Clarius Ejection Fraction AI

Clarius Ejection Fraction AI is a machine learning algorithm integrated into the Clarius App software that uses deep learning to automatically measure left ventricular ejection fraction from ultrasound images acquired by Clarius ultrasound scanners. It is intended for semi-automatic, non-invasive measurement of cardiac function in adult patients, with trained healthcare professionals retaining responsibility for validating measurements based on clinical judgment.

Both the subject device and predicate device employ ultrasound image processing software using artificial intelligence/machine learning algorithms trained on clinical and/or artificial data for detection, segmentation, and measurement of left ventricular ejection fraction. Both support segmentation of cardiac anatomy, automated measurement calculation, and manual adjustment capability. Both are non-adaptive machine learning systems intended for professional healthcare settings with licensed users.

IEC 62304:2006 + A1:2015 (medical device software life cycle processes), ISO 14971:2019 (risk management), IEC 62366-1:2015 + A1:2020 (usability engineering), and ISO 15223-1:2021 (medical device symbols and labeling).

Clarius Ejection Fraction AI is substantially equivalent to Caption Interpretation Automated Ejection Fraction Software (K210747) because both devices employ identical regulatory classifications, principles of operation, and AI/ML algorithmic approaches for left ventricular ejection fraction measurement. Clinical verification testing demonstrated Clarius EF measurements are non-inferior to expert clinician measurements with statistically significant p-values across multiple cardiac views, and the device performs as intended for semi-automated cardiac ultrasound applications.