Bénard-Séguin Étienne, Nielsen Christopher, Sarhan Abdullah, Al-Ani Abdullah, Sylvestre-Bouchard Antoine, Waldner Derek M, De Lott Lindsey B, Subramaniam Suresh, Costello Fiona
Division of Ophthalmology (EB-S, AS, AA-A, AS-B, DW, SS, FC), Department of Surgery, University of Calgary, Calgary, Canada; Department of Biomedical Engineering (CN), University of Calgary, Calgary, Canada; Departments of Neurology (LBDL) and Ophthalmology (LBDL), University of Michigan, Ann Arbor, Michigan; and Department of Clinical Neurosciences (SS, FC), University of Calgary, Calgary, Canada.
J Neuroophthalmol. 2024 Dec 1;44(4):462-468. doi: 10.1097/WNO.0000000000002229. Epub 2024 Aug 1.
Optic neuritis (ON) is a complex clinical syndrome that has diverse etiologies and treatments based on its subtypes. Notably, ON associated with multiple sclerosis (MS ON) has a good prognosis for recovery irrespective of treatment, whereas ON associated with other conditions including neuromyelitis optica spectrum disorders or myelin oligodendrocyte glycoprotein antibody-associated disease is often associated with less favorable outcomes. Delay in treatment of these non-MS ON subtypes can lead to irreversible vision loss. It is important to distinguish MS ON from other ON subtypes early, to guide appropriate management. Yet, identifying ON and differentiating subtypes can be challenging as MRI and serological antibody test results are not always readily available in the acute setting. The purpose of this study is to develop a deep learning artificial intelligence (AI) algorithm to predict subtype based on fundus photographs, to aid the diagnostic evaluation of patients with suspected ON.
This was a retrospective study of patients with ON seen at our institution between 2007 and 2022. Fundus photographs (1,599) were retrospectively collected from a total of 321 patients classified into 2 groups: MS ON (262 patients; 1,114 photographs) and non-MS ON (59 patients; 485 photographs). The dataset was divided into training and holdout test sets with an 80%/20% ratio, using stratified sampling to ensure equal representation of MS ON and non-MS ON patients in both sets. Model hyperparameters were tuned using 5-fold cross-validation on the training dataset. The overall performance and generalizability of the model was subsequently evaluated on the holdout test set.
The receiver operating characteristic (ROC) curve for the developed model, evaluated on the holdout test dataset, yielded an area under the ROC curve of 0.83 (95% confidence interval [CI], 0.72-0.92). The model attained an accuracy of 76.2% (95% CI, 68.4-83.1), a sensitivity of 74.2% (95% CI, 55.9-87.4) and a specificity of 76.9% (95% CI, 67.6-85.0) in classifying images as non-MS-related ON.
This study provides preliminary evidence supporting a role for AI in differentiating non-MS ON subtypes from MS ON. Future work will aim to increase the size of the dataset and explore the role of combining clinical and paraclinical measures to refine deep learning models over time.
视神经炎（ON）是一种复杂的临床综合征，根据其亚型具有多种病因和治疗方法。值得注意的是，与多发性硬化症相关的视神经炎（MS ON）无论接受何种治疗，恢复预后都较好，而与其他疾病相关的视神经炎，包括视神经脊髓炎谱系障碍或髓鞘少突胶质细胞糖蛋白抗体相关疾病，往往预后较差。这些非MS ON亚型的治疗延迟可能导致不可逆转的视力丧失。早期将MS ON与其他ON亚型区分开来以指导适当的管理非常重要。然而，由于在急性情况下MRI和血清学抗体检测结果并不总是容易获得，因此识别ON并区分亚型可能具有挑战性。本研究的目的是开发一种深度学习人工智能（AI）算法，根据眼底照片预测亚型，以辅助疑似ON患者的诊断评估。
这是一项对2007年至2022年在我们机构就诊的ON患者的回顾性研究。从总共321例患者中回顾性收集了1599张眼底照片，这些患者分为两组：MS ON（262例患者；1114张照片）和非MS ON（59例患者；485张照片）。使用分层抽样以80%/20%的比例将数据集分为训练集和保留测试集，以确保两组中MS ON和非MS ON患者的比例相等。在训练数据集上使用5折交叉验证调整模型超参数。随后在保留测试集上评估模型的整体性能和泛化能力。
在保留测试数据集上评估的开发模型的受试者操作特征（ROC）曲线，其ROC曲线下面积为0.83（95%置信区间[CI]，0.72 - 0.92）。在将图像分类为非MS相关ON时，该模型的准确率为76.2%（95% CI，68.4 - 83.1），灵敏度为74.2%（95% CI，55.9 - 87.4），特异性为76.9%（95% CI，67.6 - 85.0）。
本研究提供了初步证据，支持AI在区分非MS ON亚型与MS ON方面的作用。未来的工作将旨在增加数据集的规模，并探索结合临床和辅助临床措施以随着时间的推移优化深度学习模型的作用。
