arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.09394cs.AIcs.LG
收藏

复习学习:跨医疗机构隐私保护持续学习的真实世界验证

Review learning: Real world validation of privacy preserving continual learning across medical institutions

organization= School of Electrical Engineering, Korea University;organization= Department of Biomedical Engineering, Seoul National University College of Medicine;organization= Department of Medicine, Seoul National University College of Medicine;organization= Department of Applied Statistics, Chung-Ang University;organization= Department of Cardiology, Cardiovascular Center, College of Medicine, Korea University;organization= Department of Endocrinology;Metabolism, School of Medicine, Ajou University;organization= Department of Biomedical Informatics, School of Medicine, Ajou University;organization= Transdisciplinary Department of Medicine \& Advanced Technology, Seoul National University Hospital

Jaesung Yoo, Sunghyuk Choi, Ye Seul Yang, Suhyeon Kim, Jieun Choi, Dongkyeong Lim, Yaeji Lim, Hyung Joon Joo, Dae Jung Kim, Rae Woong Park, Hyeong-Jin Yoon, Kwangsoo Kim

AI总结:

提出低成本持续学习算法RevL,通过生成样本复习旧知识以解决PPDL中的灾难性遗忘问题,在真实跨机构实验中性能优于迁移学习。

摘要:

当深度学习模型在不同数据集上顺序训练时,通常会遗忘从先前数据学到的知识,此问题被称为灾难性遗忘。这损害了模型在多样化数据集上的性能,而这对基于迁移学习(TL)的隐私保护深度学习(PPDL)应用至关重要。为克服此问题,我们引入“复习学习”(RevL),一种在PPDL框架内使用电子健康记录(EHR)进行诊断预测的低成本持续学习算法。RevL从模型生成数据样本,用于复习先前数据集的知识。通过三项二元分类EHR数据,进行了六项模拟机构实验和一项涉及三个医疗机构的真实世界实验来验证RevL。在包含106,508名患者数据的真实世界实验中,RevL的平均全局受试者工作特征曲线下面积为0.710,TL为0.655。这些结果证明了RevL保留先前所学知识的能力及其在真实世界PPDL场景中的有效性。我们的工作建立了基于跨机构模型转移的PPDL研究现实流程,并突出了使用私有EHR数据在真实世界医疗环境中持续学习的实用性。

英文摘要:

When a deep learning model is trained sequentially on different datasets, it often forgets the knowledge learned from previous data, a problem known as catastrophic forgetting. This damages the model's performance on diverse datasets, which is critical in privacy-preserving deep learning (PPDL) applications based on transfer learning (TL). To overcome this, we introduce "review learning" (RevL), a low cost continual learning algorithm for diagnosis prediction using electronic health records (EHR) within a PPDL framework. RevL generates data samples from the model which are used to review knowledge from previous datasets. Six simulated institutional experiments and one real-world experiment involving three medical institutions were conducted to validate RevL, using three binary classification EHR data. In the real-world experiment with data from 106,508 patients, the mean global area under the receiver operating curve was 0.710 for RevL and 0.655 for TL. These results demonstrate RevL's ability to retain previously learned knowledge and its effectiveness in real-world PPDL scenarios. Our work establishes a realistic pipeline for PPDL research based on model transfers across institutions and highlights the practicality of continual learning in real-world medical settings using private EHR data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