Association of Machine Learning–Derived Phenogroupings of Echocardiographic Variables with Heart Failure in Stable Coronary Artery Disease: The Heart and Soul Study

doi:10.1016/j.echo.2019.09.010

Journal of the American Society of Echocardiography

Volume 33, Issue 3, March 2020, Pages 322-331.e1

https://doi.org/10.1016/j.echo.2019.09.010 Get rights and content

Highlights

•
Echocardiographic phenogroups in stable CAD can be derived with a clustering algorithm.
•
Patients with stable CAD had differential associations with HF hospitalization.
•
The phenogroups independently predicted HF hospitalizations equally as well as HFI.

Background

Many individual echocardiographic variables have been associated with heart failure (HF) in patients with stable coronary artery disease (CAD), but their combined utility for prediction has not been well studied.

Methods

Unsupervised model-based cluster analysis was performed by researchers blinded to the study outcome in 1,000 patients with stable CAD on 15 transthoracic echocardiographic variables. We evaluated associations of cluster membership with HF hospitalization using Cox proportional hazards regression analysis.

Results

The echo-derived clusters partitioned subjects into four phenogroupings: phenogroup 1 (n = 85) had the highest levels, phenogroups 2 (n = 314) and 3 (n = 205) displayed intermediate levels, and phenogroup 4 (n = 396) had the lowest levels of cardiopulmonary structural and functional abnormalities. Over 7.1 ± 3.2 years of follow-up, there were 198 HF hospitalizations. After multivariable adjustment for traditional cardiovascular risk factors, phenogroup 1 was associated with a nearly fivefold increased risk (hazard ratio [HR] = 4.8; 95% CI, 2.4-9.5), phenogroup 2 was associated with a nearly threefold increased risk (HR = 2.7; 95% CI, 1.4-5.0), and phenogroup 3 was associated with a nearly twofold increased risk (HR = 1.9; 95% CI, 1.0-3.8) of HF hospitalization, relative to phenogroup 4.

Conclusions

Transthoracic echocardiographic variables can be used to classify stable CAD patients into separate phenogroupings that differentiate cardiopulmonary structural and functional abnormalities and can predict HF hospitalization, independent of traditional cardiovascular risk factors.

Section snippets

Methods

The Heart and Soul Study is a prospective cohort study evaluating the impact of psychosocial factors on cardiovascular outcomes. The study methods have been previously described in detail.¹⁰ Participants were enrolled between 2000 and 2002 from two veterans' affairs hospitals, an academic medical center, and nine public health clinics in the San Francisco area. All participants had CAD defined by either a history of myocardial infarction, angiographic evidence of ≥50% stenosis in a coronary

Construction of Echocardiographic Phenogroupings

We identified four distinct echocardiographic phenogroups using an unsupervised (i.e., agnostic of outcomes) automated clustering method. We started with generating Spearman correlations among the 15 echocardiographic variables. In unadjusted analysis, we found moderately strong correlations (r ≥ 0.5) among LVEDVI, LVESVI, LVEF, and WMSI and between VTI_LVOT and VTI_RVOT (Figure 1); all other correlations were moderate (r < 0.5) to weak (r < 0.3). The strongest correlation was between LVEDVI and

Discussion

In this cohort of 1,000 participants with stable CAD, we found that automated model-based unsupervised clustering based on 15 echocardiographic measures identifies four distinct phenogroupings, which successfully partition subjects into categories of risk of HF hospitalization. Our group had previously used multivariable Cox proportional hazard models to select five of these 15 echocardiographic measures to create an HFI that independently predicted HF hospitalizations in the same cohort.⁶ We

Conclusion

Automated unsupervised clustering of echocardiographic measures successfully partitioned a population with stable CAD into phenogroupings of risk for HF hospitalization. This machine learning algorithm performed as well as the HFI, derived previously in the same cohort using traditional scalar methods. This suggests the possibility that automated machine learning algorithms could be applied to echocardiographic measurements to derive phenogroupings by being incorporated into echocardiographic

