Improving cardiovascular risk stratification through multivariate time-series analysis of cardiopulmonary exercise test data

Evangelos Ntalianis; Nicholas Cauwenberghs; František Sabovčik; Everton Santana; Francois Haddad; Jomme Claes; Matthijs Michielsen; Guido Claessen; Werner Budts; Kaatje Goetschalckx; Véronique Cornelissen; Tatiana Kuznetsova

doi:10.1016/j.isci.2024.110792

Improving cardiovascular risk stratification through multivariate time-series analysis of cardiopulmonary exercise test data

iScience. 2024 Aug 22;27(9):110792. doi: 10.1016/j.isci.2024.110792. eCollection 2024 Sep 20.

Affiliations

¹ Research Unit Hypertension and Cardiovascular Epidemiology, KU Leuven Department of Cardiovascular Sciences, University of Leuven, Leuven, Belgium.
² Stanford Cardiovascular Institute and Division of Cardiovascular Medicine, Stanford University School of Medicine, Stanford, CA, USA.
³ Rehabilitation in Internal Disorders, KU Leuven Department of Rehabilitation Sciences, University of Leuven, Leuven, Belgium.
⁴ Department of Cardiology, Hartcentrum, Virga Jessa Hospital, Hasselt, Belgium.
⁵ Faculty of Medicine and Life Sciences, Hasselt University, Hasselt, Belgium.
⁶ Cardiology, KU Leuven Department of Cardiovascular Sciences, University of Leuven, Leuven, Belgium.

Abstract

Nowadays cardiorespiratory fitness (CRF) is assessed using summary indexes of cardiopulmonary exercise tests (CPETs). Yet, raw time-series CPET recordings may hold additional information with clinical relevance. Therefore, we investigated whether analysis of raw CPET data using dynamic time warping combined with k-medoids could identify distinct CRF phenogroups and improve cardiovascular (CV) risk stratification. CPET recordings from 1,399 participants (mean age, 56.4 years; 37.7% women) were separated into 5 groups with distinct patterns. Cluster 5 was associated with the worst CV profile with higher use of antihypertensive medication and a history of CV disease, while cluster 1 represented the most favorable CV profile. Clusters 4 (hazard ratio: 1.30; p = 0.033) and 5 (hazard ratio: 1.36; p = 0.0088) had a significantly higher risk of incident adverse events compared to clusters 1 and 2. The model evaluation in the external validation cohort revealed similar patterns. Therefore, an integrative CRF profiling might facilitate CV risk stratification and management.

Keywords: Artificial intelligence; Cardiovascular medicine; Kinesiology.