2018 n2c2 (Track 2) - Adverse Drug Events and Medication Extraction (2018 n2c2 shared task on adverse drug events and medication extraction in electronic health records)

2018个国家NLP临床挑战的第1条共享任务侧重于确定纵向医疗记录语料库中的哪些患者符合和不符合确定的选择标准。
共有47个团队参加了这项共享任务，共有224名参与者。与会者代表18个国家，各小组提交了109个系统总产出。性能最佳的系统使用基于规则的方法获得了0.91的微F1分数。前10名团队使用基于规则和混合系统来解决问题。

The 1st Shared Task of the 2018 NLP Clinical Challenges focuses on identifying which patients in a longitudinal medical record corpus meet or do not meet predefined selection criteria. A total of 47 teams participated in this shared task, with 224 total participants. The participants represented 18 countries, and the teams collectively submitted 109 system outputs. The top-performing system achieved a micro-F1 score of 0.91 using a rule-based approach. The top 10 teams employed both rule-based and hybrid systems to address this task.

搜集汇总

背景与挑战

背景概述

该数据集是2018年n2c2共享任务（Track 2）的一部分，专注于从电子健康记录中提取药物不良事件和药物信息。任务旨在识别患者是否符合特定选择标准，吸引了47个团队参与，最佳系统采用基于规则方法达到0.91微F1分数。数据集由多个机构于2019年发布，用于临床自然语言处理研究。