Your browser doesn't support javascript.
Human versus Artificial Intelligence-Based Echocardiographic Analysis as a Predictor of Outcomes: An Analysis from the World Alliance Societies of Echocardiography COVID Study.
Asch, Federico M; Descamps, Tine; Sarwar, Rizwan; Karagodin, Ilya; Singulane, Cristiane Carvalho; Xie, Mingxing; Tucay, Edwin S; Tude Rodrigues, Ana C; Vasquez-Ortiz, Zuilma Y; Monaghan, Mark J; Ordonez Salazar, Bayardo A; Soulat-Dufour, Laurie; Alizadehasl, Azin; Mostafavi, Atoosa; Moreo, Antonella; Citro, Rodolfo; Narang, Akhil; Wu, Chun; Addetia, Karima; Upton, Ross; Woodward, Gary M; Lang, Roberto M.
  • Asch FM; MedStar Health Research Institute and Georgetown University, Washington, District of Columbia. Electronic address: federico.asch@medstar.net.
  • Descamps T; Ultromics, Oxford, United Kingdom.
  • Sarwar R; Experimental Therapeutics, Radcliffe Department of Medicine, University of Oxford, Oxford, United Kingdom.
  • Karagodin I; University of Chicago, Chicago, Illinois.
  • Singulane CC; University of Chicago, Chicago, Illinois.
  • Xie M; Union Hospital, Tongji Medical College of HUST, Wuhan, China.
  • Tucay ES; Philippine Heart Center, Quezon City, Philippines.
  • Tude Rodrigues AC; Radiology Institute of the University of São Paulo Medical School, São Paulo, Brazil.
  • Vasquez-Ortiz ZY; Instituto Nacional de Ciencias Medicas y Nutricion Salvador Zubiran, Mexico City, Mexico.
  • Monaghan MJ; King's College Hospital, London, United Kingdom.
  • Ordonez Salazar BA; Centro Medico Nacional 20 de Noviembre, ISSSTE, Mexico City, Mexico.
  • Soulat-Dufour L; Saint Antoine and Tenon Hospital, AP-HP, INSERM UMRS-ICAN 1166 and Sorbonne Université, Paris, France.
  • Alizadehasl A; Rajaie Cardiovascular Medical and Research Center, Echocardiography Research Center, Iran University of Medical Science, Tehran, Iran.
  • Mostafavi A; Baharloo Hospital, Tehran University of Medical Sciences, Tehran, Iran.
  • Moreo A; De Gasperis Cardio Center, Niguarda Hospital, Milan, Italy.
  • Citro R; University of Salerno, Salerno, Italy.
  • Narang A; Northwestern University, Chicago, Illinois.
  • Wu C; Union Hospital, Tongji Medical College of HUST, Wuhan, China.
  • Addetia K; University of Chicago, Chicago, Illinois.
  • Upton R; Ultromics, Oxford, United Kingdom.
  • Woodward GM; Ultromics, Oxford, United Kingdom.
  • Lang RM; University of Chicago, Chicago, Illinois.
J Am Soc Echocardiogr ; 35(12): 1226-1237.e7, 2022 Dec.
Article in English | MEDLINE | ID: covidwho-2095271
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.
Subject(s)
Keywords

Full text: Available Collection: International databases Database: MEDLINE Main subject: Ventricular Function, Left / COVID-19 Type of study: Cohort study / Diagnostic study / Observational study / Prognostic study / Randomized controlled trials Limits: Humans Language: English Journal: J Am Soc Echocardiogr Journal subject: Diagnostic Imaging Year: 2022 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: Ventricular Function, Left / COVID-19 Type of study: Cohort study / Diagnostic study / Observational study / Prognostic study / Randomized controlled trials Limits: Humans Language: English Journal: J Am Soc Echocardiogr Journal subject: Diagnostic Imaging Year: 2022 Document Type: Article