基于BERT-TextCNN的临床试验疾病亚型识别研究  

Identifying Subtypes of Clinical Trial Diseases with BERT-TextCNN

作　　者：杨林[1] 黄晓硕 王嘉阳 丁玲玲 李子孝[2,3] 李姣[1] Yang Lin;Huang Xiaoshuo;Wang Jiayang;Ding Lingling;Li Zixiao;Li Jiao(Institute of Medical Information/Medical Library,Chinese Academy of Medical Science&Peking Union Medical College,Beijing 100020,China;China National Clinical Research Center for Neurological Diseases,Beijing Tiantan Hospital,Capital Medical University,Beijing 100070,China;Department of Neurology,Beijing Tiantan Hospital,Capital Medical University,Beijing 100070,China)

机构地区：[1]中国医学科学院北京协和医学院医学信息研究所/图书馆,北京100020 [2]首都医科大学附属北京天坛医院国家神经系统疾病临床研究中心,北京100070 [3]首都医科大学附属北京天坛医院神经内科,北京100070

出　　处：《数据分析与知识发现》2022年第4期69-81,共13页Data Analysis and Knowledge Discovery

基　　金：北京市自然科学基金重点研究专题(项目编号:Z200016)的研究成果之一。

摘　　要：【目的】面向复杂疾病临床试验招募的需求,提出一种基于BERT-TextCNN的临床试验疾病亚型识别方法,辅助识别复杂疾病特定亚型的受试人群。【方法】将临床试验疾病亚型识别问题转化为单标签分类问题,应用基于BERT-TextCNN的单标签分类模型进行分类,以卒中为例在临床试验数据集(ClinicalTrials.gov)上开展实验验证。【结果】基于LP法的BERT-TextCNN模型性能最佳,加权宏平均F1值为0.9053,可以有效判定一项卒中临床试验可纳入卒中亚型受试者情况。【局限】缺乏在其他单病种上的可行性研究,以及在外部数据集上的有效性验证。【结论】本文方法可以有效解决从纳入标准中准确识别复杂疾病亚型的问题。[Objective]This study develops a method to identify disease subtypes based on BERT-TextCNN,which could facilitate cohort selection for clinical trials.[Methods]We transformed the disease subtype identification into a single-label classification task based on BERT-TextCNN.Then,we examined our new model with clinical trials data for strokes from ClinicalTrials.gov.[Results]The BERT-TextCNN based on the LP method yielded the best weighted macro-average F1 value of 0.9053.It identified stroke subtypes for participants of a clinical trial.[Limitations]More research is needed to evaluate our model with other diseases and data sets.[Conclusions]The proposed method could be an effective approach to identify complex disease subtypes.

关 键 词：临床试验 文本分类 BERT-TextCNN 卒中 疾病亚型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]