k-nearest neighbors, random forests, and multilayer perceptrons. Using receiver operating characteristic curve analysis to select the optimal radiomics model, a combined model was built using the output of the optimal radiomics model and clinical radiological features, and its accuracy and clinical applicability were evaluated using calibration curves and clinical decision curve analysis (DCA). RESULTS: Finally, 13 radiomics features were selected to construct machine learning models. In the radiomics model, the SVM model demonstrated higher accuracy and stability, with an AUC value of 0.915 in the training set, 0.846 in external validation set, and 0.857 in external test set. Combining the outputs of SVM models with two clinical radiological features, a combined model constructed has demonstrated optimal risk stratification ability for PPGLs with an AUC of 0.926 for the training set, 0.883 for the external validation set, and 0.899 for the external test set. The calibration curve and DCA show good calibration accuracy and clinical effectiveness for the combined model. CONCLUSION: Combined model that integrates radiomics and clinical radiological features can discriminate the risk stratification of PPGLs.

Serum concentrations of 25-hydroxyvitamin D and its association with bone mineral density and serum parathyroid hormone levels during winter in urban males from Guiyang, Southwest China.

Serum vitamin D (25-hydroxyvitamin D (25OHD)) may influence serum parathyroid hormone (PTH) levels and bone mineral density (BMD). In the present study, we assessed serum 25OHD concentration and its association with PTH and BMD in urban males from Guiyang (N26.57°), the capital city of Guizhou province, Southwest China. We recruited 634 males aged >20 years from the Guiyang Health Measures Survey, and stratified them into three groups according to age: young (20-39 years), middle aged (40-59 years) and older (60-79 years). We measured serum concentrations of 25OHD, PTH levels and BMD of the lumbar spine (L1-L4), femoral neck and total hip. In addition, we also explored the relationship between 25OHD and lifestyle, socio-economic characteristics and medical history by applying covariance analysis and locally weighted regression plots. The results showed that serum 25OHD was 75 nmol/l in 12·6 % of the subjects. Higher level of serum PTH was detected in relation to lower concentrations of serum 25OHD up to 50 nmol/l. A negative correlation between serum 25OHD and PTH concentrations was observed (r -0·207, P=0·003). Mean concentration of serum PTH increased gradually and plateaued while concentrations of serum 25OHD decreased to 50 nmol/l. Gradual increase in serum PTH was observed as 25OHD concentration was <25 nmol/l (P=0·004). BMD values at all sites were greater in the higher serum 25OHD concentration group. This study shows that low concentrations of serum 25OHD were common in males, and bone health was likely to be improved when serum 25OHD values were between 30 and 50 nmol/l.

[An epidemiological survey of the prevalence of thyroid diseases in mild iodine deficiency city after salt iodization].

OBJECTIVE: To investigate the current status of iodine nutrition and the prevalence of thyroid diseases in Guiyang, a mild iodine deficiency city practiced salt iodization for 25 years. METHODS: A representative sample of 1509 adults aged 20 years old or above in Guiyang, selected by a multistage stratified sampling method, participated in the study. After an overnight fasting, serum thyroid hormones, serum thyroid autoantibodies, and urine iodine were measured. B-mode ultrasonography of the thyroid was performed in the population. Meanwhile, urine iodine of 80 children aged 8 - 10 years old in the same community were measured after an overnight fasting. RESULTS: The median of 8-10 years old children's urinary iodine was 228.7 µg/L. The prevalence of overt hypothyroidism, subclinical hypothyroidism, overt hyperthyroidism and subclinical hyperthyroidism was 1.79%, 14.12%, 1.52% and 1.06% respectively. The prevalence of subclinical hypothyroidism was significantly higher than overt hypothyroidism (P < 0.05) and was significantly higher in female than that in male (P < 0.05). The prevalence of positive thyroid peroxidase antibody, positive thyroglobulin antibody and autoimmune thyroiditis was 14.38%, 13.59% and 4.44% respectively, which were significantly higher in female than that in male (all P values < 0.05). The prevalence of diffuse goiter and nodular goiter was 0.86% and 0.20% respectively, with a significant difference (P < 0.05). CONCLUSION: After 25 years of salt iodization, the iodine nutrition in Guiyang is more than adequate with high prevalence of overt hypothyroidism, subclinical hypothyroidism and autoimmune thyroiditis.