SanaeLaRose/FAERS-NLP
收藏Hugging Face2026-01-13 更新2026-03-29 收录
下载链接:
https://hf-mirror.com/datasets/SanaeLaRose/FAERS-NLP
下载链接
链接失效反馈官方服务:
资源简介:
---
language: en
tags:
- clinical
- adverse-event
- faers
- nlp
- drug
- disease
license: cc-by-nc-4.0
dataset_name: FAERS-NLP
---
# FAERS-NLP
**Version:** 1.0
**Author:** sixuexing
**GitHub:** [FAERS-NLP Repository](https://github.com/xingsixue123/FAERS-NLP.git)
---
## Dataset Summary
FAERS-NLP is a cleaned and processed version of the **FDA Adverse Event Reporting System (FAERS)**, formatted for **natural language retrieval** and **drug–adverse effect–disease relation extraction**.
Each record corresponds to a single adverse event report, including structured and semi-structured fields suitable for NLP tasks.
---
## Dataset Structure
Each CSV row contains the following columns:
| Column | Description |
|--------|-------------|
| `safetyreportid` | Unique ID of the safety report |
| `safetyreportversion` | Version number of the report |
| `occurcountry` | Country where the event occurred |
| `reporttype` | Type of report (e.g., Study report, Spontaneous report) |
| `serious` | Whether the event is serious (`Yes`/`No`) |
| `serious_specific` | Specific seriousness criteria (e.g., Hospitalization) |
| `receivedate` | Date FDA received the report (YYYYMMDD) |
| `transmissiondate` | Date report was transmitted (YYYYMMDD) |
| `companynumb` | Company identifier |
| `sendertype` | Type of sender (Regulatory Authority, Manufacturer, etc.) |
| `senderorganization` | Name of reporting organization |
| `patientonsetage` | Patient age at onset |
| `patientonsetageunit` | Unit of age (Year, Month, etc.) |
| `patientsex` | Patient sex |
| `reactions` | Adverse reactions reported (with recovery status) |
| `drugs_specific` | Full description of drugs in report |
| `drugnames` | List of drug names |
| `activesubstancenames` | List of active substances |
| `drugindications` | Indications for the drugs |
---
---
**FAERS source:**
U.S. Food and Drug Administration. *FDA Adverse Event Reporting System (FAERS) Public Dashboard*. [https://fis.fda.gov/extensions/FPD-QDE-FAERS/FPD-QDE-FAERS.html](https://fis.fda.gov/extensions/FPD-QDE-FAERS/FPD-QDE-FAERS.html)
**This dataset:**
sixuexing. *FAERS-NLP: A processed dataset for drug-adverse event-disease relation extraction*. Hugging Face Dataset. Version 1.0. [https://huggingface.co/datasets/sixuexing/FAERS-NLP](https://huggingface.co/datasets/sixuexing/FAERS-NLP)
You can cite in BibTeX format:
```bibtex
@misc{faers-nlp,
author = {Xing, Sixue},
title = {FAERS-NLP: A processed dataset for drug-adverse event-disease relation extraction},
year = {2025},
howpublished = {\url{https://huggingface.co/datasets/sixuexing/FAERS-NLP}},
note = {Derived from FDA FAERS public data: \url{https://fis.fda.gov/extensions/FPD-QDE-FAERS/FPD-QDE-FAERS.html}}
}
提供机构:
SanaeLaRose



