基于图像编码的电子病历和Transformer融合的妊娠期糖尿病预测
包含表格和图像编码电子健康记录的妊娠期糖尿病预测数据集,用于多模态融合分类。

基本信息
资源简介
基于图像编码的电子病历和Transformer融合的妊娠期糖尿病预测
【一句话概览】
本数据集是 figshare 公开的多模态数据集,收录 2 个文件、合计 62.70 KB,主题涵盖 Gestational diabetes mellitus、transformer、image encoding、cross-modal feature fusion、end-to-end prediction,可用于跨模态对齐与融合建模研究,CC BY 4.0 许可开放获取。
【数据集背景】
本数据集源站标题为《Gestational diabetes mellitus prediction using image-encoded electronic medical records and Transformer-based fusion》。配套论文《Gestational diabetes mellitus prediction using image-encoded electronic medical records and Transformer-based fusion》发表于 Computer Methods in Biomechanics and Biomedical Engineering(2025),DOI:10.1080/10255842.2025.2573868。源站首次发布:2025-12-13。
【数据内容】
源站原始描述:Accurate prediction of gestational diabetes mellitus (GDM) is critical for improving maternal and fetal outcomes. This study develops a Transformer-based multimodal fusion model that integrates tabular clinical features and image-encoded electronic health records (EHRs), aiming for accurate end-to-end classification of GDM. Preprocessed EHRs were transformed into grayscale, RGB, and heatmap, with visual features were extracted by a Vision Transformer and tabular features by an MLP. A modality-aw…
中文译文(机器翻译,仅供快速理解,请以原文为准):妊娠期糖尿病(GDM)的准确预测对于改善母婴结局至关重要。本研究开发了一种基于Transformer的多模态融合模型,整合表格型临床特征与图像编码的电子健康记录(EHR),旨在实现GDM的准确端到端分类。预处理后的EHR被转换为灰度图、RGB图和热力图,其中视觉特征由Vision Transformer提取,表格特征由MLP提取。一种模态感知注意力机制增强了跨模态融合。在两个公开数据集上评估时,相较于最强的单模态模型,准确率增益分别达到3.95%和0.38%。
【数据结构与技术规格】
文件数 2 个,合计 62.70 KB。gcmb_a_2573868_sm4423.docx:application/vnd.openxmlformats-officedocument.wordprocessingml.document,34.66 KB。gcmb_a_2573868_sm4422.docx:application/vnd.openxmlformats-officedocument.wordprocessingml.document,28.04 KB。数据集 DOI:10.6084/m9.figshare.30876684.v1。
【主题与分类】
源站学科分类:Space Science、Medicine、Chemical Sciences not elsewhere classified、Biological Sciences not elsewhere classified、Information Systems not elsewhere classified。主题标签:Gestational diabetes mellitus、transformer、image encoding、cross-modal feature fusion、end-to-end prediction。
【适用方向】
多模态数据适合跨模态对齐、融合建模与联合表征学习方向的研究。
【获取与许可】
源站页面:https://tandf.figshare.com/articles/dataset/Gestational_diabetes_mellitus_prediction_using_image-encoded_electronic_medical_records_and_Transformer-based_fusion/30876684
使用许可:CC BY 4.0(https://creativecommons.org/licenses/by/4.0/)。
规范引用:Gestational diabetes mellitus prediction using image-encoded electronic medical records and Transformer-based fusion. Taylor & Francis. Shan, Ying; Yu, Junsheng; Huang, Zhuya
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。
免登录有偿下载
公开数据集受托下载与技术交付服务。
提供高速下载与技术交付服务(收技术服务费,非数据销售)
暂未开放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(Figshare)
- 源站标题:Gestational diabetes mellitus prediction using image-encoded electronic medical records and Transformer-based fusion
- DOI:10.6084/m9.figshare.30876684.v1
- 发布日期:2025-12-13
- 文件数:2 个
- 文件总体积:62.70 KB
- 源站页面:https://tandf.figshare.com/articles/dataset/Gestational_diabetes_mellitus_prediction_using_image-encoded_electronic_medical_records_and_Transformer-based_fusion/30876684
命令行下载
curl -L -o "gcmb_a_2573868_sm4423.docx" "https://ndownloader.figshare.com/files/60335589"
curl -L -o "gcmb_a_2573868_sm4422.docx" "https://ndownloader.figshare.com/files/60335592"
文件清单
gcmb_a_2573868_sm4423.docx(34.66 KB)gcmb_a_2573868_sm4422.docx(28.04 KB)
文件总体积 62.70 KB(源站 API 实测)。
数据加载示例(图像类)
from PIL import Image
import glob, os
files = (glob.glob(os.path.join(path, "**", "*.png"), recursive=True)
+ glob.glob(os.path.join(path, "**", "*.jpg"), recursive=True)
+ glob.glob(os.path.join(path, "**", "*.tif"), recursive=True))
print("图像文件数:", len(files))
img = Image.open(files[0]); print("尺寸/模式:", img.size, img.mode)
# torchvision Dataset 方式:
# from torchvision import datasets
# ds = datasets.ImageFolder(path) # 要求 子目录=类别
目录组织与标注格式以源站说明和下载后实际文件为准。
数据说明
Accurate prediction of gestational diabetes mellitus (GDM) is critical for improving maternal and fetal outcomes. This study develops a Transformer-based multimodal fusion model that integrates tabular clinical features and image-encoded electronic health records (EHRs), aiming for accurate end-to-end classification of GDM. Preprocessed EHRs were transformed into grayscale, RGB, and heatmap, with visual features were extracted by a Vision Transformer and tabular features by an MLP. A modality-aware attention mechanism enhances cross-modal fusion. Evaluated on two public datasets, performance gains over the strongest single-modality models reached 3.95% and 0.38% in accuracy.
许可
CC BY 4.0
引用
学术使用请引用 DOI 10.6084/m9.figshare.30876684.v1(source: https://tandf.figshare.com/articles/dataset/Gestational_diabetes_mellitus_prediction_using_image-encoded_electronic_medical_records_and_Transformer-based_fusion/30876684)。
数据缺失?
依托陕西、四川两大基地,我们与超过十家三甲医院建立直接合作关系,覆盖合规授权、采集治理、专业标注、数据交付的全流程,为AI医疗团队提供即拿即用的高质量临床数据。
⚡️ 需要数据支持或标注服务?立即联系我们获取专业方案。




