TY - JOUR AU - D'Souza, Marcus AU - Van Munster, Caspar E P AU - Dorn, Jonas F AU - Dorier, Alexis AU - Kamm, Christian P AU - Steinheimer, Saskia AU - Dahlke, Frank AU - Uitdehaag, Bernard M J AU - Kappos, Ludwig AU - Johnson, Matthew PY - 2020 DA - 20/5/8 TI -自动编码器作为一种分析运动功能障碍患者视频时维护数据隐私的新方法:概念验证研究JO - J Med Internet Res SP - e16669 VL - 22 IS - 5 KW -自动编码器KW -视频评级KW -机器学习算法KW -深度神经元网络KW -神经状态- edss AB -背景:在慢性神经疾病中，特别是在多发性硬化症(MS)中，运动功能障碍的临床评估对监测患者的疾病至关重要。传统的量表不够灵敏，无法检测出微小的变化。患者表现的视频记录更加准确，并增加了严重程度评级的可靠性。当这些记录被自动化时，可以通过机器学习算法创建定量残疾评估。这些算法的创建涉及非医疗保健专业人员，这对维护数据隐私是一个挑战。然而，自动编码器可以解决这个问题。目的:这项概念验证研究的目的是测试自编码器的编码帧向量是否包含分析ms患者运动表现视频的相关信息。方法:在本研究中，记录了20个患者进行手指到鼻子测试的预评级视频。自动编码器从原始视频中创建编码的帧向量，并再次解码视频。原始视频和解码后的视频被展示给瑞士巴塞尔医学学术中心的10位神经学家。 The neurologists tested whether the 200 videos were human-readable after decoding and rated the severity grade of each original and decoded video according to the Neurostatus-Expanded Disability Status Scale definitions of limb ataxia. Furthermore, the neurologists tested whether ratings were equivalent between the original and decoded videos. Results: In total, 172 of 200 (86.0%) videos were of sufficient quality to be ratable. The intrarater agreement between the original and decoded videos was 0.317 (Cohen weighted kappa). The average difference in the ratings between the original and decoded videos was 0.26, in which the original videos were rated as more severe. The interrater agreement between the original videos was 0.459 and that between the decoded videos was 0.302. The agreement was higher when no deficits or very severe deficits were present. Conclusions: The vast majority of videos (172/200, 86.0%) decoded by the autoencoder contained clinically relevant information and had fair intrarater agreement with the original videos. Autoencoders are a potential method for enabling the use of patient videos while preserving data privacy, especially when non–health-care professionals are involved. SN - 1438-8871 UR - //www.mybigtv.com/2020/5/e16669 UR - https://doi.org/10.2196/16669 UR - http://www.ncbi.nlm.nih.gov/pubmed/32191621 DO - 10.2196/16669 ID - info:doi/10.2196/16669 ER -