Sugawara Risa, Usui Yoshihiko, Saito Akira, Nezu Naoya, Komatsu Hiroyuki, Tsubota Kinya, Asakage Masaki, Yamakawa Naoyuki, Wakabayashi Yoshihiro, Sugimoto Masahiro, Kuroda Masahiko, Goto Hiroshi
Department of Ophthalmology, Tokyo Medical University Hospital, Tokyo, Japan.
Department of AI Applied Quantitative Clinical Science, Tokyo Medical University, Tokyo, Japan.
Invest Ophthalmol Vis Sci. 2025 Mar 3;66(3):38. doi: 10.1167/iovs.66.3.38.
This study aimed to elucidate whether machine learning algorithms applied to vitreous levels of immune mediators predict the diagnosis of 12 representative intraocular diseases, and identify immune mediators driving the predictive power of machine learning model.
Vitreous samples in 522 eyes diagnosed with 12 intraocular diseases were collected, and 28 immune mediators were measured using a cytometric bead array. The significance of each immune mediator was determined by employing five machine learning algorithms. Stratified k-fold cross-validation was performed to divide the dataset into training and test sets. The algorithms were assessed by analyzing precision, recall, accuracy, F-score, area under the receiver operating characteristics curve, area under the precision-recall curve, and feature importance.
Of the five machine learning models, random forest attained the maximum accuracy in the classification of 12 intraocular diseases in a multi-class setting. The random forest prediction models for vitreoretinal lymphoma, endophthalmitis, uveal melanoma, rhegmatogenous retinal detachment, and acute retinal necrosis demonstrated superior classification accuracy, precision, and recall. The top three important immune mediators for predicting vitreoretinal lymphoma were IL-10, granzyme A, and IL-6; those for endophthalmitis were IL-6, G-CSF, and IL-8; and those for uveal melanoma were RANTES, IL-8 and bFGF.
The random forest algorithm effectively classified 28 immune mediators in the vitreous to accurately predict the diagnosis of vitreoretinal lymphoma, endophthalmitis, and uveal melanoma among 12 representative intraocular diseases. In summary, the results of this study enhance our understanding of potential new biomarkers that may contribute to elucidating the pathophysiology of intraocular diseases in the future.
本研究旨在阐明应用于玻璃体免疫介质水平的机器学习算法是否能预测12种代表性眼内疾病的诊断，并确定驱动机器学习模型预测能力的免疫介质。
收集了522只被诊断患有12种眼内疾病的眼睛的玻璃体样本，并使用细胞计数珠阵列测量了28种免疫介质。采用五种机器学习算法确定每种免疫介质的重要性。进行分层k折交叉验证以将数据集分为训练集和测试集。通过分析精度、召回率、准确率、F分数、受试者工作特征曲线下面积、精确召回率曲线下面积和特征重要性来评估算法。
在五种机器学习模型中，随机森林在多类设置下对12种眼内疾病的分类中获得了最高准确率。玻璃体视网膜淋巴瘤、眼内炎、葡萄膜黑色素瘤、孔源性视网膜脱离和急性视网膜坏死的随机森林预测模型表现出卓越的分类准确率、精度和召回率。预测玻璃体视网膜淋巴瘤的前三种重要免疫介质是白细胞介素-10、颗粒酶A和白细胞介素-6；预测眼内炎的是白细胞介素-6、粒细胞集落刺激因子和白细胞介素-8；预测葡萄膜黑色素瘤的是调节激活正常T细胞表达和分泌的趋化因子、白细胞介素-8和碱性成纤维细胞生长因子。
随机森林算法有效地对玻璃体中的28种免疫介质进行了分类，以准确预测12种代表性眼内疾病中的玻璃体视网膜淋巴瘤、眼内炎和葡萄膜黑色素瘤的诊断。总之，本研究结果增进了我们对潜在新生物标志物的理解，这些生物标志物可能有助于未来阐明眼内疾病的病理生理学。