References (29)

B. Ristow et al.
Usefulness of left atrial volume index to predict heart failure hospitalization and mortality in ambulatory patients with coronary heart disease and comparison to left ventricular ejection fraction (from the Heart and Soul Study)
Am J Cardiol
(2008)
M.P. Turakhia et al.
Prognostic significance of increased left ventricular mass index to mortality and sudden death in patients with stable coronary heart disease (from the Heart and Soul Study)
Am J Cardiol
(2008)
B. Ristow et al.
Left ventricular outflow tract and pulmonary artery stroke distances independently predict heart failure hospitalization and mortality: the Heart and Soul Study
J Am Soc Echocardiogr
(2011)
X. Ren et al.
Usefulness of diastolic dominant pulmonary vein flow to predict hospitalization for heart failure and mortality in ambulatory patients with coronary heart disease (from the Heart and Soul Study)
Am J Cardiol
(2009)
F. Grigioni et al.
Contribution of ischemic mitral regurgitation to congestive heart failure after myocardial infarction
J Am Coll Cardiol
(2005)
S.M. Stevens et al.
Development of an echocardiographic risk-stratification index to predict heart failure in patients with stable coronary artery disease: the Heart and Soul study
JACC Cardiovasc Imaging
(2009)
M.C. Lancaster et al.
Phenotypic clustering of left ventricular diastolic function parameters: patterns and prognostic relevance
JACC Cardiovasc Imaging
(2019)
R.M. Lang et al.
Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging
J Am Soc Echocardiogr
(2015)
J.H. Goldman et al.
Usefulness of stroke distance by echocardiography as a surrogate marker of cardiac output that is independent of gender and size in a normal population
Am J Cardiol
(2001)
C.M. Otto et al.
Determination of the stenotic aortic valve area in adults using Doppler echocardiography
J Am Coll Cardiol
(1986)

X. Ren et al.

Prevalence and prognosis of asymptomatic left ventricular diastolic dysfunction in ambulatory patients with coronary heart disease

Am J Cardiol

(2007)

W.A. Zoghbi et al.

Recommendations for noninvasive evaluation of native valvular regurgitation: a report from the American Society of Echocardiography developed in collaboration with the Society for Cardiovascular Magnetic Resonance

J Am Soc Echocardiogr

(2017)

B.J. Kircher et al.

Noninvasive estimation of right atrial pressure from the inspiratory collapse of the inferior vena cava

Am J Cardiol

(1990)

D.D. McManus et al.

Prognostic value of left ventricular end-systolic volume index as a predictor of heart failure hospitalization in stable coronary artery disease: data from the Heart and Soul Study

J Am Soc Echocardiogr

(2009)

Cited by (13)

