Phenotyping OSA: a time series analysis using fuzzy clustering and persistent homology

TL;DR

This paper introduces a novel approach to phenotyping pediatric sleep apnea by combining fuzzy clustering of airflow time series in multiple domains with topological data analysis using persistent homology, aiming to improve disorder characterization.

Contribution

It presents a new multi-method framework integrating fuzzy clustering and persistent homology for better phenotyping of sleep apnea from airflow signals.

Findings

Fuzzy clustering reveals distinct patient phenotypes.

Topological analysis uncovers periodicity features in airflow signals.

Dirichlet regression links phenotypes with clinical outcomes.

Abstract

Sleep apnea is a disorder that has serious consequences for the pediatric population. There has been recent concern that traditional diagnosis of the disorder using the apnea-hypopnea index may be ineffective in capturing its multi-faceted outcomes. In this work, we take a first step in addressing this issue by phenotyping patients using a clustering analysis of airflow time series. This is approached in three ways: using feature-based fuzzy clustering in the time and frequency domains, and using persistent homology to study the signal from a topological perspective. The fuzzy clusters are analyzed in a novel manner using a Dirichlet regression analysis, while the topological approach leverages Takens embedding theorem to study the periodicity properties of the signals.