Anxiety is a complex emotional state that has a great impact on people's physical and mental health. Effectively identifying different anxiety states is very important. By inducing various anxiety states with electroencephalograph (EEG) recording, comprehensive EEG features (frequency and time domain features, statistical and nonlinear features) were extracted from different EEG bands and brain locations. Next, correlation analysis was performed for feature selection. And different classifiers were applied to classify four anxiety levels using different features alone or together to explore their anxiety recognition ability. Based on our dataset, the highest accuracy of identifying four anxiety states reached approximately 62.56% using the Support Vector Machine (SVM), which improved the classification accuracy compared with previous studies. The results also revealed the importance of EEG linear features (especially for features including total power, mean square and variance) in anxiety recognition. Furthermore, it suggested that EEG features in the beta band and the frontal lobe contributed to anxiety recognition more than the features in the other bands or other brain locations. In short, this study improves the accuracy of multi-level anxiety recognition and helps in choosing better features for anxiety recognition, which lay the foundation for the detection of continuous anxiety changes.
13 July 2020 in IEEE Transactions on Affective Computing
In this paper, we investigate brain directed connectivity (BDC) networks for emotion recognition using electroencephalogram (EEG) source signals that were estimated from high-density sensor EEG signals, for the first time. Currently, a variety of features extracted from sensor EEG signals are used for emotion recognition. However, they cannot unambiguously describe the location of emotions associated with neural activities and information propagation or the interaction between brain regions. In addition, most current studies use low-density sensor EEG signals. Moreover, source signals estimated from high-density sensor EEG signal have not been employed for emotion recognition to date. We designed a BDC network-based framework using EEG source signals to investigate emotion recognition. The global cortex factor-based multivariate autoregressive (GCF-MVAR) method was utilized to extract emotion-related BDC features. Our study revealed that the combined BDC and DE features facilitated a recognition accuracy of up to 89.58 %, which is higher than the rate obtained from BDC features and DE features alone. The sensor features derived from high-density EEG signals also exhibited higher recognition accuracy compared to low-density EEG signals. These findings suggest that BDC features derived from EEG source signals can better characterize human emotional states and are meaningful for emotion recognition.
Previous studies have found that P1 and P2 components were more sensitive to configural and featural face processing, respectively, when attentional resources were sufficient, suggesting that face processing follows a coarse-to-fine sequence. However, the role of working memory (WM) load in the time course of configural and featural face processing is poorly understood, especially whether it differs during encoding and retrieval stages. This study employed a delayed recognition task with varying WM load and face spatial frequency (SF). Our behavioral and ERP results showed that WM load modulated face SF processing. Specifically, for the encoding stage, P1 and P2 were more sensitive to broadband SF (BSF) faces, while N170 was more sensitive to low SF (LSF) and BSF faces. For the retrieval stage, P1 on the right hemisphere was more sensitive to BSF faces relative to HSF faces, N170 was more sensitive to LSF faces than HSF faces, especially under the load 1 condition, while P2 was more sensitive to high SF (HSF) faces than HSF faces, especially under load 3 condition. These results indicate that faces are perceived less finely during the encoding stage, whereas face perception follows a coarse-to-fine sequence during the retrieval stage, which is influenced by WM load. The coarse and fine information were processed especially under the low and high load conditions, respectively.
17 October 2025 in Frontiers in Artificial Intelligence
Introduction: Liver cancer is a leading cause of cancer-related mortality worldwide, necessitating advanced tools for diagnosis and management. Knowledge graphs (KGs) are crucial for advancing smart healthcare, but existing liver cancer-specific KGs are mostly derived from literature or public databases, lacking integration with real-world clinical data [e.g., Electronic Medical Records (EMRs)], creating a critical gap. Furthermore, there is currently no publicly available KGs specifically for liver cancer, creating a significant gap in structured clinical knowledge resources.Methods: This study proposes a novel framework to construct the first Chinese liver cancer KG from Real-World Liver Cancer Electronic Medical Records (RLC-EMRs). A new named entity recognition (NER) model, DERM-RoBERTa-wwm-large-BiLSTM-CRF was developed that uses a Dynamic Entity Replacement and Masking (DERM) strategy to address data scarcity. Knowledge fusion was performed using the TF-IDF algorithm to standardize and integrate entities from clinical records, the professional medical website www.XYWY.com, and the CCMT-2019 terminology standard.Results: The final constructed liver cancer KG contained 46,364 entities and 296,655 semantic relationships. The proposed NER model achieved a state-of-the-art F1 score of 68.84% on the public CMeEE-v2 dataset. On the proprietary RLC-EMRs dataset, the model demonstrated high effectiveness with a precision of 93.23%, recall of 94.69%, and an F1 score of 93.96%. In addition, a KG-based retrieval system was successfully developed to query for complications, medications, and other related information.Discussion: The findings demonstrated the effectiveness of the proposed framework in constructing a comprehensive and clinically relevant liver cancer KG. The novel DERM-based NER model significantly improved entity extraction from complex medical texts. By successfully integrating real-world clinical data, this study addresses a critical gap in existing liver cancer-specific KGs, which are mostly derived from literature or public databases and lack integration with real-world clinical information.
10 October 2025 in Frontiers in Artificial Intelligence
Introduction: The liver cancer question-and-answer (Q&A) system is primarily intended to help patients access disease-related information more conveniently. However, there is currently no Q&A system specifically developed for liver cancer. Additionally, most existing Q&A systems lack real clinical data and have limited capability in understanding Chinese questions.Methods: This paper proposes a Chinese liver cancer question-answering system based on knowledge graphs and Large Language Models (LLMs). To unify information from diverse sources, the system employs a knowledge graph to store entities and inter-entity relationships extracted from patients' clinical electronic medical records and the professional medical website xywy.com, which serves as the foundation for the system's responses. Specifically, ChatGLM3.5 is utilized to extract entity information from questions, while BERT is applied to understand users' intent. Subsequently, the system retrieves corresponding information from the knowledge graph. Finally, the retrieved information is integrated, and a natural language response is generated as the answer to the question.Results: The experimental results indicate that in terms of intent classification, our system achieves a precision of 92.34%, representing an improvement of 1.38% over the BERT model and 4.32% over the GEBERT model. In terms of response relevance, the system's outputs are more aligned with patients' daily speech patterns and exhibit higher relevance to the target questions.Discussion: In conclusion, the improved method significantly enhances the usefulness and reliability of the liver cancer Q&A system.