Deepaware: A hybrid deep learning and context-aware heuristics-based model for atrial fibrillation detection
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Deepaware : A hybrid deep learning and context-aware heuristics-based model for atrial fibrillation detection. / Kumar, Devender; Peimankar, Abdolrahman; Sharma, Kamal; Domínguez, Helena; Puthusserypady, Sadasivan; Bardram, Jakob E.
I: Computer Methods and Programs in Biomedicine, Bind 221, 106899, 2022.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Deepaware
T2 - A hybrid deep learning and context-aware heuristics-based model for atrial fibrillation detection
AU - Kumar, Devender
AU - Peimankar, Abdolrahman
AU - Sharma, Kamal
AU - Domínguez, Helena
AU - Puthusserypady, Sadasivan
AU - Bardram, Jakob E.
N1 - Publisher Copyright: © 2022 The Author(s)
PY - 2022
Y1 - 2022
N2 - Background: State-of-the-art automatic atrial fibrillation (AF) detection models trained on RR-interval (RRI) features generally produce high performance on standard benchmark electrocardiogram (ECG) AF datasets. These models, however, result in a significantly high false positive rates (FPRs) when applied on ECG data collected under free-living ambulatory conditions and in the presence of non-AF arrhythmias. Method: This paper proposes DeepAware, a novel hybrid model combining deep learning (DL) and context-aware heuristics (CAH), which reduces the FPR effectively and improves the AF detection performance on participant-operated ambulatory ECG from free-living conditions. It exploits the RRI and P-wave features, as well as the contextual features from the ambulatory ECG. Results: DeepAware is shown to be very generalizable and superior to the state-of-the-art models when applied on unseen benchmark ECG AF datasets. Most importantly, the model is able to detect AF efficiently when applied on participant-operated ambulatory ECG recordings from free-living conditions and has achieved a sensitivity (Se), specificity (Sp), and accuracy (Acc) of 97.94%, 98.39%, 98.06%, respectively. Results also demonstrate the effect of atrial activity analysis (via P-waves detection) and CAH in reducing the FPR over the RRI features-based AF detection model. Conclusions: The proposed DeepAware model can substantially reduce the physician's workload of manually reviewing the false positives (FPs) and facilitate long-term ambulatory monitoring for early detection of AF.
AB - Background: State-of-the-art automatic atrial fibrillation (AF) detection models trained on RR-interval (RRI) features generally produce high performance on standard benchmark electrocardiogram (ECG) AF datasets. These models, however, result in a significantly high false positive rates (FPRs) when applied on ECG data collected under free-living ambulatory conditions and in the presence of non-AF arrhythmias. Method: This paper proposes DeepAware, a novel hybrid model combining deep learning (DL) and context-aware heuristics (CAH), which reduces the FPR effectively and improves the AF detection performance on participant-operated ambulatory ECG from free-living conditions. It exploits the RRI and P-wave features, as well as the contextual features from the ambulatory ECG. Results: DeepAware is shown to be very generalizable and superior to the state-of-the-art models when applied on unseen benchmark ECG AF datasets. Most importantly, the model is able to detect AF efficiently when applied on participant-operated ambulatory ECG recordings from free-living conditions and has achieved a sensitivity (Se), specificity (Sp), and accuracy (Acc) of 97.94%, 98.39%, 98.06%, respectively. Results also demonstrate the effect of atrial activity analysis (via P-waves detection) and CAH in reducing the FPR over the RRI features-based AF detection model. Conclusions: The proposed DeepAware model can substantially reduce the physician's workload of manually reviewing the false positives (FPs) and facilitate long-term ambulatory monitoring for early detection of AF.
KW - Arrhythmia
KW - Atrial fibrillation
KW - Context-awareness
KW - Convolutional neural networks
KW - Deep learning
KW - Electrocardiogram (ECG)
KW - Health informatics
KW - Long short-term memory (LSTM)
UR - http://www.scopus.com/inward/record.url?scp=85131144412&partnerID=8YFLogxK
U2 - 10.1016/j.cmpb.2022.106899
DO - 10.1016/j.cmpb.2022.106899
M3 - Journal article
C2 - 35640394
AN - SCOPUS:85131144412
VL - 221
JO - Computer Methods and Programs in Biomedicine
JF - Computer Methods and Programs in Biomedicine
SN - 0169-2607
M1 - 106899
ER -
ID: 314072581