Amalgamation of cloud-based colonoscopy videos with patient-level metadata to facilitate large-scale machine learning.
Amalgamation of cloud-based colonoscopy videos with patient-level metadata to facilitate large-scale machine learning.
复制标题
将基于云的结肠镜检查视频与患者级元数据合并，以促进大规模的机器学习。
DOI：
10.1055/a-1326-1289
复制
发表时间：
2021-03
影响因子：
2.6
通讯作者：
Etemadi M
中科院分区：
文献类型：
--
作者：
Keswani RN;Byrd D;Garcia Vicente F;Heller JA;Klug M;Mazumder NR;Wood J;Yang AD;Etemadi M
背景和研究目的全长内窥镜手术的存储越来越受欢迎。 为了促进专注于临床结果的大规模机器学习（ML），这些视频必须与电子健康记录（EHR）中的患者级数据合并。我们的目标是提出一种将患者级EHR数据与云存储的结肠镜视频准确连接的方法。 方法本研究在一个学术医学中心进行。 大多数手术视频自动上传到云服务器，但仅通过手术时间和手术室进行识别。我们开发并测试了一种算法，该算法根据手术时间和房间将记录的视频与EHR中的相应检查相匹配，随后提取感兴趣的帧。 在研究期间进行的28，611次结肠镜检查中，20，420名独特患者（54.2%男性，中位年龄58岁）的21，170个结肠镜视频与EHR数据匹配。 在100个随机抽样的视频中，所有视频都手动确认了适当的匹配。总的来说，这些视频代表了由50名内窥镜医生进行的489，721分钟的结肠镜检查（每位内窥镜医生平均214次结肠镜检查）。最常见的手术适应症是息肉筛查（47.3%）、监测（28.9%）和炎症性肠病（9.4%）。 从这些视频中，我们提取了手术亮点（通过图像捕获识别;每次结肠镜检查平均8.5）和周围帧。 结论我们报告了以高度准确的方式将存储有有限标识符的大型内窥镜视频数据库成功合并为丰富的患者级数据。 该技术有助于基于相关患者结果开发ML算法。
Background and study aims Storage of full-length endoscopic procedures is becoming increasingly popular. To facilitate large-scale machine learning (ML) focused on clinical outcomes, these videos must be merged with the patient-level data in the electronic health record (EHR). Our aim was to present a method of accurately linking patient-level EHR data with cloud stored colonoscopy videos. Methods This study was conducted at a single academic medical center. Most procedure videos are automatically uploaded to the cloud server but are identified only by procedure time and procedure room. We developed and then tested an algorithm to match recorded videos with corresponding exams in the EHR based upon procedure time and room and subsequently extract frames of interest. Results Among 28,611 total colonoscopies performed over the study period, 21,170 colonoscopy videos in 20,420 unique patients (54.2 % male, median age 58) were matched to EHR data. Of 100 randomly sampled videos, appropriate matching was manually confirmed in all. In total, these videos represented 489,721 minutes of colonoscopy performed by 50 endoscopists (median 214 colonoscopies per endoscopist). The most common procedure indications were polyp screening (47.3 %), surveillance (28.9 %) and inflammatory bowel disease (9.4 %). From these videos, we extracted procedure highlights (identified by image capture; mean 8.5 per colonoscopy) and surrounding frames. Conclusions We report the successful merging of a large database of endoscopy videos stored with limited identifiers to rich patient-level data in a highly accurate manner. This technique facilitates the development of ML algorithms based upon relevant patient outcomes.
登录
查看更多内容
影响因子：
24.5
作者：
Byrne MF;Chapados N;Soudan F;Oertel C;Linares Pérez M;Kelly R;Iqbal N;Chandelier F;Rex DK
通讯作者：
Rex DK
影响因子：
13.8
作者：
Stidham, Ryan W.;Liu, Wenshuo;Waljee, Akbar K.
通讯作者：
Waljee, Akbar K.
影响因子：
2.7
作者：
Liu, Wen-Na;Zhang, Yang-Yang;Huang, Jin
通讯作者：
Huang, Jin
影响因子：
4.6
作者：
Yamada, Masayoshi;Saito, Yutaka;Hamamoto, Ryuji
通讯作者：
Hamamoto, Ryuji
影响因子：
2.9
作者：
Becq, Aymeric;Chandnani, Madhuri;Berzin, Tyler M.
通讯作者：
Berzin, Tyler M.