Utility Metrics for Evaluating Synthetic Health Data Generation Methods: Validation Study.

Khaled El Emam Lucy Mosquera Xi Fang Alaa El-Hussuna

Published in: JMIR medical informatics (2022)

This study has validated a generative model utility metric, the multivariate Hellinger distance, which can be used to reliably rank competing SDG methods on the same data set. The Hellinger distance metric can be used to evaluate and compare alternate SDG methods.

Keyphrases

electronic health record
healthcare
public health
data analysis
machine learning
climate change
artificial intelligence