Forecasting imminent atrial fibrillation in long-term electrocardiogram recordings

被引:2
|
作者
Rooney, Sydney R. [1 ,8 ]
Kaufman, Roman [2 ]
Murugan, Raghavan [3 ]
Kashani, Kianoush B. [4 ,5 ]
Pinsky, Michael R. [6 ]
Al-Zaiti, Salah [7 ]
Dubrawski, Artur [2 ]
Clermont, Gilles [6 ]
Miller, J. Kyle [2 ]
机构
[1] Childrens Hosp Pittsburgh, Dept Pediat, 4401 Penn Ave, Pittsburgh, PA 15224 USA
[2] Carnegie Mellon Univ, Auton Lab, Newell Simon Hall 3128,Forbes Ave, Pittsburgh, PA 15213 USA
[3] Univ Pittsburgh, Dept Crit Care Med, Program Crit Care Nephrol, Sch Med, 3550 Terrace St,Alan Magee Scaife Hall,Suite 600, Pittsburgh, PA 15213 USA
[4] Mayo Clin, Div Nephrol & Hypertens, 200 First St SW, Rochester, MN 55905 USA
[5] Mayo Clin, Dept Med, Div Pulm & Crit Care Med, 200 First St SW, Rochester, MN 55905 USA
[6] Univ Pittsburgh, Dept Crit Care Med, 3550 Terrace St,Alan Magee Scaife Hall,Suite 600, Pittsburgh, PA 15213 USA
[7] Univ Pittsburgh, Med Ctr, Sch Nursing, Dept Acute & Tertiary Care, 3500 Victoria St,Victoria Bldg, Pittsburgh, PA 15261 USA
[8] 4221 Penn Ave,Ste 5400, Pittsburgh, PA 15224 USA
基金
美国国家卫生研究院;
关键词
Predictive analytics; Atrial fibrillation; Forecasting; STROKE;
D O I
10.1016/j.jelectrocard.2023.08.011
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Background: Despite the morbidity associated with acute atrial fibrillation (AF), no models currently exist to forecast its imminent onset. We sought to evaluate the ability of deep learning to forecast the imminent onset of AF with sufficient lead time, which has important implications for inpatient care. Methods: We utilized the Physiobank Long-Term AF Database, which contains 24-h, labeled ECG recordings from patients with a history of AF. AF episodes were defined as >= 5 min of sustained AF. Three deep learning models incorporating convolutional and transformer layers were created for forecasting, with two models focusing on the predictive nature of sinus rhythm segments and AF epochs separately preceding an AF episode, and one model utilizing all preceding waveform as input. Cross-validated performance was evaluated using area under time-dependent receiver operating characteristic curves (AUC(t)) at 7.5-, 15-, 30-, and 60-min lead times, precision-recall curves, and imminent AF risk trajectories. Results: There were 367 AF episodes from 84 ECG recordings. All models showed average risk trajectory divergence of those with an AF episode from those without similar to 15 min before the episode. Highest AUC was associated with the sinus rhythm model [AUC = 0.74; 7.5-min lead time], though the model using all preceding waveform data had similar performance and higher AUCs at longer lead times. Conclusions: In this proof-of-concept study, we demonstrated the potential utility of neural networks to forecast the onset of AF in long-term ECG recordings with a clinically relevant lead time. External validation in larger cohorts is required before deploying these models clinically.
引用
收藏
页码:111 / 116
页数:6
相关论文
共 50 条
  • [31] Long-term clinical outcome of right atrial ablation for paroxysmal atrial fibrillation
    Tondo, C
    Riva, SRS
    Carbucicchio, CCC
    Apostolo, AAA
    Fassini, GFG
    Della Bella, PDBP
    EUROPEAN HEART JOURNAL, 2000, 21 : 673 - 673
  • [32] Long-term electrocardiogram analysis
    Vainoras, A
    Gargasas, L
    Jurkoniene, R
    Jurkonis, V
    Ruseckas, R
    Miskinis, V
    Korsakas, S
    ANALYSIS OF BIOMEDICAL SIGNALS AND IMAGES, PROCEEDINGS, 2002, : 200 - 202
  • [33] Long-Term Incidence of Atrial Fibrillation in Patients With Autoimmune Disease
    Sun, Guoli
    Ahlehoff, Ole
    Fosbol, Emil L.
    Schou, Morten
    Faurschou, Mikkel
    Svendsen, Jesper Hastrup
    Kober, Lars
    Butt, Jawad H.
    JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY, 2023, 82 (20) : 1969 - 1971
  • [34] Response and long-term outcomes with resynchronization therapy in atrial fibrillation
    Brandao, M.
    Almeida, J. Goncalves
    Fonseca, P.
    Santos, E.
    Rosas, F.
    Ribeiro, J.
    Oliveira, M.
    Goncalves, H.
    Primo, J.
    Fontes-Carvalho, R.
    EUROPEAN HEART JOURNAL, 2021, 42 : 704 - 704
  • [35] Atrial fibrillation in pneumonia: what clinical implications at long-term?
    Vitolo, Marco
    Bonini, Niccolo
    Imberti, Jacopo F. F.
    Boriani, Giuseppe
    INTERNAL AND EMERGENCY MEDICINE, 2022, 18 (2) : 347 - 350
  • [36] Towards Long-term Monitoring of Atrial Fibrillation using Photoplethysmography
    Paliakaite, Birute
    Petrenas, Andrius
    Skibarkiene, Jurgita
    Mickus, Tomas
    Daukantas, Saulius
    Kubilius, Raimondas
    Marozas, Vaidotas
    PROCEEDINGS OF THE 10TH INTERNATIONAL JOINT CONFERENCE ON BIOMEDICAL ENGINEERING SYSTEMS AND TECHNOLOGIES, VOL 4: BIOSIGNALS, 2017, : 141 - 146
  • [37] Natural History and Long-Term Outcomes of Ablated Atrial Fibrillation
    Hussein, Ayman A.
    Saliba, Walid I.
    Martin, David O.
    Bhargava, Mandeep
    Sherman, Minerva
    Magnelli-Reyes, Christina
    Chamsi-Pasha, Mohammed
    John, Seby
    Williams-Adrews, Michelle
    Baranowski, Bryan
    Dresing, Thomas
    Callahan, Thomas
    Kanj, Mohamed
    Tchou, Patrick
    Lindsay, Bruce D.
    Natale, Andrea
    Wazni, Oussama
    CIRCULATION-ARRHYTHMIA AND ELECTROPHYSIOLOGY, 2011, 4 (03): : 271 - 278
  • [38] LONG-TERM RESULTS OF THE CORRIDOR OPERATION FOR ATRIAL-FIBRILLATION
    CHENG, TO
    BRITISH HEART JOURNAL, 1994, 72 (06): : 594 - 594
  • [39] Improving prediction of long-term success of ablation for atrial fibrillation
    Wissner, Erik
    Kuck, Karl-Heinz
    HEART, 2011, 97 (22) : 1817 - 1818
  • [40] Atrial fibrillation and mortality in a population of long-term haemodialysis patients
    Pogliani, Daniela
    Vincenti, Antonello
    Rossi, Emanuela
    Valsecchi, Maria Grazia
    Acquistapace, Irene
    Stella, Andrea
    Genovesi, Simonetta
    NEPHROLOGY DIALYSIS TRANSPLANTATION, 2006, 21 : 439 - 439