Related Experiment Video
Updated: Mar 3, 2026
Echocardiographic Approaches and Protocols for Comprehensive Phenotypic Characterization of Valvular Heart Disease in Mice
Published on: February 14, 2017
Machine-learning-derived phenotypes of hypertensive patients using multidimensional clinical and echocardiographic
In-Chang Hwang1,2, Hyue Mee Kim3, Jiesuck Park1
1Department of Cardiology, Cardiovascular Center, Seoul National University Bundang Hospital, 82 Gumi-ro-173-gil, Bundang, Seongnam, Gyeonggi 13620, South Korea.
Insights
Machine learning identified four distinct hypertensive heart disease phenotypes. These groups show varied clinical profiles, disease progression, and responses to treatment, enabling personalized patient management and improved risk stratification.
Area of Science:
- Cardiology
- Medical Imaging
- Machine Learning
Background:
- Hypertensive heart disease (HHD) management requires better patient stratification.
- Echocardiography with strain imaging offers detailed cardiac assessment.
Purpose of the Study:
- To apply unsupervised machine learning to echocardiographic strain data in hypertensive patients.
- To identify distinct HHD phenotypes with unique clinical characteristics and outcomes.
Main Methods:
- 1607 hypertensive patients from the STRATS-HHD registry underwent baseline and follow-up echocardiography.
- Principal component analysis and K-means clustering (K=4) were used on 20 variables, including atrial and ventricular strain.
- Clusters were derived and validated across two cohorts; remodelling trajectories and outcomes were assessed.
Main Results:
- Four distinct HHD phenotypes were identified: atrial fibrillation-predominant, elderly with comorbidities, middle-aged with coronary disease, and younger with severe hypertension and strain impairment.
- Prognosis varied significantly, with cluster 1 showing the highest risk of cardiovascular events and cluster 4 the most favorable outcomes.
- Renin-angiotensin blockade was associated with left ventricular mass regression in the younger, more remodeled group (cluster 4).
Conclusions:
- Machine learning-based clustering using strain imaging identified four unique HHD phenotypes.
- These data-driven phenotypes exhibit divergent remodelling, therapeutic responses, and clinical outcomes.
- This phenotyping approach may enhance risk stratification and guide tailored management strategies for hypertension.
Aims:
We applied unsupervised machine learning clustering to a large cohort of hypertensive patients undergoing echocardiography with strain imaging to identify phenotypes with distinct clinical profiles, comorbidities, remodelling trajectories, and outcomes.
Methods And Results:
We analysed 1607 patients from the STRATS-HHD registry who underwent echocardiography at baseline and after 6-18 months of therapy. Twenty clinical, laboratory, and echocardiographic variables-including left atrial and left ventricular strain-underwent principal component analysis and K-means clustering (K = 4). Clusters were derived in the SNUBH cohort (n = 1204) and validated in the CAUH cohort (n = 403), two institutional subsets of the registry. Remodelling trajectories were assessed using baseline-adjusted models, and associations with outcomes were evaluated using multivariable Cox regression. Four clusters emerged: (i) atrial fibrillation-predominant, with advanced remodelling and the highest event risk; (ii) elderly, with metabolic-renal comorbidities but preserved function; (iii) middle-aged, with prevalent coronary disease and relatively preserved function; and (iv) younger, with severe hypertension, marked strain impairment, and the greatest remodelling regression with therapy. Prognosis varied: cluster 1 had the highest risk of cardiovascular death, heart failure hospitalization, stroke, and major adverse cardiovascular events (MACE); cluster 2 exhibited increased cardiovascular death and intermediate heart failure hospitalization risk; cluster 3 showed elevated coronary risk; and cluster 4 the most favourable outcomes. Associations between medication and remodelling varied, with renin-angiotensin blockade linked to LV mass regression in cluster 4.
Conclusion:
Machine learning -based clustering incorporating strain identified four distinct HHD phenotypes with divergent remodelling, therapeutic responses, and outcomes. Data-driven phenotyping may improve risk stratification and enable tailored management in hypertension.
More Related Videos
07:21Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking
Published on: February 12, 2011
11:50High-frequency High-resolution Echocardiography: First Evidence on Non-invasive Repeated Measure of Myocardial Strain, Contractility, and Mitral Regurgitation in the Ischemia-reperfused Murine Heart
Published on: July 9, 2010
Related Concept Videos
01:29Cardiomyopathy III: Hypertrophic Cardiomyopathy
01:30Hypertension III: Clinical Manifestations and Diagnostic Studies