A cost-based multi-layer network approach for the discovery of patient phenotypes

TL;DR

This paper introduces COBALT, a cost-effective multi-layer network method for identifying patient phenotypes from questionnaire data, improving prediction of post-treatment outcomes in clinical settings.

Contribution

It presents a novel cost-based layer selection model for phenotype detection that reduces questionnaire features while maintaining predictive quality.

Findings

COBALT outperforms traditional clustering in phenotype detection for some variables.

Using phenotypes improves post-treatment outcome predictions.

The multi-layer network approach effectively captures patient heterogeneity.

Abstract

Clinical records frequently include assessments of the characteristics of patients, which may include the completion of various questionnaires. These questionnaires provide a variety of perspectives on a patient's current state of well-being. Not only is it critical to capture the heterogeneity given by these perspectives, but there is also a growing demand for developing cost-effective technologies for clinical phenotyping. Filling out many questionnaires may be a strain for the patients and therefore costly. In this work, we propose COBALT -- a cost-based layer selector model for detecting phenotypes using a community detection approach. Our goal is to minimize the number of features used to build these phenotypes while preserving its quality. We test our model using questionnaire data from chronic tinnitus patients and represent the data in a multi-layer network structure. The model is then evaluated by predicting post-treatment data using baseline features (age, gender, and pre-treatment data) as well as the identified phenotypes as a feature. For some post-treatment variables, predictors using phenotypes from COBALT as features outperformed those using phenotypes detected by traditional clustering methods. Moreover, using phenotype data to predict post-treatment data proved beneficial in comparison with predictors that were solely trained with baseline features.