Soroush Ali, Diamond Courtney J, Zylberberg Haley M, May Benjamin, Tatonetti Nicholas, Abrams Julian A, Weng Chunhua
Division of Digestive and Liver Diseases, Department of Medicine, Columbia University Irving Medical Center, New York, NY, USA.
Department of Biomedical Informatics, Columbia University Irving Medical Center, New York, NY, USA.
medRxiv. 2023 Jul 13:2023.07.11.23292529. doi: 10.1101/2023.07.11.23292529.
To develop an automated natural language processing (NLP) method for extracting high-fidelity Barrett's Esophagus (BE) endoscopic surveillance and treatment data from the electronic health record (EHR).
Patients who underwent BE-related endoscopies between 2016 and 2020 at a single medical center were randomly assigned to a development or validation set. Those not aged 40 to 80 and those without confirmed BE were excluded. For each patient, free text pathology reports and structured procedure data were obtained. Gastroenterologists assigned ground truth labels. An NLP method leveraging MetaMap Lite generated endoscopy-level diagnosis and treatment data. Performance metrics were assessed for this data. The NLP methodology was then adapted to label key endoscopic eradication therapy (EET)-related endoscopy events and thereby facilitate calculation of patient-level pre-EET diagnosis, endotherapy time, and time to CE-IM.
99 patients (377 endoscopies) and 115 patients (399 endoscopies) were included in the development and validation sets respectively. When assigning high-fidelity labels to the validation set, NLP achieved high performance (recall: 0.976, precision: 0.970, accuracy: 0.985, and F1-score: 0.972). 77 patients initiated EET and underwent 554 endoscopies. Key EET-related clinical event labels had high accuracy (EET start: 0.974, CE-D: 1.00, and CE-IM: 1.00), facilitating extraction of pre-treatment diagnosis, endotherapy time, and time to CE-IM.
High-fidelity BE endoscopic surveillance and treatment data can be extracted from routine EHR data using our automated, transparent NLP method. This method produces high-level clinical datasets for clinical research and quality metric assessment.
开发一种自动化自然语言处理（NLP）方法，用于从电子健康记录（EHR）中提取高保真的巴雷特食管（BE）内镜监测和治疗数据。
2016年至2020年在单一医疗中心接受与BE相关内镜检查的患者被随机分配到开发集或验证集。排除年龄不在40至80岁之间以及未确诊为BE的患者。为每位患者获取了自由文本病理报告和结构化程序数据。胃肠病学家分配了真实标签。一种利用MetaMap Lite的NLP方法生成了内镜检查水平的诊断和治疗数据。对这些数据评估了性能指标。然后调整NLP方法以标记关键的内镜根除治疗（EET）相关内镜检查事件，从而便于计算患者水平的EET前诊断、内镜治疗时间和达到完全内镜切除（CE-IM）的时间。
开发集和验证集分别纳入了99例患者（377次内镜检查）和115例患者（399次内镜检查）。当为验证集分配高保真标签时，NLP表现出高性能（召回率：0.976，精确率：0.970，准确率：0.985，F1分数：0.972）。77例患者开始接受EET并接受了554次内镜检查。关键的EET相关临床事件标签具有高准确率（EET开始：0.974，CE-D：1.00，CE-IM：1.00），便于提取治疗前诊断、内镜治疗时间和达到CE-IM的时间。
使用我们自动化、透明的NLP方法可以从常规EHR数据中提取高保真的BE内镜监测和治疗数据。该方法可为临床研究和质量指标评估生成高级临床数据集。
