SYMPCODER
收藏资源简介:
SYMPCODER数据集是由史蒂文斯理工学院的研究人员创建的,基于美国疾病控制与预防中心(CDC)和食品与药物管理局(FDA)管理的疫苗不良事件报告系统(VAERS)报告。该数据集包括三个变体,分别为SYMPCODER-Full、SYMPCODER-Common-50和SYMPCODER-Rare-50,涵盖了常见和罕见不良事件的报告。数据集经过人工注释,提供了症状提及和与疫苗不良事件相关的MedDRA编码的详细标注,旨在为医疗症状编码的研究和模型训练提供支持。
The SYMPCODER dataset was developed by researchers at the Stevens Institute of Technology, based on reports from the Vaccine Adverse Event Reporting System (VAERS) administered by the U.S. Centers for Disease Control and Prevention (CDC) and the U.S. Food and Drug Administration (FDA). The dataset includes three variants: SYMPCODER-Full, SYMPCODER-Common-50, and SYMPCODER-Rare-50, covering reports of both common and rare adverse events. The dataset has undergone manual annotation, providing detailed annotations of symptom mentions and Medical Dictionary for Regulatory Activities (MedDRA) codes associated with vaccine adverse events, aiming to support research and model training for medical symptom coding.

- 1Task as Context Prompting for Accurate Medical Symptom Coding Using Large Language Models史蒂文斯理工学院 · 2025年



