Federico M Asch1, Victor Mor-Avi2, David Rubenson3, Steven Goldstein4, Muhamed Saric5, Issam Mikati6, Samuel Surette7, Ali Chaudhry7, Nicolas Poilvert7, Ha Hong7, Russ Horowitz6, Daniel Park8, Jose L Diaz-Gomez9, Brandon Boesch10, Sara Nikravan11, Rachel B Liu12, Carolyn Philips4, James D Thomas6, Randolph P Martin7,13, Roberto M Lang2. 1. MedStar Health Research Institute, Washington, DC (F.M.A.). 2. University of Chicago, IL (V.M.-A., R.M.L.). 3. Scripps Clinic and Prebys Cardiovascular Institute, La Jolla, CA (D.R.). 4. MedStar Washington Hospital Center, DC (S.G., C.P.). 5. New York University Langone Health (M.S.). 6. Feinberg School of Medicine, Northwestern University, Chicago, IL (I.M., R.H., J.D.T.). 7. Caption Health Inc, San Francisco, CA (S.S., A.C., N.P., H.H., R.P.M.). 8. University of North Carolina Medical Center (D.P). 9. Baylor St. Luke's Medical Center, Houston, TX (J.L.D.-G.). 10. Highland Hospital, Oakland, CA (B.B.). 11. University of Washington Medical Center, Seattle (S.N.). 12. Yale School of Medicine, New Haven, CT (R.B.L.). 13. Emory University Medical Center, Atlanta, GA (R.P.M.).
Abstract
BACKGROUND: We have recently tested an automated machine-learning algorithm that quantifies left ventricular (LV) ejection fraction (EF) from guidelines-recommended apical views. However, in the point-of-care (POC) setting, apical 2-chamber views are often difficult to obtain, limiting the usefulness of this approach. Since most POC physicians often rely on visual assessment of apical 4-chamber and parasternal long-axis views, our algorithm was adapted to use either one of these 3 views or any combination. This study aimed to (1) test the accuracy of these automated estimates; (2) determine whether they could be used to accurately classify LV function. METHODS: Reference EF was obtained using conventional biplane measurements by experienced echocardiographers. In protocol 1, we used echocardiographic images from 166 clinical examinations. Both automated and reference EF values were used to categorize LV function as hyperdynamic (EF>73%), normal (53%-73%), mildly-to-moderately (30%-52%), or severely reduced (<30%). Additionally, LV function was visually estimated for each view by 10 experienced physicians. Accuracy of the detection of reduced LV function (EF<53%) by the automated classification and physicians' interpretation was assessed against the reference classification. In protocol 2, we tested the new machine-learning algorithm in the POC setting on images acquired by nurses using a portable imaging system. RESULTS: Protocol 1: the agreement with the reference EF values was good (intraclass correlation, 0.86-0.95), with biases <2%. Machine-learning classification of LV function showed similar accuracy to that by physicians in most views, with only 10% to 15% cases where it was less accurate. Protocol 2: the agreement with the reference values was excellent (intraclass correlation=0.84) with a minimal bias of 2.5±6.4%. CONCLUSIONS: The new machine-learning algorithm allows accurate automated evaluation of LV function from echocardiographic views commonly used in the POC setting. This approach will enable more POC personnel to accurately assess LV function.
BACKGROUND: We have recently tested an automated machine-learning algorithm that quantifies left ventricular (LV) ejection fraction (EF) from guidelines-recommended apical views. However, in the point-of-care (POC) setting, apical 2-chamber views are often difficult to obtain, limiting the usefulness of this approach. Since most POC physicians often rely on visual assessment of apical 4-chamber and parasternal long-axis views, our algorithm was adapted to use either one of these 3 views or any combination. This study aimed to (1) test the accuracy of these automated estimates; (2) determine whether they could be used to accurately classify LV function. METHODS: Reference EF was obtained using conventional biplane measurements by experienced echocardiographers. In protocol 1, we used echocardiographic images from 166 clinical examinations. Both automated and reference EF values were used to categorize LV function as hyperdynamic (EF>73%), normal (53%-73%), mildly-to-moderately (30%-52%), or severely reduced (<30%). Additionally, LV function was visually estimated for each view by 10 experienced physicians. Accuracy of the detection of reduced LV function (EF<53%) by the automated classification and physicians' interpretation was assessed against the reference classification. In protocol 2, we tested the new machine-learning algorithm in the POC setting on images acquired by nurses using a portable imaging system. RESULTS: Protocol 1: the agreement with the reference EF values was good (intraclass correlation, 0.86-0.95), with biases <2%. Machine-learning classification of LV function showed similar accuracy to that by physicians in most views, with only 10% to 15% cases where it was less accurate. Protocol 2: the agreement with the reference values was excellent (intraclass correlation=0.84) with a minimal bias of 2.5±6.4%. CONCLUSIONS: The new machine-learning algorithm allows accurate automated evaluation of LV function from echocardiographic views commonly used in the POC setting. This approach will enable more POC personnel to accurately assess LV function.
Entities:
Keywords:
algorithm; artificial intelligence; echocardiography; machine learning; ventricular function, left
Authors: Sergio Sanchez-Martinez; Oscar Camara; Gemma Piella; Maja Cikes; Miguel Ángel González-Ballester; Marius Miron; Alfredo Vellido; Emilia Gómez; Alan G Fraser; Bart Bijnens Journal: Front Cardiovasc Med Date: 2022-01-04