Boztas Asya Eylem, Sencan Efe, Payza Ayse Demet, Sencan Arzu
Health Sciences University, Dr. Behcet Uz Pediatric Diseases and Surgery Training and Research Hospital, Department of Pediatric Surgery, Ismet Kaptan Mh. Sezer Dogan Sk. No:11 Konak, Izmir, Turkey.
Boston University, College of Engineering, Electrical and Computer Engineering Department, 8 St Mary's St 324, Boston, MA, 02215, USA.
J Pediatr Surg. 2025 Jun 16;60(9):162417. doi: 10.1016/j.jpedsurg.2025.162417.
We aimed to develop a machine-learning (ML) algorithm consisting of physical examination, sonographic findings, and laboratory markers.
The data of 70 patients with confirmed ovarian torsion followed and treated in our clinic for ovarian torsion and 73 patients for control group that presented to the emergency department with similar complaints but didn't have ovarian torsion detected on ultrasound as the control group between 2013 and 2023 were retrospectively analyzed. Sonographic findings, laboratory values, and clinical status of patients were examined and fed into three supervised ML systems to identify and develop viable decision algorithms.
Presence of nausea/vomiting and symptom duration were statistically significant (p < 0.05) for ovarian torsion. Presence of abdominal pain and palpable mass on physical examination weren't significant (p > 0.05). White blood cell count (WBC), neutrophile/lymphocyte ratio (NLR), systemic immune-inflammation index (SII) and systemic inflammation response index (SIRI), high values of C-reactive protein was highly significant in prediction of torsion (p < 0.001, p < 0.05). Ovarian size ratio, medialization, follicular ring sign, presence of free fluid in pelvis in ultrasound demonstrated statistical significance in the torsion group (p < 0.001). We used supervised ML algorithms, including decision trees, random forests, and LightGBM, to classify patients as either control or having torsion. We evaluated the models using 5-fold cross-validation, achieving an average F1-score of 98 %, an accuracy of 98 %, and a specificity of 100 % across each fold with the decision tree model.
This study represents the first development of a ML algorithm that integrates clinical, laboratory and ultrasonographic findings for the diagnosis of pediatric ovarian torsion with over 98 % accuracy.
我们旨在开发一种由体格检查、超声检查结果和实验室指标组成的机器学习（ML）算法。
回顾性分析了2013年至2023年间在我们诊所随访并治疗的70例确诊为卵巢扭转的患者以及73例作为对照组的患者的数据，对照组患者因类似症状就诊于急诊科，但超声检查未发现卵巢扭转。检查了患者的超声检查结果、实验室值和临床状况，并将其输入到三个有监督的ML系统中，以识别和开发可行的决策算法。
恶心/呕吐的存在和症状持续时间对卵巢扭转具有统计学意义（p < 0.05）。体格检查中腹痛和可触及肿块的存在无统计学意义（p > 0.05）。白细胞计数（WBC）、中性粒细胞/淋巴细胞比值（NLR）、全身免疫炎症指数（SII）和全身炎症反应指数（SIRI）、高值的C反应蛋白在扭转预测中具有高度统计学意义（p < 0.001，p < 0.05）。超声检查中卵巢大小比值、内移、卵泡环征、盆腔游离液的存在在扭转组中具有统计学意义（p < 0.001）。我们使用了包括决策树、随机森林和LightGBM在内的有监督ML算法将患者分类为对照组或患有扭转。我们使用5折交叉验证评估模型，决策树模型在每一折中平均F1分数达到98%，准确率为98%，特异性为100%。
本研究首次开发了一种整合临床、实验室和超声检查结果的ML算法，用于诊断小儿卵巢扭转，准确率超过98%。
