Identification of Sleep Phenotypes in COPD Using Machine Learning-Based Cluster Analysis

Authors

Javad Razjouyan
Nicola A Hanania
Sara Nowakowski
Ritwick Agrawal
Amir Sharafkhaneh

Publication Date

6-1-2024

Journal

Respiratory Medicine

DOI

10.1016/j.rmed.2024.107641

PMID

38710399

PMCID

PMC11218872

PubMedCentral® Posted Date

7-2-2024

PubMedCentral® Full Text Version

Author MSS

Published Open-Access

yes

Keywords

Humans, Pulmonary Disease, Chronic Obstructive, Cluster Analysis, Machine Learning, Male, Female, Phenotype, Aged, Longitudinal Studies, Middle Aged, Sleep Wake Disorders, Polysomnography, Sleep, Comorbidity, Quality of Life, Unsupervised Machine Learning, Age Factors, Cohort Studies, COPD, Sleep disorders, Phenotypes, Comorbidities

Abstract

BACKGROUND: Disturbed sleep in patients with COPD impact quality of life and predict adverse outcomes.

RESEARCH QUESTION: To identify distinct phenotypic clusters of patients with COPD using objective sleep parameters and evaluate the associations between clusters and all-cause mortality to inform risk stratification.

STUDY DESIGN AND METHODS: A longitudinal observational cohort study using nationwide Veterans Health Administration data of patients with COPD investigated for sleep disorders. Sleep parameters were extracted from polysomnography physician interpretation using a validated natural language processing algorithm. We performed cluster analysis using an unsupervised machine learning algorithm (K-means) and examined the association between clusters and mortality using Cox regression analysis, adjusted for potential confounders, and visualized with Kaplan-Meier estimates.

RESULTS: Among 9992 patients with COPD and a clinically indicated baseline polysomnogram, we identified five distinct clusters based on age, comorbidity burden and sleep parameters. Overall mortality increased from 9.4 % to 42 % and short-term mortality (

INTERPRETATION: We identified five distinct clinical clusters and highlighted the significant association between total sleep time and sleep efficiency on mortality. The identified clusters highlight the importance of objective sleep parameters in determining mortality risk and phenotypic characterization in this population.

Comments

Associated Data