合成神经外科数据集
由GPT-4o生成的合成神经外科表格数据，含139例老年患者记录，可放大样本量，用于预测神经外科结果。
基本信息
资源简介
合成神经外科数据集
【数据集背景】
本数据集源站标题为《aabarr/Synthetic-Neurosurgical-Data》。源站首次发布：2025-02-13。
【数据内容】
源站原始描述：Synthetic neurosurgical datasets generated with GPT-4o and CTGAN # Synthetic Neurosurgical Data This repository is related to the study: Zero-Shot Generation of Synthetic Neurosurgical Data with Large Language Models ( Provided are the synthetic datasets generated with GPT-4o and CTGAN These datasets are generated based on the following real-world neurosurgical data: # Datasets The collection includes 13 datasets, including the following: - Ten datasets (n = 139) generated with GPT-4o labeled: L…
【适用方向】
结构化表格数据可直接用于统计建模、特征工程与队列分析。
【获取与许可】
源站页面：https://github.com/aabarr/Synthetic-Neurosurgical-Data
【使用注意】
· 源站最后修改于 2025-02-14，引用时请注意版本时效。
下载信息
注册下载
需要注册 Kaggle 账号并登录后下载，适合需要跟踪下载记录和使用 API 的用户。
暂未开放公开下载
无需注册即可直接获取公开样本或文档，适合快速预览和评估数据集质量。
免登录当前数据集主要来源为 Kaggle 公开托管，完整影像包建议通过原始链接或 Kaggle API 获取。
使用方式
数据集获取
git clone https://github.com/aabarr/Synthetic-Neurosurgical-Data.git
curl -L -o repo.zip https://github.com/aabarr/Synthetic-Neurosurgical-Data/archive/refs/heads/main.zip
unzip repo.zip
源站 README 摘录（使用方式）
Synthetic Neurosurgical Data
This repository is related to the study: Zero-Shot Generation of Synthetic Neurosurgical Data with Large Language Models (https://doi.org/10.48550/arXiv.2502.09566). Provided are the synthetic datasets generated with GPT-4o and CTGAN
These datasets are generated based on the following real-world neurosurgical data: https://zenodo.org/records/5879095
Datasets
The collection includes 13 datasets, including the following:
- Ten datasets (n = 139) generated with GPT-4o labeled: LLM_gen#_139.xlsx
- One dataset (n = 1390) generated with GPT-4o labeled: LLM_1390.xlsx
- One dataset (n = 139) generated with CTGAN labeled: CTGAN_139.xlsx
- One dataset (n = 1390) generated with CTGAN labeled: CTGAN_1390.xlsx
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))
需要用于商业化训练或医疗器械注册（NMPA/FDA）？
公开数据往往缺乏完整的病理回证与专家标注。千方医数集依托陕川双基地与超十家三甲医院直连，提供完全合规、去标识化、支持注册级质控的专病数据集交易服务。
