Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

Deep learning-based multimodal fusion of the surface ECG and clinical features in prediction of atrial fibrillation recurrence following catheter ablation.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
اقرأ على الانترنت اقرأ أكثر حفظ في قائمتي
  • معلومة اضافية
    • المصدر:
      Publisher: BioMed Central Country of Publication: England NLM ID: 101088682 Publication Model: Electronic Cited Medium: Internet ISSN: 1472-6947 (Electronic) Linking ISSN: 14726947 NLM ISO Abbreviation: BMC Med Inform Decis Mak Subsets: MEDLINE
    • بيانات النشر:
      Original Publication: London : BioMed Central, [2001-
    • الموضوع:
      Atrial Fibrillation*/surgery ; Deep Learning* ; Electrocardiography* ; Catheter Ablation* ; Recurrence*; Humans ; Male ; Female ; Middle Aged ; Aged
    • نبذة مختصرة :
      Background: Despite improvement in treatment strategies for atrial fibrillation (AF), a significant proportion of patients still experience recurrence after ablation. This study aims to propose a novel algorithm based on Transformer using surface electrocardiogram (ECG) signals and clinical features can predict AF recurrence.
      Methods: Between October 2018 to December 2021, patients who underwent index radiofrequency ablation for AF with at least one standard 10-second surface ECG during sinus rhythm were enrolled. An end-to-end deep learning framework based on Transformer and a fusion module was used to predict AF recurrence using ECG and clinical features. Model performance was evaluated using areas under the receiver operating characteristic curve (AUROC), sensitivity, specificity, accuracy and F1-score.
      Results: A total of 920 patients (median age 61 [IQR 14] years, 66.3% male) were included. After a median follow-up of 24 months, 253 patients (27.5%) experienced AF recurrence. A single deep learning enabled ECG signals identified AF recurrence with an AUROC of 0.769, sensitivity of 75.5%, specificity of 61.1%, F1 score of 55.6% and overall accuracy of 65.2%. Combining ECG signals and clinical features increased the AUROC to 0.899, sensitivity to 81.1%, specificity to 81.7%, F1 score to 71.7%, and overall accuracy to 81.5%.
      Conclusions: The Transformer algorithm demonstrated excellent performance in predicting AF recurrence. Integrating ECG and clinical features enhanced the models' performance and may help identify patients at low risk for AF recurrence after index ablation.
      (© 2024. The Author(s).)
    • References:
      Med Image Anal. 2023 Aug;88:102802. (PMID: 37315483)
      Heart Rhythm. 2015 Apr;12(4):681-6. (PMID: 25546809)
      Europace. 2009 Oct;11(10):1289-94. (PMID: 19632980)
      Circ Arrhythm Electrophysiol. 2020 Jul;13(7):e008213. (PMID: 32536204)
      J Cardiovasc Electrophysiol. 2023 Jan;34(1):153-165. (PMID: 36434795)
      Circulation. 2024 Jan 2;149(1):e1-e156. (PMID: 38033089)
      Nature. 2016 Jan 28;529(7587):484-9. (PMID: 26819042)
      Front Physiol. 2022 Jun 29;13:912739. (PMID: 35846006)
      Circulation. 2015 Sep 8;132(10):907-15. (PMID: 26260733)
      Med Image Anal. 2023 Apr;85:102762. (PMID: 36738650)
      JACC Clin Electrophysiol. 2022 Jul;8(7):882-891. (PMID: 35863814)
      Circ Arrhythm Electrophysiol. 2021 Mar;14(3):e009265. (PMID: 33576688)
      Heart Rhythm. 2024 Jul;21(7):1001-1007. (PMID: 38365127)
      J Am Coll Cardiol. 2024 Jan 2;83(1):109-279. (PMID: 38043043)
      Europace. 2009 Oct;11(10):1255-6. (PMID: 19797140)
      Heart Rhythm. 2016 Nov;13(11):2119-2125. (PMID: 27435586)
      Heart Rhythm. 2015 Nov;12(11):2207-12. (PMID: 26144350)
      Circ Arrhythm Electrophysiol. 2022 Feb;15(2):e010253. (PMID: 35089057)
      BMJ Open. 2021 Nov 2;11(11):e052887. (PMID: 34728455)
      Circ Arrhythm Electrophysiol. 2016 Feb;9(2):e003382. (PMID: 26857907)
      Front Artif Intell. 2023 Jan 09;5:1087370. (PMID: 36699614)
      Eur Heart J. 2017 Jan 1;38(1):14-19. (PMID: 26409008)
      PLoS One. 2017 Jan 13;12(1):e0169933. (PMID: 28085921)
      Circ Arrhythm Electrophysiol. 2017 Nov;10(11):. (PMID: 29141843)
      NPJ Digit Med. 2019 May 30;2:43. (PMID: 31304389)
      Heart Rhythm. 2017 Oct;14(10):e275-e444. (PMID: 28506916)
      Circ Arrhythm Electrophysiol. 2022 Aug;15(8):e010850. (PMID: 35867397)
      Artif Intell Med. 2022 Feb;124:102236. (PMID: 35115130)
      IEEE Trans Med Imaging. 2021 Dec;40(12):3543-3554. (PMID: 34138702)
      Clin Cardiol. 2019 Feb;42(2):320-329. (PMID: 30578568)
      JAMA Cardiol. 2023 Aug 1;8(8):765-772. (PMID: 37378966)
      Eur Heart J. 2017 Jan 1;38(1):20-26. (PMID: 27389907)
    • Grant Information:
      82170322 National Natural Science Foundation of China
    • Contributed Indexing:
      Keywords: Atrial fibrillation recurrence; Clinical features; Deep learning; Electrocardiogram; Pulmonary vein isolation; Transformer
    • الموضوع:
      Date Created: 20240808 Date Completed: 20240809 Latest Revision: 20240811
    • الموضوع:
      20240812
    • الرقم المعرف:
      PMC11308714
    • الرقم المعرف:
      10.1186/s12911-024-02616-x
    • الرقم المعرف:
      39118118