TY - JOUR
T1 - Fully Automated Artificial Intelligence Assessment of Aortic Stenosis by Echocardiography
AU - Krishna, Hema
AU - Desai, Kevin
AU - Slostad, Brody
AU - Bhayani, Siddharth
AU - Arnold, Joshua H.
AU - Ouwerkerk, Wouter
AU - Hummel, Yoran
AU - Lam, Carolyn S.P.
AU - Ezekowitz, Justin
AU - Frost, Matthew
AU - Jiang, Zhubo
AU - Equilbec, Cyril
AU - Twing, Aamir
AU - Pellikka, Patricia A.
AU - Frazin, Leon
AU - Kansal, Mayank
N1 - Publisher Copyright: © 2023
PY - 2023/7/1
Y1 - 2023/7/1
N2 - BACKGROUND: Aortic stenosis (AS) is a common form of valvular heart disease, present in over 12% of the population age 75 years and above. Transthoracic echocardiography (TTE) is the first line of imaging in the adjudication of AS severity but is time-consuming and requires expert sonographic and interpretation capabilities to yield accurate results. Artificial intelligence (AI) technology has emerged as a useful tool to address these limitations but has not yet been applied in a fully hands-off manner to evaluate AS. Here, we correlate artificial neural network measurements of key hemodynamic AS parameters to experienced human reader assessment. METHODS: Two-dimensional and Doppler echocardiographic images from patients with normal aortic valves and all degrees of AS were analyzed by an artificial neural network (Us2.ai) with no human input to measure key variables in AS assessment. Trained echocardiographers blinded to AI data performed manual measurements of these variables, and correlation analyses were performed. RESULTS: Our cohort included 256 patients with an average age of 67.6 ± 9.5 years. Across all AS severities, AI closely matched human measurement of aortic valve peak velocity (r = 0.97, P < .001), mean pressure gradient (r = 0.94, P < .001), aortic valve area by continuity equation (r = 0.88, P < .001), stroke volume index (r = 0.79, P < .001), left ventricular outflow tract velocity-time integral (r = 0.89, P < .001), aortic valve velocity-time integral (r = 0.96, P < .001), and left ventricular outflow tract diameter (r = 0.76, P < .001). CONCLUSIONS: Artificial neural networks have the capacity to closely mimic human measurement of all relevant parameters in the adjudication of AS severity. Application of this AI technology may minimize interscan variability, improve interpretation and diagnosis of AS, and allow for precise and reproducible identification and management of patients with AS.
AB - BACKGROUND: Aortic stenosis (AS) is a common form of valvular heart disease, present in over 12% of the population age 75 years and above. Transthoracic echocardiography (TTE) is the first line of imaging in the adjudication of AS severity but is time-consuming and requires expert sonographic and interpretation capabilities to yield accurate results. Artificial intelligence (AI) technology has emerged as a useful tool to address these limitations but has not yet been applied in a fully hands-off manner to evaluate AS. Here, we correlate artificial neural network measurements of key hemodynamic AS parameters to experienced human reader assessment. METHODS: Two-dimensional and Doppler echocardiographic images from patients with normal aortic valves and all degrees of AS were analyzed by an artificial neural network (Us2.ai) with no human input to measure key variables in AS assessment. Trained echocardiographers blinded to AI data performed manual measurements of these variables, and correlation analyses were performed. RESULTS: Our cohort included 256 patients with an average age of 67.6 ± 9.5 years. Across all AS severities, AI closely matched human measurement of aortic valve peak velocity (r = 0.97, P < .001), mean pressure gradient (r = 0.94, P < .001), aortic valve area by continuity equation (r = 0.88, P < .001), stroke volume index (r = 0.79, P < .001), left ventricular outflow tract velocity-time integral (r = 0.89, P < .001), aortic valve velocity-time integral (r = 0.96, P < .001), and left ventricular outflow tract diameter (r = 0.76, P < .001). CONCLUSIONS: Artificial neural networks have the capacity to closely mimic human measurement of all relevant parameters in the adjudication of AS severity. Application of this AI technology may minimize interscan variability, improve interpretation and diagnosis of AS, and allow for precise and reproducible identification and management of patients with AS.
KW - Aortic stenosis
KW - Artificial intelligence
KW - Doppler
KW - Echocardiography
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=85163729445&partnerID=8YFLogxK
U2 - https://doi.org/10.1016/j.echo.2023.03.008
DO - https://doi.org/10.1016/j.echo.2023.03.008
M3 - Article
C2 - 36958708
SN - 0894-7317
VL - 36
SP - 769
EP - 777
JO - Journal of the American Society of Echocardiography
JF - Journal of the American Society of Echocardiography
IS - 7
ER -