METHODS: A retrospective study was performed on patients diagnosed with orbital fractures at Farabi Hospital between 2016 and 2022. Patients with a comprehensive ophthalmologic examination and orbital CT scan were included. Predictive signs or imaging findings for SCGI were identified by logistic regression (LR) analysis. Support vector machine (SVM), random forest regression (RFR), and extreme gradient boosting (XGBoost) were also trained using a fivefold cross-validation method.
RESULTS: A total of 415 eyes from 403 patients were included. Factors associated with an increased risk of SCGI were reduced uncorrected visual acuity (UCVA), increased difference between UCVA of the traumatic eye from the contralateral eye, older age, male sex, grade of periorbital soft tissue trauma, trauma in the occupational setting, conjunctival hemorrhage, extraocular movement restriction, number of fractured walls, presence of medial wall fracture, size of fracture, intraorbital emphysema and retrobulbar hemorrhage. The area under the curve of the receiver operating characteristic for LR, SVM, RFR, and XGBoost for the prediction of SCGI was 57.2%, 68.8%, 63.7%, and 73.1%, respectively.
CONCLUSIONS: Clinical and radiographic findings could be utilized to efficiently predict SCGI. XGBoost outperforms the logistic regression model in the prediction of SCGI and could be incorporated into clinical practice.
方法:对2016年至2022年在Farabi医院诊断为眼眶骨折的患者进行了回顾性研究。包括接受全面眼科检查和眼眶CT扫描的患者。通过逻辑回归(LR)分析确定SCGI的预测体征或影像学发现。支持向量机(SVM)随机森林回归(RFR),和极端梯度增强(XGBoost)也使用五倍交叉验证方法进行训练。
结果:共纳入403例患者的415只眼。与SCGI风险增加相关的因素是未矫正视力(UCVA)降低,外伤眼与对侧眼的UCVA之间的差异增加,年龄较大,男性,眶周软组织创伤分级,职业环境中的创伤,结膜出血,眼外活动限制,裂缝壁的数量,存在内侧壁骨折,骨折的大小,眶内气肿和球后出血。LR的接收机工作特性曲线下的面积,SVM,RFR,XGBoost对SCGI的预测为57.2%,68.8%,63.7%,73.1%,分别。
结论:临床和影像学检查结果可用于有效预测SCGI。XGBoost在预测SCGI方面优于逻辑回归模型,可以纳入临床实践。