Thakur Anshul, Goldbaum Michael, Yousefi Siamak
School of Computing and Electrical EngineeringIndian Institute of Technology MandiMandi175005India.
Department of OphthalmologyUniversity of California San DiegoSan DiegoCA92093USA.
IEEE J Transl Eng Health Med. 2020 May 28;8:3800107. doi: 10.1109/JTEHM.2020.2982150. eCollection 2020.
The purpose of this study was to identify clinically relevant patterns of glaucomatous vision loss through convex representation to predict glaucoma several years prior to disease onset. We developed a deep archetypal analysis to identify patterns of glaucomatous vision loss, and then projected visual fields over the identified patterns. Projections provided a representation that was more accurate in detecting glaucomatous vision loss, thus, more appropriate for recognizing preclinical signs of glaucoma prior to disease development. To overcome the class imbalance in prediction, we implemented a class-balanced bagging with neural networks. Using original visual field as features of the class-balanced bagging classification provided an area under the receiver-operating characteristic curve (AUC) of 0.55 for predicting glaucoma approximately four years prior to disease development. Using convex representation of the visual fields as input features provided an AUC of 0.61 while using deep convex representation as input features improved the AUC to 0.71. Relevance vector machine (RVM) achieved an AUC of 0.64. Deep archetypal analysis representation of visual functional features with balanced bagging classification could serve as an automated tool for predicting glaucoma. Glaucoma is the second leading cause of worldwide blindness. Most people with glaucoma have no early symptoms or pain, delaying diagnosis in many patients until they reach late irreversible vision loss stages. In fact, about 50% of people with glaucoma are unaware they have the disease. Deep archetypal analysis models may impact clinical practice in effectively identifying at-risk glaucoma patients well prior to disease development.
本研究的目的是通过凸表示法识别青光眼性视力丧失的临床相关模式，以在疾病发作前数年预测青光眼。我们开发了一种深度原型分析来识别青光眼性视力丧失的模式，然后将视野投影到已识别的模式上。投影提供了一种在检测青光眼性视力丧失方面更准确的表示，因此，更适合在疾病发展之前识别青光眼的临床前体征。为了克服预测中的类别不平衡，我们实施了带神经网络的类别平衡装袋法。使用原始视野作为类别平衡装袋分类的特征，在疾病发展前约四年预测青光眼时，受试者操作特征曲线（AUC）下的面积为0.55。使用视野的凸表示作为输入特征时，AUC为0.61，而使用深度凸表示作为输入特征时，AUC提高到0.71。相关向量机（RVM）的AUC为0.64。具有平衡装袋分类的视觉功能特征的深度原型分析表示可作为预测青光眼的自动化工具。青光眼是全球第二大致盲原因。大多数青光眼患者没有早期症状或疼痛，许多患者直到视力丧失到晚期不可逆转阶段才被诊断出来。事实上，约50%的青光眼患者不知道自己患有这种疾病。深度原型分析模型可能会在疾病发展之前有效地识别青光眼高危患者，从而影响临床实践。
