Best Public Datasets for Health Data Science Projects
I will keep updating this page. If you have a suggestion on a dataset to add, send me a message on Twitter @ahobby9
Kaggle Datasets Kaggle has tons of machine learning-friendly datasets. It also has a search feature where you can find healthcare datasets.
UCI Datasets UCI has a popular heart disease and breast cancer machine-learning Dataset. However, there are other datasets if you search.
Google Dataset Search You can find healthcare datasets here, among other datasets.
Amazon Dataset Search Amazon has a list of various kinds of health datasets.
WHO Dataset These are datasets made available by the World Health Organization. The WHO Dataset is an excellent resource for those interested in global health.
Wikipedia This has a list of datasets. Some are healthcare.
SEER Cancer This has cancer data for the United States.
National Health and Nutrition Examination Survey (NHANES) This is a popular public health dataset.
Health Statistics & Data: Datasets/Raw Data This is a list of health datasets from UC Berkeley.
Population Health and Health Services Research Datasets This is a list of health datasets from UCSF.
NICHD Datasets & Research Resources: This is a list of datasets.
MIMIC-III Clinical Database: This is an open-access database of deidentified health data.
Openfmri This is an MRI imaging dataset.
Oasis Brains Dataset This is a brain imaging dataset.
NIH DeepLesion This is an imaging dataset from the NIH.
Cancer Imaging This has cancer imaging data.
https://wonder.cdc.gov/ per Gene S