数据集导航

医疗数据集导航 - 全部数据集（第 166 页）

汇集 20 大疾病系统 5035 个医疗数据集，支持搜索与分类筛选，助力医疗AI研发选型

共 5035 个数据集 · 第 166 / 168 页
数据集名称 系统分类 病种 数据模态 任务类型 描述 来源 原始地址 操作
多模态胸部X光影像-文本临床诊断数据集环境因素所致疾病多模态胸片报告生成胸部疾病医学影像分析，JPG影像+自由文本放射学报告，包含影像解读及诊断信息中国科技资源共享网https://escience.org.cn/metadata/detail访问
华西医院乳腺超声数据集通用医学数据集超声乳腺结节分析四川大学华西医院乳腺外科乳腺超声数据，含报告图像、超声图像、结节模型权重参数和预测代码国家基础学科公共科学数据中心https://nbsdc.cn/general/dataSetHome访问
JMED 京东健康医疗对话数据集医学文本与大模型文本医疗对话源自京东健康互联网医院匿名医患对话，1k份高质量临床记录，覆盖0-90岁和多个专业，21个回答选项 2025京东健康https://hyper.ai/cn/news/39375访问
MIAP Chest X-ray Multi-label Dataset呼吸道疾病X光胸片多标签分类High-resolution chest X-ray images, 15 thoracic conditions multi-label classification, train/val/test splitsKagglehttps://www.kaggle.com/datasets/gouravkai11/miap-dataset/data访问
Augmented Alzheimer MRI Dataset神经系统疾病MRI阿尔茨海默分级Augmented brain MRI dataset for Alzheimer's disease severity classificationKagglehttps://www.kaggle.com/datasets/uraninjo/augmented-alzheimer-mri-dataset访问
Alzheimer's Disease Dataset神经系统疾病阿尔茨海默预测Alzheimer's disease dataset for severity classification and analysisKagglehttps://www.kaggle.com/datasets/rabieelkharoua/alzheimers-disease-dataset访问
CheXpert Plus医学文本与大模型多模态报告生成223,462 unique pairs of radiology reports and chest X-raysStanfordhttps://aimi.stanford.edu/shared-datasets访问
NIH Chest X-ray ChestXray-NIHCC呼吸道疾病X光胸片多标签分类~112,000 chest X-ray images for pneumonia detection and multi-label disease classificationNIHhttps://nihcc.app.box.com/v/ChestXray-NIHCC访问
MIMIC-IV通用医学数据集重症监护研究Comprehensive critical care dataset containing de-identified health records of ICU patients (2008-2019)PhysioNethttps://physionet.org/content/mimiciv/访问
MIMIC-III通用医学数据集重症监护研究De-identified health records of ICU patients, widely used critical care datasetPhysioNethttps://physionet.org/content/mimic-iii-ext-notes/1.0.0/访问
TCGA The Cancer Genome Atlas肿瘤癌症基因组学Genomic, epigenomic, transcriptomic, and proteomic data across 33 cancer types, 11,000+ casesNCIhttps://www.cancer.gov/ccg/research/genome-sequencing/tcga访问
gnomAD Genome Aggregation Database通用医学数据集变异分析Large-scale variant database with 140,000+ exomes & genomesBroad Institutehttps://gnomad.broadinstitute.org/访问
PTB-XL ECG心血管系统疾病心律失常检测Large-scale 12-lead ECG dataset with 21,000+ recordings for arrhythmia detectionPhysioNethttps://physionet.org/content/ptb-xl/1.0.0/访问
CORD-19 COVID-19 Literature呼吸道疾病文本文献检索Scientific literature corpus with 1M+ COVID-19 research papersAllen AIhttps://www.kaggle.com/datasets/allen-institute-for-ai/CORD-19-research-challenge访问
BioASQ Biomedical QA医学文本与大模型文本生物医学问答Biomedical question answering and semantic indexing datasetBioASQhttp://bioasq.org/访问
DATASUS TABNET Brazil Health通用医学数据集公共卫生Official health information system of the Brazilian Ministry of HealthBrazil MoHhttps://datasus.saude.gov.br/informacoes-de-saude-tabnet/访问
