数据集获取

git clone https://github.com/ZhaoyueSun/PHEE.git

curl -L -o repo.zip https://github.com/ZhaoyueSun/PHEE/archive/refs/heads/master.zip
unzip repo.zip

源站 README 摘录（使用方式）

UPDATES

Data Updates: Version 2.0 of PHEE (PHEE V2.0)

In the original dataset, we observed particularly low levels of annotation inconsistency for the ‘subject.disorder,’ ‘time_elapsed,’ and ‘duration’ arguments. To address this, we implemented an automatic revision for the ‘subject.disorder’ annotation and employed annotators to manually correct the ‘time_elapsed’ and ‘duration’ annotations. For the ‘subject.disorder’ correction, if a ‘treatment.disorder’ was present in the ‘subject’ argument but not annotated as ‘subject.disorder,’ we added it to the annotation. For ‘time_elapsed’ and ‘duration’ corrections, we provided detailed guidelines to the annotators to ensure consistent annotations. We evaluated annotation consistency using the EM_F1 score. The average EM_F1 scores for the ‘time_elapsed’ and ‘duration’ annotations were 75.3%.
The updated data can be downloaded at Leveraging ChatGPT in Pharmacovigilance Event Extraction: An Empirical Study Git Repo

New Paper: DrugWatch: A Comprehensive Multi-Source Data Visualisation Platform for Drug Safety Information

The paper introduces “DrugWatch”, an easy-to-use and interactive multi-source information visualisation platform for drug safety study. It allows users to understand common side effects of drugs and their statistical information, flexibly retrieve relevant medical reports, or annotate their own medical texts with our automated annotation tool. Supported by NLP technology and enriched with interactive visual components, we are committed to providing researchers and practitioners with a one-stop information analysis, retrieval, and annotation service. The demo system is online.

New Paper: Leveraging ChatGPT in Pharmacovigilance Event Extraction: An Empirical Study

The paper explores the potential of ChatGPT in pharmacovigilance event extraction. The research involves extensive experiments using various prompts and strategies to assess ChatGPT’'s performance. The paper also investigates using ChatGPT for data augmentation and filtering strategies to achieve more stable results.

---

Introduction

Data and Code for [``

数据加载示例（表格/文本类）

import pandas as pd, glob, os

files = (glob.glob(os.path.join(path, "**", "*.csv"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tsv"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.xlsx"), recursive=True))
print("数据文件:", files)
df = pd.read_csv(files[0])
print(df.shape); print(df.columns.tolist()); print(df.head(3))

完整仓库：github.com/ZhaoyueSun/PHEE