Diagnosis of atrial fibrillation based on AI-detected anomalies of ECG segments
Sanghoon Choi,
Kyungmin Choi,
Hong Kyun Yun,
Su Hyeon Kim,
Hyeon-Hwa Choi,
Yi-Seul Park,
Segyeong Joo
Affiliations
Sanghoon Choi
Department of Biomedical Engineering, University of Ulsan College of Medicine, Seoul, Republic of Korea; Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, Seoul, Republic of Korea
Kyungmin Choi
Department of Biomedical Engineering, University of Ulsan College of Medicine, Seoul, Republic of Korea; Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, Seoul, Republic of Korea
Hong Kyun Yun
Department of Biomedical Engineering, University of Ulsan College of Medicine, Seoul, Republic of Korea; Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, Seoul, Republic of Korea
Su Hyeon Kim
Department of Biomedical Engineering, University of Ulsan College of Medicine, Seoul, Republic of Korea; Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, Seoul, Republic of Korea
Hyeon-Hwa Choi
Department of Biomedical Engineering, University of Ulsan College of Medicine, Seoul, Republic of Korea; Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, Seoul, Republic of Korea
Yi-Seul Park
Department of Biomedical Engineering, University of Ulsan College of Medicine, Seoul, Republic of Korea; Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, Seoul, Republic of Korea
Segyeong Joo
Department of Biomedical Engineering, University of Ulsan College of Medicine, Seoul, Republic of Korea; Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, Seoul, Republic of Korea; Corresponding author. Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, 388-1 Pungnap-dong, Songpa-gu, Seoul, Republic of Korea.
Early detection of atrial fibrillation (AF) is crucial for its effective management and prevention. Various methods for detecting AF using deep learning (DL) based on supervised learning with a large labeled dataset have a remarkable performance. However, supervised learning has several problems, as it is time-consuming for labeling and has a data dependency problem. Moreover, most of the DL methods do not provide any clinical evidence to physicians regarding the analysis of electrocardiography (ECG) for classification or detection of AF. To address these limitations, in this study, we proposed a novel AF diagnosis system using unsupervised learning for anomaly detection with three segments, PreQ, QRS, and PostS, based on the normal ECG. Two independent datasets, PTB-XL and China, were used in three experiments. We used a long short-term memory (LSTM)-based autoencoder to train the segments of the normal ECG. Based on the threshold of anomaly scores using mean squared error (MSE), it distinguished between normal and AF segments. In Experiment A, the best score was that of PreQ, which detected AF with an AUROC score of 0.96. In Experiment B and C for cross validation of each dataset, the best scores were also of PreQ, with AUROC scores of 0.9 and 0.95, respectively. To verify the significance of the anomaly score in distinguishing between AF and normal segments, we utilized an XG-Boosted model after generating anomaly scores in the three segments. The XG-Boosted model achieved an AUROC score of 0.98 and an F1 score of 0.94. AF detection using DL has been controversial among many physicians. However, our study differentiates itself from previous studies in that we can demonstrate evidence that distinguishes AF from normal segments based on the anomaly score.