Work in Progress
This page is currently under development. Content may be incomplete or contain inaccuracies. If you notice any errors or have suggestions, please contact us.
Medical & Clinical Repositories
Access to medical and clinical data is often restricted due to privacy regulations. However, several open datasets, controlled-access repositories, and synthetic data sources exist for research purposes.
Medical Imaging Repositories
| Repository | Description | Access | Link |
|---|---|---|---|
| The Cancer Imaging Archive (TCIA) | Large archive of medical images for cancer research (CT, MRI, PET) | Open / Controlled | cancerimagingarchive.net |
| UK Biobank Imaging | Brain, cardiac, and body MRI from 100,000+ participants | Controlled | ukbiobank.ac.uk |
| OpenNeuro | Open platform for sharing neuroimaging data (MRI, EEG, MEG) in BIDS format | Open | openneuro.org |
| Grand Challenge | Platform hosting medical imaging challenges with curated datasets | Varies | grand-challenge.org |
| TCGA (The Cancer Genome Atlas) | Multi-omics cancer data including histopathology images | Controlled | cancer.gov/tcga |
Clinical and Health Data
| Repository | Description | Access | Link |
|---|---|---|---|
| MIMIC-IV | Critical care database with de-identified EHR data from Beth Israel Deaconess Medical Center | Controlled (credentialing) | physionet.org/content/mimiciv |
| eICU Collaborative Research Database | Multi-center ICU dataset with physiological and clinical data | Controlled | physionet.org/content/eicu-crd |
| PhysioNet | Archive of physiological signals (ECG, EEG, etc.) and clinical data | Open / Controlled | physionet.org |
| ClinicalTrials.gov | Registry of clinical studies with protocols and summary results | Open | clinicaltrials.gov |
| EU Clinical Trials Register | European register of clinical trials with protocols | Open | clinicaltrialsregister.eu |
Synthetic and Benchmark Data
| Resource | Description | Link |
|---|---|---|
| Synthea | Open-source synthetic patient generator producing realistic FHIR/C-CDA records | synthetichealth.github.io/synthea |
| Medical Segmentation Decathlon | 10 curated medical image segmentation tasks for benchmarking | medicaldecathlon.com |
Terminology and Knowledge Bases
| Resource | Description | Link |
|---|---|---|
| UMLS (Unified Medical Language System) | NLM's metathesaurus integrating 200+ biomedical vocabularies | nlm.nih.gov/research/umls |
| BioPortal | Repository of biomedical ontologies | bioportal.bioontology.org |
| DrugBank | Comprehensive drug and drug target database | drugbank.com |
Important Note on Data Access
Many medical datasets require:
- Institutional ethics approval or IRB review
- Data use agreements (DUA) specifying permitted uses
- CITI training or equivalent research ethics certification
- Controlled-access applications with justification of research need
Always check access requirements before planning analyses with clinical data.