Your browser doesn't support javascript.
loading
Deep learning evaluation of echocardiograms to identify occult atrial fibrillation.
Yuan, Neal; Stein, Nathan R; Duffy, Grant; Sandhu, Roopinder K; Chugh, Sumeet S; Chen, Peng-Sheng; Rosenberg, Carine; Albert, Christine M; Cheng, Susan; Siegel, Robert J; Ouyang, David.
Affiliation
  • Yuan N; School of Medicine, University of California, San Francisco, CA; Division of Cardiology, San Francisco Veterans Affairs Medical Center, San Francisco, CA, USA. Neal.Yuan@ucsf.edu.
  • Stein NR; Cedars-Sinai Smidt Heart Institute, Los Angeles, CA, USA.
  • Duffy G; Cedars-Sinai Smidt Heart Institute, Los Angeles, CA, USA.
  • Sandhu RK; Cedars-Sinai Smidt Heart Institute, Los Angeles, CA, USA.
  • Chugh SS; Cedars-Sinai Smidt Heart Institute, Los Angeles, CA, USA.
  • Chen PS; Cedars-Sinai Smidt Heart Institute, Los Angeles, CA, USA.
  • Rosenberg C; Cedars-Sinai Smidt Heart Institute, Los Angeles, CA, USA.
  • Albert CM; Cedars-Sinai Smidt Heart Institute, Los Angeles, CA, USA.
  • Cheng S; Cedars-Sinai Smidt Heart Institute, Los Angeles, CA, USA.
  • Siegel RJ; Cedars-Sinai Smidt Heart Institute, Los Angeles, CA, USA.
  • Ouyang D; Cedars-Sinai Smidt Heart Institute, Los Angeles, CA, USA.
NPJ Digit Med ; 7(1): 96, 2024 Apr 13.
Article in En | MEDLINE | ID: mdl-38615104
ABSTRACT
Atrial fibrillation (AF) often escapes detection, given its frequent paroxysmal and asymptomatic presentation. Deep learning of transthoracic echocardiograms (TTEs), which have structural information, could help identify occult AF. We created a two-stage deep learning algorithm using a video-based convolutional neural network model that (1) distinguished whether TTEs were in sinus rhythm or AF and then (2) predicted which of the TTEs in sinus rhythm were in patients who had experienced AF within 90 days. Our model, trained on 111,319 TTE videos, distinguished TTEs in AF from those in sinus rhythm with high accuracy in a held-out test cohort (AUC 0.96 (0.95-0.96), AUPRC 0.91 (0.90-0.92)). Among TTEs in sinus rhythm, the model predicted the presence of concurrent paroxysmal AF (AUC 0.74 (0.71-0.77), AUPRC 0.19 (0.16-0.23)). Model discrimination remained similar in an external cohort of 10,203 TTEs (AUC of 0.69 (0.67-0.70), AUPRC 0.34 (0.31-0.36)). Performance held across patients who were women (AUC 0.76 (0.72-0.81)), older than 65 years (0.73 (0.69-0.76)), or had a CHA2DS2VASc ≥2 (0.73 (0.79-0.77)). The model performed better than using clinical risk factors (AUC 0.64 (0.62-0.67)), TTE measurements (0.64 (0.62-0.67)), left atrial size (0.63 (0.62-0.64)), or CHA2DS2VASc (0.61 (0.60-0.62)). An ensemble model in a cohort subset combining the TTE model with an electrocardiogram (ECGs) deep learning model performed better than using the ECG model alone (AUC 0.81 vs. 0.79, p = 0.01). Deep learning using TTEs can predict patients with active or occult AF and could be used for opportunistic AF screening that could lead to earlier treatment.

Full text: 1 Collection: 01-internacional Database: MEDLINE Language: En Journal: NPJ Digit Med Year: 2024 Document type: Article Affiliation country: Estados Unidos Country of publication: Reino Unido

Full text: 1 Collection: 01-internacional Database: MEDLINE Language: En Journal: NPJ Digit Med Year: 2024 Document type: Article Affiliation country: Estados Unidos Country of publication: Reino Unido