Titre :

PhenoLines: Phenotype Comparison Visualizations for Disease Subtyping via Topic Models

Auteur(s) :

Glueck, Michael [Auteur]
University of Toronto
Autodesk Research
Pakdaman Naeini, Mahdi [Auteur]
Harvard University
Doshi-Velez, Finale [Auteur]
Harvard University
Chevalier, Fanny [Auteur]
Computing tools to empower users [MJOLNIR]
Khan, Azam [Auteur]
Autodesk Research
Wigdor, Daniel [Auteur]
Dynamic Graphics Project [Toronto] [DGP]
Brudno, Michael [Auteur]
University of Toronto
The Hospital for sick children [Toronto] [SickKids]

Titre de la manifestation scientifique :

IEEE Conference on Visual Analytics Science and Technology (IEEE VAST 2017)

Ville :

Phoenix

Pays :

Etats-Unis d'Amérique

Date de début de la manifestation scientifique :

2017

Date de publication :

2017

Mot(s)-clé(s) en anglais :

Developmental disorder
Human Phenotype Ontology (HPO)
Phenotypes
Topic models
Topology simplification

Discipline(s) HAL :

Sciences cognitives/Informatique
Informatique [cs]/Interface homme-machine [cs.HC]

Résumé en anglais : [en]

—PhenoLines is a visual analysis tool for the interpretation of disease subtypes, derived from the application of topic models to clinical data. Topic models enable one to mine cross-sectional patient comorbidity data ...
Lire la suite >—PhenoLines is a visual analysis tool for the interpretation of disease subtypes, derived from the application of topic models to clinical data. Topic models enable one to mine cross-sectional patient comorbidity data (e.g., electronic health records) and construct disease subtypes—each with its own temporally evolving prevalence and co-occurrence of phenotypes—without requiring aligned longitudinal phenotype data for all patients. However, the dimensionality of topic models makes interpretation challenging, and de facto analyses provide little intuition regarding phenotype relevance or phenotype interrelationships. PhenoLines enables one to compare phenotype prevalence within and across disease subtype topics, thus supporting subtype characterization, a task that involvesidentifying a proposed subtype’s dominant phenotypes, ages of effect, and clinical validity. We contribute a data transformation workflow that employs the Human Phenotype Ontology to hierarchically organize phenotypes and aggregate the evolving probabilities produced by topic models. We introduce a novel measure of phenotype relevance that can be used to simplify the resulting topology. The design of PhenoLines was motivated by formative interviews with machine learning and clinical experts. We describe the co-operative design process, distill high-level tasks, and report on initial evaluations with machine learning experts and a medical domain expert. These results suggest that PhenoLines demonstrates promising approaches to support the characterization and optimization of topic models.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL