He Zirong, Yang Bo, Tang Yunman, Wang Xuejun
Department of Pediatric Surgery of Children's Medical Center, Sichuan Provincial People's Hospital, School of Medicine, University of Electronic Science and Technology of China, Chengdu, China.
Front Pediatr. 2024 Apr 30;12:1297642. doi: 10.3389/fped.2024.1297642. eCollection 2024.
To describe the anatomical abnormalities of hypospadias before puberty using current commonly used anthropometric index data and predict postoperative diagnostic classification.
Children with hypospadias before puberty who were initially treated at Sichuan Provincial People's Hospital from April 2021 to September 2022 were selected. We recorded their preoperative penoscrotal distance, anogenital distance, 2D:4D finger ratio, and postoperative hypospadias classification. The receiver operating character curve was used for univariate analysis of the diagnostic predictive value of each index for hypospadias classification in the training set. Binary logistic regression, random forest, and support vector machine models were constructed. In addition, we also prospectively collected data from October 2022 to September 2023 as a test set to verify the constructed machine learning models.
This study included 389 cases, with 50 distal, 167 midshaft, and 172 proximal cases. In the validation set, the sensitivity of the binary LR, RF, and SVM was 17%, 17% and 0% for identifying the distal type, 61%, 55% and 64% for identifying the midshaft type, and 56%, 60% and 48% for identifying the proximal type, respectively. The sensitivity of the three-classification RF and SVM models was 17% and 17% for distal type, 64% and 73% for midshaft type, 60% and 60% for proximal type, respectively. In the Testing set, the sensitivity of the binary LR, RF and SVM was 6%, 0% and 0% for identifying the distal type, 64%, 55% and 66% for identifying the midshaft type, and 48%, 62% and 39% for identifying the proximal type, respectively. The sensitivity of the three-classification RF and SVM models was 12% and 0% for distal type, 57% and 77% for midshaft type, and 65% and 53% for proximal type, respectively. Compared with binary classification models, the sensitivity of the three-classification models for distal type was not improved.
Anogenital distance and penoscrotal distance have a favorable predictive value for midshaft and proximal hypospadias, among which AGD2, with higher test efficiency and stability, is recommended as the preferred anogenital distance indicator. The 2D:4D finger ratio (RadioL, RadioR) has little predictive value for hypospadias classification.
利用当前常用的人体测量指标数据描述青春期前尿道下裂的解剖学异常，并预测术后诊断分类。
选取2021年4月至2022年9月在四川省人民医院初治的青春期前尿道下裂患儿。记录其术前阴茎阴囊距离、肛生殖距离、2D:4D指比值及术后尿道下裂分类。采用受试者操作特征曲线对训练集中各指标对尿道下裂分类的诊断预测价值进行单因素分析。构建二元逻辑回归、随机森林和支持向量机模型。此外，我们还前瞻性收集了2022年10月至2023年9月的数据作为测试集，以验证构建的机器学习模型。
本研究共纳入389例，其中远端型50例，中段型167例，近端型172例。在验证集中，二元逻辑回归、随机森林和支持向量机识别远端型的敏感度分别为17%、17%和0%，识别中段型的敏感度分别为61%、55%和64%，识别近端型的敏感度分别为56%、60%和48%。三分类随机森林和支持向量机模型识别远端型的敏感度分别为17%和17%，识别中段型的敏感度分别为64%和73%，识别近端型的敏感度分别为60%和60%。在测试集中，二元逻辑回归、随机森林和支持向量机识别远端型的敏感度分别为6%、0%和0%，识别中段型的敏感度分别为64%、55%和66%，识别近端型的敏感度分别为48%、62%和39%。三分类随机森林和支持向量机模型识别远端型的敏感度分别为12%和0%，识别中段型的敏感度分别为57%和77%，识别近端型的敏感度分别为65%和53%。与二分类模型相比，三分类模型对远端型的敏感度未提高。
肛生殖距离和阴茎阴囊距离对中段和近端尿道下裂具有良好的预测价值，其中AGD2检测效率和稳定性较高，推荐作为首选的肛生殖距离指标。2D:4D指比值（RadioL、RadioR）对尿道下裂分类的预测价值较小。
