Identifying high-risk Fontan phenotypes using K-means clustering of cardiac magnetic resonance-based dyssynchrony metrics

Background: Individuals with a Fontan circulation encompass a heterogeneous group with adverse outcomes linked to ventricular dilation, dysfunction, and dyssynchrony. The purpose of this study was to assess if unsupervised machine learning cluster analysis of cardiovascular magnetic resonance (CMR)-...

Full description

Saved in:
Bibliographic Details
Main Authors: Addison Gearhart, Sunakshi Bassi, Rahul H. Rathod, Rebecca S. Beroukhim, Stuart Lipsitz, Maxwell P. Gold, David M. Harrild, Audrey Dionne, Sunil J. Ghelani
Format: Article
Language:English
Published: Elsevier 2024-01-01
Series:Journal of Cardiovascular Magnetic Resonance
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1097664724010871
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846121390370979840
author Addison Gearhart
Sunakshi Bassi
Rahul H. Rathod
Rebecca S. Beroukhim
Stuart Lipsitz
Maxwell P. Gold
David M. Harrild
Audrey Dionne
Sunil J. Ghelani
author_facet Addison Gearhart
Sunakshi Bassi
Rahul H. Rathod
Rebecca S. Beroukhim
Stuart Lipsitz
Maxwell P. Gold
David M. Harrild
Audrey Dionne
Sunil J. Ghelani
author_sort Addison Gearhart
collection DOAJ
description Background: Individuals with a Fontan circulation encompass a heterogeneous group with adverse outcomes linked to ventricular dilation, dysfunction, and dyssynchrony. The purpose of this study was to assess if unsupervised machine learning cluster analysis of cardiovascular magnetic resonance (CMR)-derived dyssynchrony metrics can separate ventricles in the Fontan circulation from normal control left ventricles and identify prognostically distinct subgroups within the Fontan cohort. Methods: This single-center, retrospective study used 503 CMR studies from Fontan patients (median age 15 y) and 42 from age-matched controls from January 2005 to May 2011. Feature tracking on short-axis cine stacks assessed radial and circumferential strain, strain rate, and displacement. Unsupervised K-means clustering was applied to 24 mechanical dyssynchrony metrics derived from these deformation measurements. Clusters were compared for demographic, anatomical, and composite outcomes of death, or heart transplantation. Results: Four distinct phenotypic clusters were identified. Over a median follow-up of 4.2 y (interquartile ranges 1.7–8.8 y), 58 (11.5%) patients met the composite outcome. The highest-risk cluster (largely comprised of right or mixed ventricular morphology and dilated, dyssynchronous ventricles) exhibited a higher hazard for the composite outcome compared to the lowest-risk cluster while controlling for ventricular morphology (hazard ratio [HR] 6.4; 95% confidence interval [CI] 2.1–19.3; P value 0.001) and higher indexed end-diastolic volume (HR 3.2; 95% CI 1.04–10.0; P value 0.043) per 10 mL/m2. Conclusion: Unsupervised machine learning using CMR-derived dyssynchrony metrics identified four distinct clusters of patients with Fontan circulation and healthy controls with varying clinical characteristics and risk profiles. This technique can be used to guide future studies and identify more homogeneous subsets of patients from an overall heterogeneous population.
format Article
id doaj-art-59249554e8554ed3b57ca3aa9cbb6e61
institution Kabale University
issn 1097-6647
language English
publishDate 2024-01-01
publisher Elsevier
record_format Article
series Journal of Cardiovascular Magnetic Resonance
spelling doaj-art-59249554e8554ed3b57ca3aa9cbb6e612024-12-16T05:34:41ZengElsevierJournal of Cardiovascular Magnetic Resonance1097-66472024-01-01262101060Identifying high-risk Fontan phenotypes using K-means clustering of cardiac magnetic resonance-based dyssynchrony metricsAddison Gearhart0Sunakshi Bassi1Rahul H. Rathod2Rebecca S. Beroukhim3Stuart Lipsitz4Maxwell P. Gold5David M. Harrild6Audrey Dionne7Sunil J. Ghelani8Department of Cardiology, Boston Children’s Hospital, Boston, Massachusetts, USA; Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USA; Corresponding author.Department of Cardiology, Children's Hospital of Philadelphia, Phildelphia, Pennsylvannia, USADepartment of Cardiology, Boston Children’s Hospital, Boston, Massachusetts, USA; Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USADepartment of Cardiology, Boston Children’s Hospital, Boston, Massachusetts, USA; Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USADepartment of Cardiology, Boston Children’s Hospital, Boston, Massachusetts, USA; Division of General Internal Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USAMassachusetts Institute of Technology, Boston, Massachusetts, USADepartment of Cardiology, Boston Children’s Hospital, Boston, Massachusetts, USA; Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USADepartment of Cardiology, Boston Children’s