Key result
ML strain imaging outperforms EF and GLS in detecting severe AS with ~0.97 AUC.
Why the study?
Current echocardiographic measures like EF are insensitive to minor LV dysfunction changes in aortic stenosis, while strain imaging is usually limited to GLS due to robustness issues.
Does a machine learning-based strain imaging algorithm improve the detection of left ventricular dysfunction in severe aortic stenosis patients compared to ejection fraction and global longitudinal strain?
Observational (n=497)
Does a machine learning-based strain imaging algorithm improve the detection of left ventricular dysfunction in severe aortic stenosis patients compared to ejection fraction and global longitudinal strain?
A novel machine learning-based strain imaging algorithm significantly improves the detection of left ventricular dysfunction in severe aortic stenosis compared to traditional ejection fraction and global longitudinal strain.
ML strain imaging may aid severe AS detection; hypothesis-generating and requires prospective validation before clinical use.
Purpose Aortic stenosis (AS) is a common cardiovascular condition where early detection of left ventricular (LV) dysfunction is essential for timely intervention and optimal management. Current echocardiographic measurements, such as ejection fraction (EF), are insensitive to minor changes in LV function, and strain imaging is typically limited to the global longitudinal strain (GLS) parameter due to robustness issues. This study introduces a novel, fully automatic algorithm to enhance the detection of LV dysfunction in AS patients using multiple strain imaging parameters. Methods We applied supervised machine‐learning techniques to classify data from 82 severe AS patients, 96 chest pain subjects, and 319 healthy volunteers. Results Our model significantly outperformed EF and GLS in distinguishing AS patients from healthy volunteers (area under the curve [AUC] = 0.97 vs. 0.88 and 0.82, respectively). It also surpassed EF and GLS in differentiating AS patients from chest pain subjects (AUC = 0.95 vs. 0.90 and 0.55, respectively). Conclusion This novel, clinically interpretable model leverages the potential of strain imaging to enhance diagnostic accuracy and guide clinical decision‐making in LV dysfunction, thereby improving clinical practice.
No takes yet. Share an insight, caveat, or question.
Yahav et al. (2024) conducted an observational in Aortic stenosis (n=497). Machine learning-based strain imaging algorithm vs. Ejection fraction (EF) and global longitudinal strain (GLS) was evaluated on Distinguishing aortic stenosis patients from healthy volunteers (AUC). A machine learning-based strain imaging algorithm outperformed ejection fraction and global longitudinal strain in distinguishing severe aortic stenosis patients from healthy volunteers (AUC 0.97 vs 0.88 and 0.82).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: