Multi-Branching Temporal Convolutional Network With Tensor Data Completion for Diabetic Retinopathy Prediction.
Multi-Branching Temporal Convolutional Network With Tensor Data Completion for Diabetic Retinopathy Prediction.
复制标题
用于糖尿病视网膜病变预测的具有张量数据补全的多分支时间卷积网络。
DOI：
10.1109/jbhi.2024.3351949
复制
发表时间：
2024
影响因子：
7.7
通讯作者：
Yao,Bing
中科院分区：
文献类型：
--
作者：
Wang,Zekai;Chen,Suhao;Liu,Tieming;Yao,Bing
糖尿病视网膜病变（DR）是糖尿病的一种微血管并发症，是工作年龄成人视力丧失的主要原因。然而，由于DR筛查的低依从率和用于眼科检查的昂贵医疗设备，许多DR患者直到DR发展到不可逆阶段（即，视力丧失）。幸运的是，广泛使用的电子健康记录（EHR）数据库为开发用于DR检测的经济高效的机器学习工具提供了前所未有的机会。本文提出了一种多分支时间卷积网络与张量数据完成（MB-TCN-TC）模型来分析纵向EHR收集糖尿病患者的DR预测。实验结果表明，MB-TCN-TC模型不仅能有效地解决EHR数据集中常见的数据不平衡和缺失问题，而且能捕捉纵向病历中医疗变量之间的时间相关性和复杂的相互作用，与现有方法相比具有上级预测性能.具体而言，我们的MB-TCN-TC模型提供的AUROC和AUPRC评分分别为0.949和0.793，与传统TCN模型相比，AUROC评分提高了6.27%，AUPRC评分提高了11.85%，F1评分提高了19.3%。
Diabetic retinopathy (DR), a microvascular complication of diabetes, is the leading cause of vision loss among working-aged adults. However, due to the low compliance rate of DR screening and expensive medical devices for ophthalmic exams, many DR patients did not seek proper medical attention until DR develops to irreversible stages (i.e., vision loss). Fortunately, the widely available electronic health record (EHR) databases provide an unprecedented opportunity to develop cost-effective machine-learning tools for DR detection. This paper proposes a Multi-branching Temporal Convolutional Network with Tensor Data Completion (MB-TCN-TC) model to analyze the longitudinal EHRs collected from diabetic patients for DR prediction. Experimental results demonstrate that the proposed MB-TCN-TC model not only effectively copes with the imbalanced data and missing value issues commonly seen in EHR datasets but also captures the temporal correlation and complicated interactions among medical variables in the longitudinal clinical records, yielding superior prediction performance compared to existing methods. Specifically, our MB-TCN-TC model provides AUROC and AUPRC scores of 0.949 and 0.793 respectively, achieving an improvement of 6.27% on AUROC, 11.85% on AUPRC, and 19.3% on F1 score compared with the traditional TCN model.