Human Versus Artificial Intelligence–Based Echocardiographic Analysis As a Predictor of Outcomes: An Analysis From the World Alliance Societies of Echocardiography Covid Study

Human Versus Artificial Intelligence–Based Echocardiographic Analysis As a Predictor of Outcomes: An Analysis From the World Alliance Societies of Echocardiography Covid Study Publisher Pubmed

Asch FM¹ ; Descamps T² ; Sarwar R³ ; Karagodin I⁴ ; Singulane CC⁴ ; Xie M⁵ ; Tucay ES⁶ ; Tude Rodrigues AC⁷ ; Vasquezortiz ZY⁸ ; Monaghan MJ⁹ ; Ordonez Salazar BA¹⁰ ; Soulatdufour L¹¹ ; Alizadehasl A¹² ; Mostafavi A¹³ Show All Authors

Asch FM¹
Descamps T²
Sarwar R³
Karagodin I⁴
Singulane CC⁴
Xie M⁵
Tucay ES⁶
Tude Rodrigues AC⁷
Vasquezortiz ZY⁸
Monaghan MJ⁹
Ordonez Salazar BA¹⁰
Soulatdufour L¹¹
Alizadehasl A¹²
Mostafavi A¹³
Moreo A¹⁴
Citro R¹⁵
Narang A¹⁶
Wu C⁵
Addetia K⁴
Upton R²
Woodward GM²
Lang RM⁴

Show Affiliations

1. MedStar Health Research Institute and Georgetown University, Washington, District of Columbia
2. Ultromics, Oxford, United Kingdom
3. Experimental Therapeutics, Radcliffe Department of Medicine, University of Oxford, Oxford, United Kingdom
4. University of Chicago, Chicago, Illinois, United States
5. Union Hospital, Tongji Medical College of HUST, Wuhan, China
6. Philippine Heart Center, Quezon City, Philippines
7. Radiology Institute of the University of Sao Paulo Medical School, Sao Paulo, Brazil
8. Instituto Nacional de Ciencias Medicas y Nutricion Salvador Zubiran, Mexico City, Mexico
9. King's College Hospital, London, United Kingdom
10. Centro Medico Nacional 20 de Noviembre, ISSSTE, Mexico City, Mexico
11. Saint Antoine and Tenon Hospital, AP-HP, INSERM UMRS-ICAN 1166 and Sorbonne Universite, Paris, France
12. Rajaie Cardiovascular Medical and Research Center, Echocardiography Research Center, Iran University of Medical Science, Tehran, Iran
13. Baharloo Hospital, Tehran University of Medical Sciences, Tehran, Iran
14. De Gasperis Cardio Center, Niguarda Hospital, Milan, Italy
15. University of Salerno, Salerno, Italy
16. Northwestern University, Chicago, Illinois, United States

Source: Journal of the American Society of Echocardiography Published:2022

Abstract

Background: Transthoracic echocardiography is the leading cardiac imaging modality for patients admitted with COVID-19, a condition of high short-term mortality. The aim of this study was to test the hypothesis that artificial intelligence (AI)–based analysis of echocardiographic images could predict mortality more accurately than conventional analysis by a human expert. Methods: Patients admitted to 13 hospitals for acute COVID-19 who underwent transthoracic echocardiography were included. Left ventricular ejection fraction (LVEF) and left ventricular longitudinal strain (LVLS) were obtained manually by multiple expert readers and by automated AI software. The ability of the manual and AI analyses to predict all-cause mortality was compared. Results: In total, 870 patients were enrolled. The mortality rate was 27.4% after a mean follow-up period of 230 ± 115 days. AI analysis had lower variability than manual analysis for both LVEF (P = .003) and LVLS (P = .005). AI-derived LVEF and LVLS were predictors of mortality in univariable and multivariable regression analysis (odds ratio, 0.974 [95% CI, 0.956-0.991; P = .003] for LVEF; odds ratio, 1.060 [95% CI, 1.019-1.105; P = .004] for LVLS), but LVEF and LVLS obtained by manual analysis were not. Direct comparison of the predictive value of AI versus manual measurements of LVEF and LVLS showed that AI was significantly better (P = .005 and P = .003, respectively). In addition, AI-derived LVEF and LVLS had more significant and stronger correlations to other objective biomarkers of acute disease than manual reads. Conclusions: AI-based analysis of LVEF and LVLS had similar feasibility as manual analysis, minimized variability, and consequently increased the statistical power to predict mortality. AI-based, but not manual, analyses were a significant predictor of in-hospital and follow-up mortality. © 2022 American Society of Echocardiography

Related Docs

View other Related Docs

1. Echocardiographic Correlates of In-Hospital Death in Patients With Acute Covid-19 Infection: The World Alliance Societies of Echocardiography (Wase-Covid) Study, Journal of the American Society of Echocardiography (2021)

2. 2D Speckle-Tracking Echocardiography As a Prognostic Imaging Modality for Covid-19 Adverse Outcomes, Future Cardiology (2022)

