Unsupervised phenotypic clustering of cardiac MRI data reveals distinct subgroups associated with outcomes in
Gaetano Nucifora1,2, Daniele Muser3,4, Joshua Bradley5
1Cardiac Imaging Unit, Wythenshawe Hospital, Manchester University NHS Foundation Trust, Trust Southmoor Rd, Manchester, M23 9LT, UK. gaetano.nucifora@mft.nhs.uk.
Insights
Unsupervised machine learning identified two distinct patient groups in ischemic cardiomyopathy (ICM) using cardiac MRI data. This approach enhances risk prediction and personalized treatment for ICM patients.
Area of Science:
- Cardiology
- Medical Imaging
- Artificial Intelligence
Background:
- Ischemic cardiomyopathy (ICM) exhibits significant outcome heterogeneity, complicating risk stratification.
- Cardiac magnetic resonance (CMR) provides detailed myocardial data, but integration is challenging.
- Unsupervised machine learning offers a potential solution for identifying distinct ICM phenotypes.
Purpose of the Study:
- To apply unsupervised machine learning to CMR-derived variables in ICM patients.
- To identify distinct phenotypic subgroups within ICM.
- To enhance prognostic accuracy and risk stratification in ICM.
Main Methods:
- Included 319 clinically stable ICM patients.
- Utilized KAMILA clustering algorithm on CMR variables (LVEF, volumes, scar burden).
- Employed PCA for visualization, Cox regression/Kaplan-Meier for prognosis, and SHAP for feature importance.
Main Results:
- Identified two distinct clusters: Cluster 1 (better function, lower scar) and Cluster 2 (advanced disease, higher scar).
- Cluster 2 patients showed significantly higher risk of adverse outcomes (HR=3.96, p<0.001).
- Ischemic scar burden, sphericity index, and midwall fibrosis were key outcome predictors (SHAP analysis).
Conclusions:
- Unsupervised clustering of CMR data reveals distinct ICM phenotypes with prognostic value.
- This machine learning approach improves ICM risk stratification.
- Potential for personalized treatment strategies based on identified phenotypes.
Abstract:
Ischemic cardiomyopathy (ICM) shows significant heterogeneity in clinical outcomes, challenging traditional risk stratification methods. Cardiac magnetic resonance (CMR) imaging offers detailed insights into myocardial structure and function, yet integrating this multidimensional data remains complex. Aim of the current study was to assess whether unsupervised machine learning could help identify distinct phenotypic subgroups and enhance prognostic accuracy. This study included 319 clinically stable ICM patients. CMR-derived variables, including left ventricular ejection fraction (LVEF), ventricular volumes, and myocardial scar burden, were analysed using KAMILA clustering algorithm. The optimal number of clusters was determined through silhouette analysis, within-cluster sum of squares, and gap statistics. Principal Component Analysis (PCA) visualized the clustering results, and prognostic value was assessed using Cox regression and Kaplan-Meier survival analysis. SHAP (SHapley Additive exPlanations) values were used to evaluate feature importance. Two distinct phenotypic clusters were identified. Cluster 1 (n = 219) demonstrated better cardiac function, with higher LVEF, smaller ventricular volumes, and lower scar burden. Cluster 2 (n = 100) indicated advanced disease, with lower LVEF, larger volumes, higher scar burden, and greater midwall fibrosis. PCA confirmed clear separation between clusters, explaining 62.6% of the variance. After a median follow-up of 13 months, the composite endpoint was observed in 37 (12%) patients. Patients in Cluster 2 had a significantly higher risk of experiencing the composite outcome (HR = 3.96, p < 0.001). SHAP analysis identified ischaemic scar burden, sphericity index, and midwall fibrosis as key predictors of outcomes. Unsupervised clustering of CMR-derived variables identified distinct ICM phenotypes with important prognostic implications. This method improves risk stratification and could help tailor personalised treatment plans, highlighting the potential of machine learning in understanding ICM heterogeneity.
Related Concept Videos
01:25Cardiomyopathy I: Introduction and Classification
01:29Cardiomyopathy III: Hypertrophic Cardiomyopathy
01:21Imaging Studies for Cardiovascular System IV: CMRI