An ensemble of features based deep learning neural network for reduction of inappropriate atrial fibrillation detection in implantable cardiac monitors

Sarkar, Shantanu; Majumder, Shubha; Koehler, Jodi; Landman, Sean R.

doi:10.1016/j.hroo.2022.10.014

Cited by 4 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the proposed deep model, we employed the ECG arrhythmia classification dataset [30]. The Electrocardiogram (ECG) Arrhythmia Classification Dataset is a comprehensive data collection offering an in-depth view into the broad spectrum of cardiac arrhythmias.…”

Section: Datasetmentioning

confidence: 99%

Convolutional LSTM Network for Heart Disease Diagnosis on Electrocardiograms

Omarov,

Baikuvekov,

Momynkulov

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Heart disease is a leading cause of mortality worldwide. Electrocardiograms (ECG) play a crucial role in diagnosing heart disease. However, interpreting ECG signals necessitates specialized knowledge and training. The development of automated methods for ECG analysis has the potential to enhance the accuracy and efficiency of heart disease diagnosis. This research paper proposes a 3D Convolutional Long Short-Term Memory (Conv-LSTM) model for detecting heart disease using ECG signals. The proposed model combines the advantages of both convolutional neural networks (CNN) and long short-term memory (LSTM) networks. By considering both the spatial and temporal dependencies of ECG, the 3D Conv-LSTM model enables the detection of subtle changes in the signal over time. The model is trained on a dataset of ECG recordings from patients with various heart conditions, including arrhythmia, myocardial infarction, and heart failure. Experimental results show that the proposed 3D Conv-LSTM model outperforms traditional 2D CNN models in detecting heart disease, achieving an accuracy of 88% in the classification of five classes. Furthermore, the model outperforms the other state-of-the-art deep learning models for ECG-based heart disease detection. Moreover, the proposed Conv-LSTM network yields highly accurate outcomes in identifying abnormalities in specific ECG leads. The proposed 3D Conv-LSTM model holds promise as a valuable tool for automated heart disease detection and diagnosis. This study underscores the significance of incorporating spatial and temporal dependencies in ECG-based heart disease detection. It highlights the potential of deep-learning models in enhancing the accuracy and efficiency of diagnosis.

show abstract

Section: Datasetmentioning

confidence: 99%

Convolutional LSTM Network for Heart Disease Diagnosis on Electrocardiograms

Omarov,

Baikuvekov,

Momynkulov

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

Incidence of atrial fibrillation in patients with an insertable cardiac monitor and symptomatic heart failure

Khan,

Zile,

Kahwash

et al. 2024

ESC Heart Failure

View full text Add to dashboard Cite

AimsWe aim to evaluate the incidence of atrial fibrillation (AF) in a large real‐world cohort of patients implanted with an insertable cardiac monitor (ICM) who had a clinical history of symptomatic heart failure (HF) with reduced or preserved left ventricular ejection fraction (LVEF).MethodsPatients with an ICM and a history of HF events were identified from the Optum® de‐identified Electronic Health Record dataset merged with an ICM device dataset collected during 2007–2021. All ICM‐detected AF episodes that were available with ≥30‐s of ECG at onset were adjudicated using artificial intelligence (AI model). Episodes with AI model probability of AF ≥ 0.9 were analysed. The Kaplan–Meier incidence of AF as a function of episode duration, history of AF, and LVEF were assessed.ResultsA total of 1020 patients with ICM were identified of whom 911 had ≥180 days of follow‐up and were included. According to the AI model, 358 patients had 8407 episodes of true AF. Incidence of AF at 42 months was 45.6% (44.1% vs. 46.8% in reduced vs. preserved LVEF). Incidence of new‐onset AF was 23.2% (23.3% vs. 22.2% in reduced vs. preserved LVEF) in patients with no clinical history of AF. Patients with new‐onset AF had a higher HF event rate compared with patients who had no clinical history of AF and did not develop AF during follow‐up [OR = 2.73 (1.47–5.09); P = 0.002]. Patients with preserved LVEF had more longer duration paroxysmal AF compared with those with reduced LVEF (44.5% vs. 33.9%, P = 0.02).ConclusionsAF was observed in almost half of patients with ICM and symptomatic HF. One‐fourth of the patients had new onset AF and a higher rate of HF events compared with patients without AF. AF incidence was similar in patients with preserved and reduced LVEF.

show abstract