Fully Automated Artificial Intelligence Assessment of Aortic Stenosis by Echocardiography - 05/07/23
Abstract |
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.
Il testo completo di questo articolo è disponibile in PDF.Highlights |
• | AI was applied to echocardiograms with normal AVs and AS. |
• | AI and human measurements of AV Doppler and area measurements were closely matched. |
• | Artificial neural networks have the capacity to mimic human measurements in AS. |
Keywords : Aortic stenosis, Echocardiography, Doppler, Artificial intelligence, Machine learning
Abbreviations : 2D, AI, AS, AV, AVA, AVR, FDA, HEART, IEC, LVEF, LVOT, LVOTd, MPG, POCUS, SVi, TTE, Vmax, VTI
Mappa
| Given her role as Editor-in-Chief, Patricia A. Pellikka, MD, had no involvement in the peer review of this article and has no access to information regarding its peer review. Full responsibility for the editorial process for this article was delegated to Partho P. Sengupta, MD. |
|
| Conflicts of Interest: Y.H., M.F., Z.J., and C.E. are employees of Us2.ai. W.O. is co-owner of a patent entitled “Automatic clinical workflow that recognizes and analyses 2D and Doppler modality echocardiogram images for automated cardiac measurements and the diagnosis, prediction and prognosis of heart disease” related to the present work. In addition, W.O. is scientific advisor of Us2.ai and holds equity in the company. C.S.P.L. is supported by a Clinician Scientist Award from the National Medical Research Council of Singapore; has received research support from Bayer and Roche Diagnostics; has served as consultant or on the Advisory Board/Steering Committee/Executive Committee for Actelion, Alleviant Medical, Allysta Pharma, Amgen, AnaCardio AB, Applied Therapeutics, AstraZeneca, Bayer, Boehringer Ingelheim, Boston Scientific, Cytokinetics, Darma, EchoNous, Eli Lilly, Impulse Dynamics, Intellia Therapeutics, Ionis Pharmaceutical, Janssen Research and Development LLC, Medscape/WebMD Global LLC, Merck, Novartis, Novo Nordisk, Prosciento, Radcliffe Group, ReCor Medical, Roche Diagnostics, Sanofi, Siemens Healthcare Diagnostics, and Us2.ai; and serves as cofounder and nonexecutive director of Us2.ai. J.E. reports research support for trial leadership from Bayer, Merck, Novo Nordisk, Cytokinetics, Applied Therapeutics, and American Regent and honoraria for consultancy from AstraZeneca, Boehringer Ingelheim, Novo Nordisk, Otsuka, Bayer, and Novartis and serves as an advisor to US2.ai. The remaining authors have nothing to disclose. |
Vol 36 - N° 7
P. 769-777 - luglio 2023 Ritorno al numero
Articolo precedente
- Clinical and Echocardiographic Features of Patients With Infective Endocarditis and Bicuspid Aortic Valve According to Echocardiographic Definition of Valve Morphology
- Rossella Maria Benvenga, Christophe Tribouilloy, Hector I. Michelena, Angelo Silverio, Florent Arregle, Hélène Martel, Seyhan Denev, Yohann Bohbot, Sandrine Hubert, Sébastien Renard, Laurence Camoin, Anne Claire Casalta, Jean Paul Casalta, Frédérique Gouriet, Alberto Riberi, Hubert Lepidi, Frederic Collart, Didier Raoult, Michel Drancourt, Gennaro Galasso, Daniel C. DeSimone, Rodolfo Citro, Gilbert Habib
- Unsupervised Time-Series Clustering of Left Atrial Strain for Cardiovascular Risk Assessment
- Evangelos Ntalianis, František Sabovčik, Nicholas Cauwenberghs, Dmitry Kouznetsov, Yne Daels, Piet Claus, Tatiana Kuznetsova
Benvenuto su EM|consulte, il riferimento dei professionisti della salute.
L'accesso al testo integrale di questo articolo richiede un abbonamento.
Già abbonato a @@106933@@ rivista ?