Cardiac Structure and Function Phenogroups and Risk of Incident Heart Failure (from the Multi-ethnic Study of Atherosclerosis)
2023, American Journal of Cardiology
Citation Excerpt :
Furthermore, some studies found significant associations between phenogroup classes and adverse outcomes such as sudden death or death from HF, all-cause mortality, all-cause hospitalization, and HF hospitalization.22–24 Other statistical methods have also been used for phenogroup identification.10,22–25 In a study of 397 patients with HFpEF, Shah et al used unbiased hierarchical cluster analysis and penalized model-based clustering to identify 3 distinct phenogroups that differed in clinical characteristics, cardiac structure and function, and outcomes.10
Indices of cardiac structure and function, such as left ventricular (LV) mass and ejection fraction, have been associated with risk of incident heart failure (HF), but the clinical relevance of data-driven grouping of a comprehensive set of cardiac parameters is unclear. In Multi-Ethnic Study of Atherosclerosis participants, latent class analysis was applied in the sample stratified by gender to define phenogroups on the basis of cardiovascular magnetic resonance imaging parameters of right ventricular and LV structure and function at baseline. Cox proportional hazard models in gender-stratified analyses were used to assess the association between phenogroup membership and risk of HF subtypes adjusting for potential confounders. In the 4,204 participants (mean age 61 ± 10 years, 53% women), the mean follow-up time was 14 ± 4 years for men and 15 ± 4 years for women. For both genders, 4 distinct phenogroups were identified: (1) ideal cardiac mechanics; (2) higher output/hypertrophied LV; (3) impaired ejection fraction/dilated LV; and (4) higher output/hyperdynamic (LV). Men in phenogroups 4 (hazard ratio [HR] 2.91, 95% confidence interval [CI] 1.60 to 5.31, p = 0.0005), 3 (HR 3.52, 95% CI 1.90 to 6.53, p <0.0001), and 2 (HR 3.49, 95% CI 1.94 to 6.28, p <0.0001) had higher rates of incident HF than did men in phenogroup 1, in fully adjusted models. No significant associations were found between phenogroup membership and incident HF in women. In conclusion, phenogroup membership based on cardiac structure and function in men was significantly associated with incident HF. Integration of cardiac magnetic resonance imaging variables may help identify differential risk for HF in men.
Artificial intelligence in heart failure and transplant
2023, Artificial Intelligence in Clinical Practice: How AI Technologies Impact Medical Research and Clinics
Several artificial intelligence (AI) and machine learning (ML) algorithms have been constructed for cardiovascular medicine applications. These models have the potential to positively augment decision-making at the detection, management, and transplantation stages, thereby enhancing personalization, efficiency, and outcomes. However, concerns regarding generalizability, interoperability, and interpretability hinder their adoption in the clinical setting. In this chapter, recent AI/ML developments for heart failure and cardiomyopathy are discussed. This discussion is contextualized to the basic principles of AI/ML, and relevant areas of emerging research are identified. The primary objective is to highlight the vast potential of these intelligent systems, yet also outline limitations that must be addressed prior to implementation. Although AI/ML algorithms offer a multitude of benefits for decision-making in heart failure and cardiomyopathy, they are not ready to be utilized autonomously. Instead, iterative refinement must take place to allow for their effective integration as decision-support tools for cardiovascular applications.
Automated Pattern Recognition in Whole-Cardiac Cycle Echocardiographic Data: Capturing Functional Phenotypes with Machine Learning
2021, Journal of the American Society of Echocardiography
Echocardiography provides complex data on cardiac function that can be integrated into patterns of dysfunction related to the severity of cardiac disease. The aim of this study was to demonstrate the feasibility of applying machine learning (ML) to automate the integration of echocardiographic data from the whole cardiac cycle and to automatically recognize patterns in velocity profiles and deformation curves, allowing the identification of functional phenotypes.
Echocardiography was performed in 189 clinically managed patients with hypertension and 97 healthy individuals without hypertension. Speckle-tracking analysis of the left ventricle and atrium was performed, and deformation curves were extracted. Aortic and mitral blood pool pulsed-wave Doppler and mitral annular tissue pulsed-wave Doppler velocity profiles were obtained. These whole–cardiac cycle deformation and velocity curves were used as ML input. Unsupervised ML was used to create a representation of patients with hypertension in a virtual space in which patients are positioned on the basis of the similarity of their integrated whole–cardiac cycle echocardiography data. Regression methods were used to explore patterns of echocardiographic traces within this virtual ML-derived space, while clustering was used to define phenogroups.
The algorithm captured different patterns in tissue and blood-pool velocity and deformation profiles and integrated the findings, yielding phenotypes related to normal cardiac function and others to advanced remodeling associated with pressure overload in hypertension. The addition of individuals without hypertension into the ML-derived space confirmed the interpretation of normal and remodeled phenotypes.
ML-based pattern recognition is feasible from echocardiographic data obtained during the whole cardiac cycle. Automated algorithms can consistently capture patterns in velocity and deformation data and, on the basis of these patterns, group patients into interpretable, clinically comprehensive phenogroups that describe structural and functional remodeling. Automated pattern recognition may potentially aid interpretation of imaging data and diagnostic accuracy.
Artificial intelligence applied to support medical decisions for the automatic analysis of echocardiogram images: A systematic review
2021, Artificial Intelligence in Medicine
Citation Excerpt :
The RF model was better, with an AUC of 0.881 for LVDD and 0.785 for LVH. Mishra et al. [111] highlighted that many individual echocardiographic variables are associated with patients with CAD. However, they have not been combined in prediction models.
The echocardiogram is a test that is widely used in Heart Disease Diagnoses. However, its analysis is largely dependent on the physician's experience. In this regard, artificial intelligence has become an essential technology to assist physicians. This study is a Systematic Literature Review (SLR) of primary state-of-the-art studies that used Artificial Intelligence (AI) techniques to automate echocardiogram analyses. Searches on the leading scientific article indexing platforms using a search string returned approximately 1400 articles. After applying the inclusion and exclusion criteria, 118 articles were selected to compose the detailed SLR. This SLR presents a thorough investigation of AI applied to support medical decisions for the main types of echocardiogram (Transthoracic, Transesophageal, Doppler, Stress, and Fetal). The article's data extraction indicated that the primary research interest of the studies comprised four groups: 1) Improvement of image quality; 2) identification of the cardiac window vision plane; 3) quantification and analysis of cardiac functions, and; 4) detection and classification of cardiac diseases. The articles were categorized and grouped to show the main contributions of the literature to each type of ECHO. The results indicate that the Deep Learning (DL) methods presented the best results for the detection and segmentation of the heart walls, right and left atrium and ventricles, and classification of heart diseases using images/videos obtained by echocardiography. The models that used Convolutional Neural Network (CNN) and its variations showed the best results for all groups. The evidence produced by the results presented in the tabulation of the studies indicates that the DL contributed significantly to advances in echocardiogram automated analysis processes. Although several solutions were presented regarding the automated analysis of ECHO, this area of research still has great potential for further studies to improve the accuracy of results already known in the literature.
Machine Learning in Cardiac Imaging: Exploring the Art of Cluster Analysis
2021, Journal of the American Society of Echocardiography
Explainable machine learning using echocardiography to improve risk prediction in patients with chronic coronary syndrome
2024, European Heart Journal - Digital Health

