What does this research mean for the field?

An ensemble machine-learning model improves sensitivity and specificity for discriminating hypertrophic cardiomyopathy from athlete's heart compared to conventional echocardiographic parameters. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This study aimed to assess the diagnostic efficacy of machine-learning models for differentiating hypertrophic cardiomyopathy from physiological hypertrophy.

May 18, 2026Journal of the American College of Cardiology

Machine-Learning Algorithms to Automate Morphological and Functional Assessments in 2D Echocardiography

Q: What are the key findings of this study?

An ensemble machine-learning model improved sensitivity and specificity for discriminating HCM from athlete's heart compared with conventional echocardiographic parameters (p<0.01).

Q: What is the clinical evidence from this study?

Study design: Observational. Population: Hypertrophic cardiomyopathy and physiological hypertrophy (n=139). Intervention: Ensemble machine-learning model vs. Conventional echocardiographic parameters (E/A ratio, e', and strain). Primary outcome: Discrimination of hypertrophic cardiomyopathy from physiological hypertrophy (p=<0.01).

View Full Paper

Ask AI

Bookmark

Key result

Ensemble machine-learning model outperforms conventional echo for discriminating HCM from athlete's heart.

P<0.01
n=139

Why the study?

Machine-learning models may aid cardiac phenotypic recognition using cardiac tissue deformation, prompting evaluation of a framework incorporating speckle-tracking echocardiography to discriminate HCM from athlete physiological hypertrophy.

Does an ensemble machine-learning model using speckle-tracking echocardiographic data improve the discrimination of hypertrophic cardiomyopathy from physiological hypertrophy in athletes compared to conventional echocardiographic parameters?

Population

77 athletes and 62 HCM patients

Comparison

Ensemble machine-learning model vs conventional echocardiographic parameters

Design

Machine-learning model development and cross-validation study

Authors

SNSukrit NarulaYale University KSKhader ShameerTarget (United States)AOAlaa Mabrouk Salem OmarMount Sinai Hospital

Discussion

Member takes

Implication

May aid echo differentiation of HCM from athlete's heart; leaves open prospective validation before clinical use.

Key Points

This study aimed to assess the diagnostic efficacy of machine-learning models for differentiating hypertrophic cardiomyopathy from physiological hypertrophy.
Utilized 139 echocardiographic datasets (77 ATH, 62 HCM) for model development.
Developed an ensemble machine-learning model using support vector machines, random forests, and artificial neural networks.
Conducted K-fold cross-validation and majority voting for predictive accuracy.
Volume was identified as the best predictor for differentiation between HCM and ATH (IG = 0.24).
The ensemble model demonstrated increased sensitivity and specificity compared to traditional measures (p < 0.01).
In younger HCM patients, the automated model maintained sensitivity and exhibited greater specificity compared to early diastolic measures.

Study Design

Type

Observational (n=139)

Structured PICO

Population

139 individuals (77 athletes [ATH] with physiological hypertrophy and 62 patients with hypertrophic cardiomyopathy [HCM])

Intervention

Ensemble machine-learning model (support vector machines, random forests, and artificial neural networks) incorporating speckle-tracking echocardiographic data

Comparator

Conventional echocardiographic parameters (early-to-late diastolic transmitral velocity ratio, average early diastolic tissue velocity [e'], and strain)

Outcome

Automated discrimination of hypertrophic cardiomyopathy (HCM) from physiological hypertrophy seen in athletes (ATH)surrogate

Main Result

p-value: p=<0.01

An ensemble machine-learning model using speckle-tracking echocardiographic data improves the discrimination between hypertrophic cardiomyopathy and physiological athlete's heart compared to conventional echocardiographic parameters.

Cite This Study

Narula et al. (2016) conducted an observational in Hypertrophic cardiomyopathy and physiological hypertrophy (n=139). Ensemble machine-learning model vs. Conventional echocardiographic parameters (E/A ratio, e', and strain) was evaluated on Discrimination of hypertrophic cardiomyopathy from physiological hypertrophy (p=<0.01). An ensemble machine-learning model improved sensitivity and specificity for discriminating HCM from athlete's heart compared with conventional echocardiographic parameters (p<0.01).

synapsesocial.com/papers/6a0b2de23a96fd342f4319bd https://doi.org/10.1016/j.jacc.2016.08.062

Topics

Echocardiography Hypertrophic cardiomyopathy Sports cardiology

View Full Paper

Ask AI

Bookmark

Machine-Learning Algorithms to Automate Morphological and Functional Assessments in 2D Echocardiography

Discussion

Member takes

Implication

Key Points

Study Design

Structured PICO

Main Result

Cite This Study

Topics

Machine-Learning Algorithms to Automate Morphological and Functional Assessments in 2D Echocardiography

Discussion

Member takes

Implication

Key Points

Study Design

Structured PICO

Main Result

Cite This Study

Also Consider

Topics

Also Consider