Hospital, Boston, Massachusetts, USA; Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USADepartment of Cardiology, Boston Children’s Hospital, Boston, Massachusetts, USA; Department of Pediatrics, Harvard Medical School, Boston, Massachusetts, USABackground: Individuals with a Fontan circulation encompass a heterogeneous group with adverse outcomes linked to ventricular dilation, dysfunction, and dyssynchrony. The purpose of this study was to assess if unsupervised machine learning cluster analysis of cardiovascular magnetic resonance (CMR)-derived dyssynchrony metrics can separate ventricles in the Fontan circulation from normal control left ventricles and identify prognostically distinct subgroups within the Fontan cohort. Methods: This single-center, retrospective study used 503 CMR studies from Fontan patients (median age 15 y) and 42 from age-matched controls from January 2005 to May 2011. Feature tracking on short-axis cine stacks assessed radial and circumferential strain, strain rate, and displacement. Unsupervised K-means clustering was applied to 24 mechanical dyssynchrony metrics derived from these deformation measurements. Clusters were compared for demographic, anatomical, and composite outcomes of death, or heart transplantation. Results: Four distinct phenotypic clusters were identified. Over a median follow-up of 4.2 y (interquartile ranges 1.7–8.8 y), 58 (11.5%) patients met the composite outcome. The highest-risk cluster (largely comprised of right or mixed ventricular morphology and dilated, dyssynchronous ventricles) exhibited a higher hazard for the composite outcome compared to the lowest-risk cluster while controlling for ventricular morphology (hazard ratio [HR] 6.4; 95% confidence interval [CI] 2.1–19.3; P value 0.001) and higher indexed end-diastolic volume (HR 3.2; 95% CI 1.04–10.0; P value 0.043) per 10 mL/m2. Conclusion: Unsupervised machine learning using CMR-derived dyssynchrony metrics identified four distinct clusters of patients with Fontan circulation and healthy controls with varying clinical characteristics and risk profiles. This technique can be used to guide future studies and identify more homogeneous subsets of patients from an overall heterogeneous population.http://www.sciencedirect.com/science/article/pii/S1097664724010871Unsupervised machine learningPediatricsFontanCardiovascular magnetic resonance imagingDyssynchrony
spellingShingle Addison Gearhart
Sunakshi Bassi
Rahul H. Rathod
Rebecca S. Beroukhim
Stuart Lipsitz
Maxwell P. Gold
David M. Harrild
Audrey Dionne
Sunil J. Ghelani
Identifying high-risk Fontan phenotypes using K-means clustering of cardiac magnetic resonance-based dyssynchrony metrics
Journal of Cardiovascular Magnetic Resonance
Unsupervised machine learning
Pediatrics
Fontan
Cardiovascular magnetic resonance imaging
Dyssynchrony
title Identifying high-risk Fontan phenotypes using K-means clustering of cardiac magnetic resonance-based dyssynchrony metrics
title_full Identifying high-risk Fontan phenotypes using K-means clustering of cardiac magnetic resonance-based dyssynchrony metrics
title_fullStr Identifying high-risk Fontan phenotypes using K-means clustering of cardiac magnetic resonance-based dyssynchrony metrics
title_full_unstemmed Identifying high-risk Fontan phenotypes using K-means clustering of cardiac magnetic resonance-based dyssynchrony metrics
title_short Identifying high-risk Fontan phenotypes using K-means clustering of cardiac magnetic resonance-based dyssynchrony metrics
title_sort identifying high risk fontan phenotypes using k means clustering of cardiac magnetic resonance based dyssynchrony metrics
topic Unsupervised machine learning
Pediatrics
Fontan
Cardiovascular magnetic resonance imaging
Dyssynchrony
url http://www.sciencedirect.com/science/article/pii/S1097664724010871
work_keys_str_mv AT addisongearhart identifyinghighriskfontanphenotypesusingkmeansclusteringofcardiacmagneticresonancebaseddyssynchronymetrics
AT sunakshibassi identifyinghighriskfontanphenotypesusingkmeansclusteringofcardiacmagneticresonancebaseddyssynchronymetrics
AT rahulhrathod identifyinghighriskfontanphenotypesusingkmeansclusteringofcardiacmagneticresonancebaseddyssynchronymetrics
AT rebeccasberoukhim identifyinghighriskfontanphenotypesusingkmeansclusteringofcardiacmagneticresonancebaseddyssynchronymetrics
AT stuartlipsitz identifyinghighriskfontanphenotypesusingkmeansclusteringofcardiacmagneticresonancebaseddyssynchronymetrics
AT maxwellpgold identifyinghighriskfontanphenotypesusingkmeansclusteringofcardiacmagneticresonancebaseddyssynchronymetrics
AT davidmharrild identifyinghighriskfontanphenotypesusingkmeansclusteringofcardiacmagneticresonancebaseddyssynchronymetrics
AT audreydionne identifyinghighriskfontanphenotypesusingkmeansclusteringofcardiacmagneticresonancebaseddyssynchronymetrics
AT suniljghelani identifyinghighriskfontanphenotypesusingkmeansclusteringofcardiacmagneticresonancebaseddyssynchronymetrics