Patient similarity: methods and applications
1 December 2020
Patient similarity facilitates personalized predictive models, disease subtyping and treatment design
Main steps: data integration, similarity measurement, neighborhood identification
Methods include distance metrics, neural networks, clustering and active learning
Key applications are in precision medicine and clinical decision support
Demystifying patient similarity: A guide to computational methods for personalized medicine
This paper reviews computational methods for analyzing patient similarity from electronic health records and other biomedical data. It summarizes key techniques for data integration, similarity measurement, neighborhood identification and applications in precision medicine. The review aims to provide an accessible introduction to this emerging field.
No comments yet, be the first to start the conversation...
Sign up to comment on this paper