| Title: | Inferring disease subtypes from clusters in explanation space |
| Journal: | Scientific Reports |
| Published: | 30 Jul 2020 |
| Pubmed: | https://pubmed.ncbi.nlm.nih.gov/32732917/ |
| DOI: | https://doi.org/10.1038/s41598-020-68858-7 |
| URL: | https://www.nature.com/articles/s41598-020-68858-7.pdf |
Publication 5235
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
Identification of disease subtypes and corresponding biomarkers can substantially improve clinical diagnosis and treatment selection. Discovering these subtypes in noisy, high dimensional biomedical data is often impossible for humans and challenging for machines. We introduce a new approach to facilitate the discovery of disease subtypes: Instead of analyzing the original data, we train a diagnostic classifier (healthy vs. diseased) and extract instance-wise explanations for the classifier's decisions. The distribution of instances in the explanation space of our diagnostic classifier amplifies the different reasons for belonging to the same class-resulting in a representation that is uniquely useful for discovering latent subtypes. We compare our ability to recover subtypes via cluster analysis on model explanations to classical cluster analysis on the original data. In multiple datasets with known ground-truth subclasses, particularly on UK Biobank brain imaging data and transcriptome data from the Cancer Genome Atlas, we show that cluster analysis on model explanations substantially outperforms the classical approach. While we believe clustering in explanation space to be particularly valuable for inferring disease subtypes, the method is more general and applicable to any kind of sub-type identification.</p>
5 Authors
- Marc-Andre Schulz
- Matt Chapman-Rounds
- Manisha Verma
- Danilo Bzdok
- Konstantinos Georgatzis
Enabling scientific discoveries that improve human health