pandalla/datatager_extract_med_information

---
license: apache-2.0
---

<p align="center">
<img src="https://raw.githubusercontent.com/PandaVT/DataTager/main/assert/datatager_logo_right.png" width="650" style="margin-bottom: 0.2;"/>
<p>
<h5 align="center"> If you like our project, please give us a star ⭐ </h2>
<h4 align="center"> [<a href="https://github.com/PandaVT/DataTager">GitHub</a> | <a href="https://datatager.com/">DataTager Home</a>]

# Extract Medical Information Dataset

## Prompt for Training
When training your model with this dataset, prepend the following prompt to each input instance:

```
你需要从用户描述中提取三到六个关键的医疗信息，并以结构化的方式输出，以便快速理解用户的健康状况和相关的疑问。
```

## Description
AnyTaskTune is a publication by the DataTager team. We advocate for rapid training of large models suitable for specific business scenarios through task-specific fine-tuning. We have open-sourced several datasets across various domains such as legal, medical, education, and HR, and this dataset is one of them.

The "Extract Medical Information Dataset" is designed to streamline the process of medical consultations by extracting key medical information from patient inquiries. This dataset enables the automated identification and categorization of important medical details within the dialogues, facilitating quicker and more efficient patient assessment by healthcare professionals.

## Usage

This dataset serves as a critical tool for developing AI systems that assist in automating medical data extraction from patient dialogues. By utilizing this dataset, AI models can be trained to efficiently identify and categorize essential information such as symptoms, diagnosis, and treatment suggestions. This automation aids healthcare professionals in understanding patient conditions more quickly, leading to faster and more accurate medical responses. It is also invaluable for educational purposes, helping medical students learn to quickly identify key information in patient interactions.

## Citation

Please cite this dataset in your work as follows:

```
@misc{ Extract Medical Information Dataset,
author = {DataTager},
title = {Extract Medical Information Dataset},
year = {2024},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\\url{https://github.com/PandaVT/DataTager}}
}
```

许可证：Apache-2.0

<p align="center">
<img src="https://raw.githubusercontent.com/PandaVT/DataTager/main/assert/datatager_logo_right.png" width="650" style="margin-bottom: 0.2;"/>
<p>
<h5 align="center">如果您喜爱本项目，请为我们点亮一颗星⭐</h5>
<h4 align="center">[<a href="https://github.com/PandaVT/DataTager">GitHub</a> | <a href="https://datatager.com/">DataTager 官方主页</a>]

# 医疗信息提取数据集

## 训练提示词
使用此数据集训练模型时，请在每个输入样本前添加如下提示词：

你需要从用户描述中提取三到六个关键的医疗信息，并以结构化的方式输出，以便快速理解用户的健康状况和相关的疑问。

## 数据集说明
AnyTaskTune 是DataTager团队发布的研究成果。我们倡导通过针对特定任务的微调，快速训练适配特定业务场景的大语言模型（Large Language Model）。我们开源了覆盖法律、医疗、教育、人力资源等多个领域的多款数据集，本数据集即为其中之一。

"医疗信息提取数据集"旨在通过从患者咨询内容中提取关键医疗信息，优化问诊流程。该数据集可实现对话中重要医疗细节的自动识别与分类，帮助医护人员更快速高效地完成患者病情评估。

## 使用场景
本数据集是开发AI系统的关键工具，可实现从患者对话中自动提取医疗信息。通过本数据集训练的AI模型，能够高效识别并分类症状、诊断结果、治疗建议等核心医疗信息。该自动化流程可帮助医护人员更快了解患者病情，从而提供更快速、准确的诊疗响应。此外，本数据集在教育场景中同样极具价值，可帮助医学生学习如何在患者交互中快速识别关键信息。

## 引用方式
在您的研究工作中引用本数据集时，请遵循如下格式：

@misc{ Extract Medical Information Dataset,
author = {DataTager},
title = {Extract Medical Information Dataset},
year = {2024},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {url{https://github.com/PandaVT/DataTager}}
}