To have an objective depression diagnosis, numerous studies based on machine learning and deep learning using electroencephalogram (EEG) have been conducted. Most studies depend on one-dimensional raw data and required fine feature extraction. To solve this problem, in the EEG visualization research field, short-time Fourier transform (STFT), wavelet, and coherence commonly used as method s for transferring EEG data to 2D images. However, we devised a new way from the concept that EEG’s asymmetry was considered one of the major biomarkers of depression. This study proposes a deep-asymmetry methodology that converts the EEG’s asymmetry feature into a matrix image and uses it as input to a convolutional neural network. The asymmetry matrix image in the alpha band achieved 98.85% accuracy and outperformed most of the methods presented in previous studies. This study indicates that the proposed method can be an effective tool for pre-screening major depressive disorder patients.

Objectives: De-identifying protected health information (PHI) in medical documents is important, and a prerequisite to deidentification is the identification of PHI entity names in clinical documents. This study aimed to compare the performance of three pre-training models that have recently attracted significant attention and to determine which model is more suitable for PHI recognition. Methods: We compared the PHI recognition performance of deep learning models using the i2b2 2014 dataset. We used the three pre-training models—namely, bidirectional encoder representations from transformers (BERT), robustly optimized BERT pre-training approach (RoBERTa), and XLNet (model built based on Transformer-XL)—to detect PHI. After the dataset was tokenized, it was processed using an inside-outside-beginning tagging scheme and WordPiecetokenized to place it into these models. Further, the PHI recognition performance was investigated using BERT, RoBERTa, and XLNet. Results: Comparing the PHI recognition performance of the three models, it was confirmed that XLNet had a superior F1-score of 96.29%. In addition, when checking PHI entity performance evaluation, RoBERTa and XLNet showed a 30% improvement in performance compared to BERT. Conclusions: Among the pre-training models used in this study, XLNet exhibited superior performance because word embedding was well constructed using the two-stream self-attention method. In addition, compared to BERT, RoBERTa and XLNet showed superior performance, indicating that they were more effective in grasping the context.

For the secondary use of clinical documents, it is necessary to de-identify protected health information (PHI) in documents. However, the difficulty lies in the fact that there are few publicly annotated PHI documents. To solve this problem, in this study, we propose a filtered bidirectional encoder representation from transformers (BERT)-based method that predicts a masked word and validates the word again through a similarity filter to construct augmented sentences. The proposed method effectively performs data augmentation. The results show that the augmentation method based on filtered BERT improved the performance of the model. This suggests that our method can effectively improve the performance of the model in the limited data environment.

There is ongoing research on using electroencephalography (EEG) to predict depression. In particular, the deep learning method in which brain waves are used as inputs of a convolutional neural network (CNN) is being widely researched and has shown remarkable performance. We built a regression model to predict the severity score (Beck Depression Inventory [BDI]) of depressed patients as an extension of the deep-asymmetry method, which has shown promising performance in depression classification. Predicting the severity of depression is very important because the treatment and coping methods are different for each severity level. We imaged brain waves using the deep-asymmetry method, used them to train a two-dimensional CNN-based deep learning model, and achieved satisfactory performance. The EEG image-based CNN approach will make an important contribution to creating a highly interpretable model for predicting depression in the future.