RESUMO
As one of the most common diseases in pediatric surgery, an inguinal hernia is usually diagnosed by medical experts based on clinical data collected from magnetic resonance imaging (MRI), computed tomography (CT), or B-ultrasound. The parameters of blood routine examination, such as white blood cell count and platelet count, are often used as diagnostic indicators of intestinal necrosis. Based on the medical numerical data on blood routine examination parameters and liver and kidney function parameters, this paper used machine learning algorithm to assist the diagnosis of intestinal necrosis in children with inguinal hernia before operation. In the work, we used clinical data consisting of 3,807 children with inguinal hernia symptoms and 170 children with intestinal necrosis and perforation caused by the disease. Three different models were constructed according to the blood routine examination and liver and kidney function. Some missing values were replaced by using the RIN-3M (median, mean, or mode region random interpolation) method according to the actual necessity, and the ensemble learning based on the voting principle was used to deal with the imbalanced datasets. The model trained after feature selection yielded satisfactory results with an accuracy of 86.43%, sensitivity of 84.34%, specificity of 96.89%, and AUC value of 0.91. Therefore, the proposed methods may be a potential idea for auxiliary diagnosis of inguinal hernia in children.
RESUMO
Background: Triglycerides and 25(OH)D had been reported as correlates of IR, but the results suggest substantial heterogeneity across races. In addition, little research reported on whether different 25(OH)D levels affect triglycerides and IR. Therefore, a similar study on the US population would be a great addition to the current one. This study investigated the association between triglycerides and IR at different 25(OH)D levels. Methods: A total of 19,926 participants were included, each containing specific indicators for the study project. IR was estimated as a HOMA-IR index ≥2.73. Four multivariate logistic regression models were developed to analyze the association between TG and IR and whether different 25(OH)D levels influenced this association. Smoothed fitting curves were plotted. Results: Triglyceride was significantly associated with IR (OR: 1.3, 95 CI %), while this association received different 25(OH)D levels (P for interaction <0.001). The effect value OR was 1.33 with the high levels, and its effect value OR was 1.28 with the low levels. Conclusion: This study demonstrates that triglyceride levels are significantly associated with insulin in the US adult population and can be used as a predictor of IR. This correlation was compromised at different 25 (OH)D levels, so future studies need to be explored in more ethnically diverse contexts.