Grand Challenge Biomedical Imaging通用医学数据集多模态生物医学影像挑战Platform for end-to-end development of machine learning solutions in biomedical imaging, hosts many challengesGrand Challengehttps://grand-challenge.org/访问
EchoNext心血管系统疾病结构性心脏病检测100K 12-lead ECGs paired with echocardiogram-confirmed structural heart disease labels, Columbia University 2026PhysioNethttps://physionet.org/content/?types=0&page=2访问
MEETI Multimodal ECG Text Image心血管系统疾病多模态心电图解读MIMIC-IV-Ext ECG-Text-Image, large-scale dataset synchronizing raw ECG waveforms, high-resolution plotted images, and tePhysioNethttps://physionet.org/content/访问
Neurotech EEG Ambulatory心血管系统疾病动态脑电23,607 records, 4,914 patients, ambulatory EEG with ECG channel, 212,186 hours 2026BDSPhttps://github.com/aaekay/ecg-datasets访问
BBBD Biobehavioral Brain Dataset心血管系统疾病多模态脑电眼动5 experiments, 178 participants, EEG + ECG + eye tracking during educational videos 2026Projecthttps://github.com/aaekay/ecg-datasets访问
ARGO Post-ischemic Ventricular Tachycardia心血管系统疾病室性心动过速Annotated dataset of post-ischemic ventricular tachycardia electrograms 2026PhysioNethttps://www.physionet.org/content/argo/1.0.0/访问
NEUROSKY-EPI神经系统疾病癫痫分层First open dataset of single-channel consumer-grade EEG for epilepsy, collected in South Asian clinic with rich metadataarXivhttps://arxiv.org/pdf/2511.01879v1访问
BDSP Cardiac Arrest EEG Database心血管系统疾病心脏骤停后脑电Multicenter clinical and EEG Database, 1,020 patients, 50,000+ hours continuous EEG, comatose after cardiac arrest, 7 hoBDSPhttps://bdsp.io/data/访问
IKEM ECG Dataset心血管系统疾病心电图诊断12-lead ECG, 30,290 patients, 98,130 records, 10s 500Hz HDF5, Institute for Clinical and Experimental Medicine Prague, CZenodohttps://github.com/vlbthambawita/ECGDatasets/访问
GenECG Synthetic ECG心血管系统疾病合成心电图High-fidelity synthetic image-based ECG dataset, 21,799 ECG images paired with imperfection-free images and signal dataHugging Facehttps://huggingface.co/datasets/edcci/GenECG访问
Patient Records 100K 15 Conditions内分泌系统疾病多病种分析100K patients with 15 conditions including obesity, hyperlipidemia, CKD, type 2 diabetes, osteoarthritis, asthma 2026Kagglehttps://www.kaggle.com/datasets/sergionefedov/patient-records-100k-patients-15-conditions/data访问
SmartThyro-MV Multi-Visit Thyroid Cancer内分泌系统疾病多模态甲状腺癌监测80,000 patients, multi-visit longitudinal dataset for thyroid cancer early diagnosis and progression monitoring, wearablKagglehttps://www.kaggle.com/datasets/datasetengineer/multi-visit-thyroid-cancer-monitoring-dataset-shd访问
Diabetes Risk Prediction内分泌系统疾病糖尿病风险预测Diabetes risk prediction dataset with clinical featuresKagglehttps://www.kaggle.com/datasets?tags=4202-Healthcare访问
CUPCase Clinically Uncommon Patient Cases医学文本与大模型文本罕见病诊断3,562 real-world case reports from BMC, rare diseases and uncommon presentations, diagnoses in open-ended and multiple-carXivhttps://arxiv.org/pdf/2503.06204v1访问