View all citing articles on Scopus

: Dr. Tison received support from the National Institutes of Health (NHLBI K23HL135274). The Heart and Soul Study was supported by grants from the Department of Veterans Affairs, the National Heart, Lung, and Blood Institute (HL079235), the American Federation for Aging Research, and the Robert Wood Johnson Foundation.

: Conflicts of Interest: None

^∗: Dr. Mishra acted as the corresponding author during the submission of this manuscript, but passed away prior to the article’s publication.

View full text

2019 Published by Elsevier Inc. on behalf of the American Society of Echocardiography.

Clinical InvestigationPredicting Heart Failure Risk from Echocardiograms of Coronary Artery Disease PatientsAssociation of Machine Learning–Derived Phenogroupings of Echocardiographic Variables with Heart Failure in Stable Coronary Artery Disease: The Heart and Soul Study

Highlights

Background

Methods

Results

Conclusions

Section snippets

Methods

Construction of Echocardiographic Phenogroupings

Discussion

Conclusion

Am J Cardiol

Am J Cardiol

J Am Soc Echocardiogr

Am J Cardiol

J Am Coll Cardiol

JACC Cardiovasc Imaging

JACC Cardiovasc Imaging

J Am Soc Echocardiogr

Am J Cardiol

J Am Coll Cardiol

Am J Cardiol

J Am Soc Echocardiogr

Am J Cardiol

J Am Soc Echocardiogr

Clinical Investigation
Predicting Heart Failure Risk from Echocardiograms of Coronary Artery Disease Patients
Association of Machine Learning–Derived Phenogroupings of Echocardiographic Variables with Heart Failure in Stable Coronary Artery Disease: The Heart and Soul Study