严重低血糖多模态融合数据集
用于识别1型糖尿病成人严重低血糖的多模态(表格、文本、时间序列)融合数据集,含原始和预处理数据,支持可解释AI研究。

基本信息
资源简介
严重低血糖多模态融合数据集
【数据集背景】
本数据集源站标题为《Multimodal-fusion-severe-hypo-data》。源站首次发布:2024-10-03。
【数据内容】
源站原始描述:Datasets (raw and preprocessed) for reproducibility results of the paper "Interpretable and multimodal fusion methods to identify severe hypoglycemia in adults with T1D". We also added the reports and results obtained in the multiple experiments. The file "Multimodal-fusion-severe-hypo-data" contains the last version and results. This study aims to identify severe hypoglycemia (SH) in Type 1 diabetes patients, leveraging machine learning and explainable artificial intelligence (XAI) techniques.…
【数据结构与技术规格】
文件数 3 个,合计 173.02 MB。数据集 DOI:10.6084/m9.figshare.25136942.v2。
【主题与分类】
源站学科分类:Other biomedical and clinical sciences not elsewhere classified。主题标签:hypoglycemia、severe hypoglycemia、multimodal fusion、type 1 diabetes mellitus、representation learning、CGM data、survey data。
【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://figshare.com/articles/dataset/Multimodal-fusion-severe-hypo-data/25136942
使用许可:CC BY 4.0(https://creativecommons.org/licenses/by/4.0/)。
规范引用:Chushig-Muzo, David; Chushig-Muzo, David; Lara-Abelenda, Francisco J.; Soguero-Ruiz, Cristina (2024). Multimodal-fusion-severe-hypo-data. figshare. Dataset
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:Multimodal-fusion-severe-hypo-data
- DOI:10.6084/m9.figshare.25136942.v2
- 发布日期:2024-10-03
- 文件数:3 个
- 文件总体积:173.02 MB
- 源站页面:https://figshare.com/articles/dataset/Multimodal-fusion-severe-hypo-data/25136942
命令行下载
curl -L -o "severe_hypo_fusion_data.zip" "https://ndownloader.figshare.com/files/44380793"
curl -L -o "severe_hypo_fusion_data.zip" "https://ndownloader.figshare.com/files/44380799"
curl -L -o "Multimodal-fusion-severe-hypo-data.zip" "https://ndownloader.figshare.com/files/49582173"
文件清单
severe_hypo_fusion_data.zip(63.23 MB)severe_hypo_fusion_data.zip(63.23 MB)Multimodal-fusion-severe-hypo-data.zip(46.57 MB)
文件总体积 173.02 MB(源站 API 实测)。
数据说明
Datasets (raw and preprocessed) for reproducibility results of the paper “Interpretable and multimodal fusion methods to identify severe hypoglycemia in adults with T1D”. We also added the reports and results obtained in the multiple experiments. The file “Multimodal-fusion-severe-hypo-data” contains the last version and results.
This study aims to identify severe hypoglycemia (SH) in Type 1 diabetes patients, leveraging machine learning and explainable artificial intelligence (XAI) techniques. Using clinical data from the Jaeb Center for Health Research, including tabular, text, and time series data, multimodal fusion models outperform single-modality models by 5.8%, achieving an AUCROC of 0.779. XAI reveals a higher incidence of cardiovascular diseases and associated drugs in individuals with SH, along with a correlation between consistently low blood glucose levels and SH risk. These findings hold promise for early detection and intervention, benefiting both clinicians and patients.
许可
CC BY 4.0
引用
学术使用请引用 DOI 10.6084/m9.figshare.25136942.v2(source: https://figshare.com/articles/dataset/Multimodal-fusion-severe-hypo-data/25136942)。
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。




