Health Data Guide

This guide is designed to provide practical information on healthcare data and analytics for researchers and companies alike. Focus is in the context of machine learning and artificial intelligence, which require effective handling of big data from multiple data sources.

About Health Data Guide

In this guide, you will learn

  • what kind of health datasets are available and how to get the data
  • principles of legislation for using the data (GDPR and national laws in Finland)
  • what kind of consents are needed from the patient
  • special properties of electronic patient records
  • what is augmented/synthetic data
  • how to preprocess the data to get the maximum knowledge of it
  • recommendations for anonymization techniques
  • basics of machine learning for health data
  • secure data management

The text is complemented with web links to relevant articles, data sources, and EU guidelines for those who want more information on these topics. Feel free to give feedback for improving this guide!

Disclaimer: This Guide was made for informative purposes only. It was put together in 2019 and has not been updated since. The legislation is under constant change, and all the information in this version might not be valid. The Guide should not be used for legal guidance or should not be considered as legal advice or as an interpretation of any existing legislation.

Creative Commons license CC BY