Colonoscopy is used for colorectal cancer (CRC) screening. Extracting details of the colonoscopy findings from free text in electronic health records (EHRs) can be used to determine patient risk for CRC and colorectal screening strategies. We developed and evaluated the accuracy of a deep learning model framework to extract information for the clinical decision support system to interpret relevant free-text reports, including indications, pathology, and findings notes. The Bio-Bi-LSTM-CRF framework was developed using Bidirectional Long Short-term Memory (Bi-LSTM) and Conditional Random Fields (CRF) to extract several clinical features from these free-text reports including indications for the colonoscopy, findings during the colonoscopy, and pathology of resected material. We trained the Bio-Bi-LSTM-CRF and existing Bi-LSTM-CRF models on 80% of 4,000 manually annotated notes from 3,867 patients. These clinical notes were from a group of patients over 40 years of age enrolled in four Veterans Affairs Medical Centers. A total of 10% of the remaining annotated notes were used to train hyperparameter and the remaining 10% were used to evaluate the accuracy of our model Bio-Bi-LSTM-CRF and compare to Bi-LSTM-CRF.
翻译:Colonoscopy用于直肠癌检查,从电子健康记录(EHRs)的免费文本中摘取结肠镜检查结果的详情,可用于确定患者对《儿童权利公约》和直肠筛查战略的风险;我们开发并评价了深入学习示范框架的准确性,以便为临床决策支持系统提取信息,以解释相关的自由文本报告,包括指示、病理和结果说明;Bio-Bi-LSTM-CRF框架是利用双向长期短期内存(Bi-LSTM)和有条件随机字段(CRF)开发的,以从这些自由文本报告中提取若干临床特征,包括结肠镜检查、结肠镜检查期间的发现和再切除材料的病理学;我们培训了Bio-Bi-BI-LSTM-CRF和现有的Bi-LSTM-CRF模型,在3,867名病人的4 000份人工附加说明说明中80%是利用BI-LSTM-RS-MS-RS-RS-RS-S-C 其余的精确度样本和BIRF-RM-RF-RM-RM-R-R-R-R-R-R-C-Ris-C-C-C-Ris-C-C-C-C-C-C-C-C-C-C-C-C-C-C-SUDRisal-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-C-SUruptraqRVDRVDRVDRVDRVDRVDRVDRVDRVDR-C-C-SDR-R-S-R-R-R-R-R-R-C-R-C-C-C-C-C-C-