Inferring disease subtypes from clusters in explanation space - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Scientific Reports Year : 2020

Inferring disease subtypes from clusters in explanation space


UNCORRECTED PROOFJournal : SREP 41598Article No : 68858Pages : 6MS Code : 68858Dispatch : 5-7-20201Vol.:(0123456789)Scientific RepoRtS | _#####################_ | disease subtypes from clusters in explanation spaceMarc‑Andre Schulz1*, Matt chapman‑Rounds2, Manisha Verma3, Danilo Bzdok4 & Konstantinos Georgatzis5Identification 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, most compellingly 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


Fichier principal
Vignette du fichier
schulz_2020_SR_clusters_explanation.pdf (1.21 Mo) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

hal-02892863 , version 1 (07-07-2020)



Marc-Andre Schulz, Matt Chapman-Rounds, Manisha Verma, Danilo Bzdok, Konstantinos Georgatzis. Inferring disease subtypes from clusters in explanation space. Scientific Reports, 2020, ⟨10.1038/s41598-020-68858-7⟩. ⟨hal-02892863⟩
90 View
85 Download



Gmail Facebook X LinkedIn More