AUTHOR=Liu Zhi-Wen , Chen Gang , Dong Chao-Fan , Qiu Wang-Ren , Zhang Shou-Hua 

TITLE=Intelligent assistant diagnosis for pediatric inguinal hernia based on a multilayer and unbalanced classification model

JOURNAL=Frontiers in Physiology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2023.1105891

DOI=10.3389/fphys.2023.1105891

ISSN=1664-042X

ABSTRACT=As one of the most common diseases in pediatric surgery, inguinal hernia is usually diagnosed by medical experts on basis of clinical data collected from MRI, 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 of 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, the clinical data consists of 3’807 children with inguinal hernia symptoms and 170 children with intestinal necrosis and perforation caused by the disease, and three different models were constructed according to the blood routine examination, liver and kidney function. Some missing values were replaced with the RIN-3M (median, mean or mode region random interpolation) method according to the actual necessity and the ensemble learning based on voting principle was used to deal with the imbalanced data sets. The model trained after feature selection has satisfactory results with an accuracy of 86.43%, a sensitivity of 84.34%, a specificity of 96.89%, and an AUC value of 0.91. Therefore, the proposed methods may be a potential idea for auxiliary diagnosing of inguinal hernia in children.