Kim Jinsoo, Han Bo Sook, Ha Joo Eun, Park Min Seon, Kwon Soonil, Cho Bum-Joo
Department of Ophthalmology, Hallym University Sacred Heart Hospital, Hallym University College of Medicine, Anyang 14068, Republic of Korea.
Medical Artificial Intelligence Center, Hallym University Medical Center, Anyang 14068, Republic of Korea.
Diagnostics (Basel). 2025 Feb 4;15(3):371. doi: 10.3390/diagnostics15030371.
This study aimed to predict the unknown etiology of fundus-obscuring vitreous hemorrhage (FOVH) based on preoperative conditions using machine learning (ML) and to identify key preoperative factors. Medical records of 223 eyes from 204 patients who underwent vitrectomy for FOVH of unknown etiology between January 2012 and July 2022 were retrospectively reviewed. Preoperative data, including demographic information, systemic disease, ophthalmic history, and retinal status of the unaffected eye, were collected. The postoperatively identified etiologies of FOVH were categorized into six groups: proliferative diabetic retinopathy (PDR), retinal vein occlusion (RVO) or rupture of retinal arterial macroaneurysm, neovascular age-related macular degeneration (nAMD), retinal tear, Terson syndrome, and other causes. Four ML algorithms were trained and evaluated using seven-fold cross-validation. : The ML algorithms achieved mean accuracies of 76.2% for artificial neural network, 74.5% for XG-Boost, 74.4% for LASSO logistic regression, and 68.5% for decision tree. Key predictive factors commonly selected by the ML algorithms included PDR in the fellow eye, underlying diabetes mellitus, subarachnoid hemorrhage, and a history of retinal tear, RVO, or nAMD in the affected eye. : The unknown etiology of FOVH could be predicted preoperatively with considerable accuracy by ML algorithms. Previous ophthalmic conditions in the affected eye and the condition of the fellow eye were important variables for prediction. This approach might assist in determining appropriate treatment plans.
本研究旨在利用机器学习（ML），根据术前情况预测导致眼底模糊的玻璃体积血（FOVH）的未知病因，并确定关键的术前因素。回顾性分析了2012年1月至2022年7月间因病因不明的FOVH接受玻璃体切除术的204例患者的223只眼的病历。收集了术前数据，包括人口统计学信息、全身疾病、眼科病史以及未受影响眼的视网膜状况。术后确定的FOVH病因分为六组：增殖性糖尿病视网膜病变（PDR）、视网膜静脉阻塞（RVO）或视网膜动脉大动脉瘤破裂、新生血管性年龄相关性黄斑变性（nAMD）、视网膜裂孔、Terson综合征和其他原因。使用七重交叉验证对四种ML算法进行了训练和评估。ML算法的平均准确率分别为：人工神经网络76.2%、XG-Boost 74.5%、LASSO逻辑回归74.4%、决策树68.5%。ML算法共同选择的关键预测因素包括对侧眼中的PDR、潜在糖尿病、蛛网膜下腔出血以及患眼中视网膜裂孔、RVO或nAMD的病史。通过ML算法可以在术前以相当高的准确率预测FOVH的未知病因。患眼先前的眼科状况和对侧眼的状况是预测的重要变量。这种方法可能有助于确定合适的治疗方案。
