Improving generalization performance of electrocardiogram classification models.

Objective.Recently, many electrocardiogram (ECG) classification algorithms using deep learning have been proposed. Because the ECG characteristics vary across datasets owing to variations in factors such as recorded hospitals and the race of participants, the model needs to have a consistently high generalization performance across datasets. In this study, as part of the PhysioNet/Computing in Cardiology Challenge (PhysioNet Challenge) 2021, we present a model to classify cardiac abnormalities from the 12- and the reduced-lead ECGs.Approach.To improve the generalization performance of our earlier proposed model, we adopted a practical suite of techniques, i.e. constant-weighted cross-entropy loss, additional features, mixup augmentation, squeeze/excitation block, and OneCycle learning rate scheduler. We evaluated its generalization performance using the leave-one-dataset-out cross-validation setting. Furthermore, we demonstrate that the knowledge distillation from the 12-lead and large-teacher models improved the performance of the reduced-lead and small-student models.Main results.With the proposed model, our DSAIL SNU team has received Challenge scores of 0.55, 0.58, 0.58, 0.57, and 0.57 (ranked 2nd, 1st, 1st, 2nd, and 2nd of 39 teams) for the 12-, 6-, 4-, 3-, and 2-lead versions of the hidden test set, respectively.Significance.The proposed model achieved a higher generalization performance over six different hidden test datasets than the one we submitted to the PhysioNet Challenge 2020.

Study on the use of standard 12-lead ECG data for rhythm-type ECG classification problems.

BACKGROUND AND OBJECTIVES: Most deep-learning-related methodologies for electrocardiogram (ECG) classification are focused on finding an optimal deep-learning architecture to improve classification performance. However, in this study, we proposed a methodology for fusion of various single-lead ECG data as training data in the single-lead ECG classification problem. METHODS: We used a squeeze-and-excitation residual network (SE-ResNet) with 152 layers as the baseline model. We compared the performance of a 152-layer SE-ResNet trained on ECG signals from various leads of a standard 12-lead ECG system to that of a 152-layer SE-ResNet trained on only single-lead ECG data with the same lead information as the test set. The experiments were performed using five different types of rhythm-type single-lead ECG data obtained from Konkuk University Hospital in South Korea. RESULTS: Experiment results based on the combination from the relationship experiments of the leads showed that lead -aVR or II revealed the best classification performance. In case of -aVR, this model achieved a high F1 score for normal (98.7%), AF (98.2%), APC (95.1%), and VPC (97.4%), indicating its potential for practical use in the medical field. CONCLUSION: We concluded that the 152-layer SE-ResNet trained by fusion of single-lead ECGs had better classification performance than the 152-layer SE-ResNet trained on only single-lead ECG data, regardless of the single-lead ECG signal type. We also found that the best performance directions for single-lead ECG classification are Lead -aVR and II.

The Association between Excessive Internet Gaming Behavior and Immersive Tendency, Mediated by Attention Deficit/Hyperactivity Disorder Symptoms, in Korean Male University Students.

OBJECTIVE: Problematic online gaming (POG) and problematic Internet use (PIU) have become a serious public mental health problem, with Internet gaming disorder (IGD) included in "Conditions for further study" section of DSM-5. Although higher immersive tendency is observed in people affected by POG, little is known about the simultaneous effect of immersive tendency and its highly comorbid mental disorder, attention deficit/hyperactivity disorder (ADHD). This study aimed to assess the relationship between immersive tendency, ADHD, and IGD. METHODS: Cross-sectional interview study was conducted in Seoul, Korea with 51 male undergraduate students; 23 active gamers and 28 controls. RESULTS: Current ADHD symptoms showed partial mediation effect on the path of immersive tendency on POG and PIU. The mediation model with inattention explained variance in both POG and PIU better than other current ADHD symptom models (R2=69.2 in POG; 69.3 in PIU). Childhood ADHD symptoms models demonstrated mediation effect on both POG and PIU which explained less variance than current ADHD symptom models (R2=53.7 in POG; 52.1 in PIU). Current ADHD symptoms, especially inattention, appear to mediate the effect of immersive tendency on POG/PIU. CONCLUSION: Immersive tendencies may entail greater susceptibility to IGD, and comorbidity with ADHD may mediate the effect of immersive tendency on IGD.