3. Ventricular Changes in Patients With Acute Covid-19 Infection: Follow-Up of the World Alliance Societies of Echocardiography (Wase-Covid) Study, Journal of the American Society of Echocardiography (2022)

4. Carpnet: Transformer for Mitral Valve Disease Classification in Echocardiographic Videos, International Journal of Imaging Systems and Technology (2023)

5. A Deep Learning Approach for the Automatic Recognition of Prosthetic Mitral Valve in Echocardiographic Images, Computers in Biology and Medicine (2021)

6. Paradoxical Increase in Left Atrial Strains Early After Covid-19 Infection, a Result of Comprehensive Recovery Phase Four-Chamber Strains Study, International Journal of Cardiovascular Imaging (2023)

7. Cardiovascular Diseases Burden in Covid-19: Systematic Review and Meta-Analysis, American Journal of Emergency Medicine (2021)

8. Comprehensive Review of Cardiovascular Complications of Coronavirus Disease 2019 and Beneficial Treatments, Cardiology in Review (2022)

Experts (# of related papers)

View all Related Experts

Nima Rezaei (2)

Atoosa Mostafavi (2)

Style	Citing Format
MLA	Asch FM, et al.. "Human Versus Artificial Intelligence–Based Echocardiographic Analysis As a Predictor of Outcomes: An Analysis From the World Alliance Societies of Echocardiography Covid Study." Journal of the American Society of Echocardiography, vol. 35, no. 12, 2022, pp. 1226-1237.e7.
APA	Asch FM, Descamps T, Sarwar R, Karagodin I, Singulane CC, Xie M, Tucay ES, Tude Rodrigues AC, Vasquezortiz ZY, Monaghan MJ, Ordonez Salazar BA, Soulatdufour L, Alizadehasl A, Mostafavi A, Moreo A, Citro R, Narang A, Wu C, Addetia K, ... Lang RM (2022). Human Versus Artificial Intelligence–Based Echocardiographic Analysis As a Predictor of Outcomes: An Analysis From the World Alliance Societies of Echocardiography Covid Study. Journal of the American Society of Echocardiography, 35(12), 1226-1237.e7.
Chicago	Asch FM, Descamps T, Sarwar R, Karagodin I, Singulane CC, Xie M, Tucay ES, et al.. "Human Versus Artificial Intelligence–Based Echocardiographic Analysis As a Predictor of Outcomes: An Analysis From the World Alliance Societies of Echocardiography Covid Study." Journal of the American Society of Echocardiography 35, no. 12 (2022): 1226-1237.e7.
Harvard	Asch FM et al. (2022) 'Human Versus Artificial Intelligence–Based Echocardiographic Analysis As a Predictor of Outcomes: An Analysis From the World Alliance Societies of Echocardiography Covid Study', Journal of the American Society of Echocardiography, 35(12), pp. 1226-1237.e7.
Vancouver	Asch FM, Descamps T, Sarwar R, Karagodin I, Singulane CC, Xie M, et al.. Human Versus Artificial Intelligence–Based Echocardiographic Analysis As a Predictor of Outcomes: An Analysis From the World Alliance Societies of Echocardiography Covid Study. Journal of the American Society of Echocardiography. 2022;35(12):1226-1237.e7.
BibTex	@article{ author = {Asch FM and Descamps T and Sarwar R and Karagodin I and Singulane CC and Xie M and Tucay ES and Tude Rodrigues AC and Vasquezortiz ZY and Monaghan MJ and Ordonez Salazar BA and Soulatdufour L and Alizadehasl A and Mostafavi A and Moreo A and Citro R and Narang A and Wu C and Addetia K and Upton R and Woodward GM and Lang RM}, title = {Human Versus Artificial Intelligence–Based Echocardiographic Analysis As a Predictor of Outcomes: An Analysis From the World Alliance Societies of Echocardiography Covid Study}, journal = {Journal of the American Society of Echocardiography}, volume = {35}, number = {12}, pages = {1226-1237.e7}, year = {2022} }
RIS	TY - JOUR AU - Asch FM AU - Descamps T AU - Sarwar R AU - Karagodin I AU - Singulane CC AU - Xie M AU - Tucay ES AU - Tude Rodrigues AC AU - Vasquezortiz ZY AU - Monaghan MJ AU - Ordonez Salazar BA AU - Soulatdufour L AU - Alizadehasl A AU - Mostafavi A AU - Moreo A AU - Citro R AU - Narang A AU - Wu C AU - Addetia K AU - Upton R AU - Woodward GM AU - Lang RM TI - Human Versus Artificial Intelligence–Based Echocardiographic Analysis As a Predictor of Outcomes: An Analysis From the World Alliance Societies of Echocardiography Covid Study JO - Journal of the American Society of Echocardiography VL - 35 IS - 12 SP - 1226 EP - 1237.e7 PY - 2022 ER -

Science Communicator Platform

Authors

Authors Affiliations

Abstract