医疗数据集导航 - 全部数据集(第 161 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 161 / 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
CORD-19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
Medical Transcriptions医学文本与大模型文本医疗文本Medical transcription data for NLP tasksKagglehttps://www.kaggle.com/tboyle10/medicaltranscriptions访问
Augmented Clinical Notes Asclepius医学文本与大模型文本临床笔记生成167k synthetic clinical notes with discharge summaries and comprehensive medical histories 2026Hugging Facehttps://huggingface.co/datasets/starmpcc/Asclepius-Synthetic-Clinical-Notes访问
Med_Dataset医学文本与大模型文本医疗对话100k real doctor-patient interactions across medical specialties with diagnoses and treatment 2026Hugging Facehttps://huggingface.co/datasets/Med-dataset/Med_Dataset访问
Medical Medicine Dataset医学文本与大模型文本药物信息700 medications with therapeutic uses, side effects, descriptions for medical chatbots 2026Hugging Facehttps://huggingface.co/datasets/darkknight25/medical_medicine_dataset访问
MedFit Dataset医学文本与大模型文本医学问答6,444 healthcare Q&A pairs for fine-tuning medical chatbot language models 2026Hugging Facehttps://huggingface.co/datasets/mlx-community/medfit-dataset访问
CNTXTAI Medical Case Studies医学文本与大模型文本临床病例Diverse clinical cases from chronic diseases to acute conditions from academic publications 2026Hugging Facehttps://huggingface.co/datasets/CNTXTAI0/CNTXTAI_Medical_Case_Studies访问
Synthetic Emergency Healthcare Services Dataset血液与淋巴系统疾病急诊模拟Synthetic simulation data of emergency services including blood pressure, patient types, OPD data 2026Zenodohttps://zenodo.org/records/14058516访问
Hindi English and Punjabi Healthcare Datasets医学文本与大模型文本多语言医疗Multilingual healthcare datasets covering medical diagnoses, disease names in three languages 2026Zenodohttps://zenodo.org/records/14599295访问
DATASUS TABNET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
Portal de Dados Abertos do SUS通用医学数据集公共卫生Open data portal for the Brazilian Unified Health System (SUS)Brazil SUShttps://dadosabertos.saude.gov.br/访问
Global Health Observatory WHO通用医学数据集全球健康统计WHO gateway to health-related statistics for 194 Member StatesWHOhttps://www.who.int/data/gho访问
Global Health Data Exchange GHDx通用医学数据集全球健康数据Comprehensive catalog of surveys, censuses, vital statistics, and health-related dataIHMEhttps://ghdx.healthdata.org/global-health-data-exchange访问
Stanford AIMI Shared Datasets通用医学数据集医学影像影像共享Stanford AIMI shared medical imaging datasets platformStanfordhttps://aimi.stanford.edu/shared-datasets访问
Multi-RADS医学文本与大模型文本报告分类Synthetic Radiology Report Dataset, 1600 synthetic reports covering 17 imaging findings, RADS classification 2026GitHubhttps://arxiv.org/pdf/2601.03232访问
Bones and Joints B&J Benchmark医学文本与大模型多模态临床推理1245 QA pairs spanning 7 clinical competency tasks, X-ray/CT/MRI, VQA & treatment planning 2025Hugging Facehttps://arxiv.org/pdf/2512.22275访问
MediEval医学文本与大模型文本自然语言推理37144 medical statements from 2015 hospital admissions, patient-contextual reasoning, NLI 2025GitHubhttps://arxiv.org/pdf/2512.20822访问
TCM-BEST4SDT医学文本与大模型文本中医辨证600 questions including 300 clinical syndrome differentiation cases, TCM benchmark 2025GitHubhttps://arxiv.org/pdf/2512.02816访问
SurgMLLMBench眼病视频手术场景理解10652 frames with annotations from 5 surgical datasets, surgical scene understanding 2025Project Pagehttps://arxiv.org/pdf/2511.21339访问
MedVision通用医学数据集医学影像检测测量30.8 million image-annotation pairs across 22 public datasets, CT/MRI/X-ray/PET detection & measurement 2025Project Pagehttps://arxiv.org/pdf/2511.18676访问
EHRStruct医学文本与大模型关系推理2200 task-specific samples across 11 data and knowledge tasks, structured EHR reasoning 2025GitHubhttps://arxiv.org/pdf/2511.08206访问
TCM-Eval医学文本与大模型文本中医问答6099 questions from expert-level Chinese medical examinations, TCM benchmark 2025GitHubhttps://arxiv.org/pdf/2511.07148访问
RxSafeBench医学文本与大模型文本用药安全2443 consultation scenarios including 1063 contraindication cases, medication safety QA BIBM2025GitHubhttps://arxiv.org/pdf/2511.04328访问
SemBench通用医学数据集语义查询1400+ SPARQL templates for evaluating medical query engines, knowledge graph semantic query 2025GitHubhttps://arxiv.org/pdf/2511.01716访问
XBench呼吸道疾病多模态视觉问答12601 chest X-ray cases with localization and textual explanations, grounding & explanation 2025GitHubhttps://arxiv.org/pdf/2510.19599访问
IMB Italian Medical Benchmark医学文本与大模型文本医学问答808506 items featuring 782644 clinical Italian conversations, medical QA & MCQA CLIC-it 2025GitHubhttps://arxiv.org/pdf/2510.18468访问
ViPET-ReportGen医学文本与大模型多模态报告生成1.5 million slices paired with 2757 Vietnamese clinical reports, PET/CT report generation NeurIPS 2025GitHubhttps://arxiv.org/pdf/2509.24739访问
Neural-MedBench神经系统疾病多模态鉴别诊断120 expert cases resulting in 200 depth-of-reasoning tasks, differential diagnosis MRI/CT 2025Project Pagehttps://arxiv.org/pdf/2509.22258访问
MedQARo医学文本与大模型文本医学问答102646 Romanian QA pairs covering 1011 clinical patients, multilingual medical QA 2025GitHubhttps://arxiv.org/pdf/2508.16390访问