Deep learning evaluation of biomarkers from echocardiogram videos.

Autor:	Hughes JW; Department of Computer Science, Stanford University, Palo Alto, CA 94025., Yuan N; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, 90048., He B; Department of Computer Science, Stanford University, Palo Alto, CA 94025., Ouyang J; Department of Electrical Engineering, Stanford University, Palo Alto, CA, 94025., Ebinger J; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, 90048., Botting P; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, 90048., Lee J; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, 90048., Theurer J; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, 90048., Tooley JE; Department of Medicine, Stanford University, Palo Alto, CA, 94025., Nieman K; Department of Medicine, Stanford University, Palo Alto, CA, 94025; Department of Radiology, Stanford University, Palo Alto, CA, 94025., Lungren MP; Department of Radiology, Stanford University, Palo Alto, CA, 94025., Liang DH; Department of Medicine, Stanford University, Palo Alto, CA, 94025., Schnittger I; Department of Medicine, Stanford University, Palo Alto, CA, 94025., Chen JH; Department of Medicine, Stanford University, Palo Alto, CA, 94025., Ashley EA; Department of Medicine, Stanford University, Palo Alto, CA, 94025., Cheng S; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, 90048., Ouyang D; Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, 90048. Electronic address: david.ouyang@cshs.org., Zou JY; Department of Computer Science, Stanford University, Palo Alto, CA 94025; Department of Electrical Engineering, Stanford University, Palo Alto, CA, 94025; Department of Biomedical Data Science, Stanford University, Palo Alto, CA, 94025. Electronic address: jamesz@stanford.edu.
Jazyk:	angličtina
Zdroj:	EBioMedicine [EBioMedicine] 2021 Nov; Vol. 73, pp. 103613. Date of Electronic Publication: 2021 Oct 14.
DOI:	10.1016/j.ebiom.2021.103613
Abstrakt:	Background: Laboratory testing is routinely used to assay blood biomarkers to provide information on physiologic state beyond what clinicians can evaluate from interpreting medical imaging. We hypothesized that deep learning interpretation of echocardiogram videos can provide additional value in understanding disease states and can evaluate common biomarkers results. Methods: We developed EchoNet-Labs, a video-based deep learning algorithm to detect evidence of anemia, elevated B-type natriuretic peptide (BNP), troponin I, and blood urea nitrogen (BUN), as well as values of ten additional lab tests directly from echocardiograms. We included patients (n = 39,460) aged 18 years or older with one or more apical-4-chamber echocardiogram videos (n = 70,066) from Stanford Healthcare for training and internal testing of EchoNet-Lab's performance in estimating the most proximal biomarker result. Without fine-tuning, the performance of EchoNet-Labs was further evaluated on an additional external test dataset (n = 1,301) from Cedars-Sinai Medical Center. We calculated the area under the curve (AUC) of the receiver operating characteristic curve for the internal and external test datasets. Findings: On the held-out test set of Stanford patients not previously seen during model training, EchoNet-Labs achieved an AUC of 0.80 (0.79-0.81) in detecting anemia (low hemoglobin), 0.86 (0.85-0.88) in detecting elevated BNP, 0.75 (0.73-0.78) in detecting elevated troponin I, and 0.74 (0.72-0.76) in detecting elevated BUN. On the external test dataset from Cedars-Sinai, EchoNet-Labs achieved an AUC of 0.80 (0.77-0.82) in detecting anemia, of 0.82 (0.79-0.84) in detecting elevated BNP, of 0.75 (0.72-0.78) in detecting elevated troponin I, and of 0.69 (0.66-0.71) in detecting elevated BUN. We further demonstrate the utility of the model in detecting abnormalities in 10 additional lab tests. We investigate the features necessary for EchoNet-Labs to make successful detection and identify potential mechanisms for each biomarker using well-known and novel explainability techniques. Interpretation: These results show that deep learning applied to diagnostic imaging can provide additional clinical value and identify phenotypic information beyond current imaging interpretation methods. Funding: J.W.H. and B.H. are supported by the NSF Graduate Research Fellowship. D.O. is supported by NIH K99 HL157421-01. J.Y.Z. is supported by NSF CAREER 1942926, NIH R21 MD012867-01, NIH P30AG059307 and by a Chan-Zuckerberg Biohub Fellowship. Competing Interests: Declaration of Competing Interest Dr Nieman reports grants from Siemens Healthineers, Bayer, HeartFlow Inc., personal fees from Siemens Medical Solutions USA, outside the submitted work. The other authors have nothing to disclose. (Copyright © 2021 The Authors. Published by Elsevier B.V. All rights reserved.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu