September 4, 2024Mayo Clinic Proceedings Digital HealthOpen Access

Echocardiographic Diagnosis of Hypertrophic Cardiomyopathy by Machine Learning

View Full Paper

Ask AI

Bookmark

Authors

NFNasibeh Zanjirani FarahaniWinnMed MAMateo Alzate AguirreMayo Clinic in Arizona VVVanessa Karlinski VizentinTwitter (United States)

Discussion

Member takes

Implication

Case-control study demonstrates high diagnostic accuracy in hypertrophic cardiomyopathy patients, indicating adding strain metrics improves machine learning performance.

Key Points

Automated random forest machine learning models accurately identify hypertrophic cardiomyopathy cases using standard echocardiographic metrics.
Model performance achieved an area under the curve of 0.98 using individual strain measurements, compared to 0.92 without strain data across cohorts.
Case-control cohort training using ten-fold crossvalidation indicates that adding global longitudinal strain metrics substantially improves automated detection.

Cite This Study

Farahani et al. (2024) studied this question.

synapsesocial.com/papers/68e5969ab6db643587531a5d https://doi.org/10.1016/j.mcpdig.2024.08.009

View Full Paper

Ask AI

Bookmark

September 4, 2024Mayo Clinic Proceedings Digital HealthOpen Access

Echocardiographic Diagnosis of Hypertrophic Cardiomyopathy by Machine Learning

View Full Paper

Ask AI

Bookmark

Authors

NFNasibeh Zanjirani FarahaniWinnMed MAMateo Alzate AguirreMayo Clinic in Arizona VVVanessa Karlinski VizentinTwitter (United States)

Discussion

Member takes

Implication

Case-control study demonstrates high diagnostic accuracy in hypertrophic cardiomyopathy patients, indicating adding strain metrics improves machine learning performance.

Key Points

Automated random forest machine learning models accurately identify hypertrophic cardiomyopathy cases using standard echocardiographic metrics.
Model performance achieved an area under the curve of 0.98 using individual strain measurements, compared to 0.92 without strain data across cohorts.
Case-control cohort training using ten-fold crossvalidation indicates that adding global longitudinal strain metrics substantially improves automated detection.

Cite This Study

Farahani et al. (2024) studied this question.

synapsesocial.com/papers/68e5969ab6db643587531a5d https://doi.org/10.1016/j.mcpdig.2024.08.009

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark