I want to experiment with Bayesian networks, as well as try other machine learning approaches for learning dependancies in the data.
Is there any clinical dataset (containing results of various medical tests like blood pressure, cholesterol, maybe some diagnoses of medical conditions) with around 500-1000 attributes, and at least 500 instances?

I checked the UCI machine learning repository and found nothing satisfactory.

Or maybe there's some other dataset which could be somewhat similiar to patients' data?


1 Answer 1


You should take a look at MIMIC-III dataset. It has almost 50K patients with many features.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.