In the field of graphic design, the application of Artificial Intelligence (AI) is reshaping the design process. This study employs the Critical Interpretive Synthesis (CIS) approach to explore the impacts and challenges of AI on graphic design. Through a comprehensive review of 33 papers, this research reveals four research paradigms of AI in graphic design: Artificial Intelligence Driven Design Automation and Generation (AIDAG), Artificial Intelligence Assisted Graphic Design and Image Processing (AGDIP), Artificial Intelligence in Art and Creative Design Processes (AACDP), and Artificial Intelligence Enhanced Visual Attention and Emotional Response Modeling (AVERM). These paradigms demonstrate the multidimensional role of AI in design, ranging from automation to emotional interaction. The findings suggest that AI serves a dual role as both a design tool and a medium for innovation. AI not only enhances the automation and efficiency of the design process but also fosters designers' creative thinking and understanding of users' emotional needs. This study also proposes a path for the application of the four paradigms in the graphic design process, providing effective design ideas for future design workflows.

Intangible cultural heritage is an invaluable treasure for all human beings worldwide. In 2009, the United Nations Educational, Scientific and Cultural Organization (UNESCO) inscribed the Chinese Cantonese Opera, also known as Yueju in Chinese Pinyin, on the Representative List of Intangible Cultural Heritage of Humanity. The awareness of inheriting Yueju is not uncommon, but advancing methods to involve more young generations in this art form is still necessary. In this study, we focused on Yueju videos on Bilibili, a cultural community and video website popular among the younger generation. Through quantitative and qualitative research, we explored the types of Yueju videos that would have a significant spreading effect. The 1916 Bilibili videos related to Yueju were collected using Python crawler technology. We analyzed each video using seventeen variables. The elaboration likelihood model (ELM) forms the theoretical foundation of this research. We constructed the Yueju transmission model with two persuasive routes based on this model. The research methods mainly comprised regression analysis, multi-factor ANOVA, and analytic hierarchy process (AHP). We invited thirty-one experts to assess the importance hierarchy of those video factors and calculate the weight coefficient using AHP. This study demonstrated the central route concerning the causal relationship between video recognition and spreading effect through regression analysis. Additionally, this research identified the optimal combination of 8 video factors using multi-factor ANOVA in the peripheral route. In this study, we focused on the niche of Yueju video transmission on Bilibili. This research utilized the ELM and hybrid methods to obtain the statistical results. Then, we developed appropriate macro-level and micro-level strategies for transmitting Yueju culture, particularly those aimed at the younger generation.

Haptics for stress regulation is well developed these years. Using vibrotactile to present biofeedback, guiding breathing or heartbeat regulation is a dominant technical approach. However, designing computer-mediated affective touch for stress regulation is also a promising way and has not been fully explored. In this paper, a haptic device was developed to test whether the computer-mediated affective stroking on the forearm could help to assist people in reducing stress. In our method, we used mid-air technology to generate subtle pressure force by blowing air and generating thermal feedback by using Peltier elements simultaneously. Firstly, we found intensity and velocity parameters to present comfort and pleasant stroking sensations. Afterward, an experiment was conducted to find out whether this approach could help people mediate their perceived and physiological stress. A total of 49 participants were randomly assigned to either a Stroking Group (SG) or a Control Group (CG). Results showed that participants from SG felt more relaxed than those from CG. The physiological stress index, RMSSD, increased and LF/HF decreased in SG although these changes were not statistically significant. Our exploration created subtle, non-invasive, noiseless haptic sensations. It could be a promising alternative for assisting people in stress regulation. Design implications and future applicable scenarios were discussed.

Background: The World Health Organization reports that >1 billion people worldwide experience mental disorders, with the prevalence of depression and anxiety among children and adolescents at 2.6% and 6.5%, respectively. However, commonly used clinical questionnaires such as the Hamilton Depression Rating Scale and the Beck Depression Inventory suffer from several problems, including the high degree of overlap of symptoms of depression with those of other psychiatric disorders and a lack of professional supervision during administration of the questionnaires, which often lead to inaccurate diagnoses. In the wake of the COVID-19 pandemic, the health care system is facing the dual challenges of a surge in patient numbers and the complexity of mental health issues. Artificial Intelligence (AI) technology has now been shown to have great promise in improving diagnostic accuracy, assisting clinical decision-making, and simplifying questionnaire development and data analysis. Objective: This review aimed to explore the current applications, potential benefits, and issues of AI in medical questionnaires, focusing on its role in 3 main functions: assessment, development, and prediction. The global mental health burden remains severe. Methods: The review included peer-reviewed studies that applied AI technologies to medical, psychological, or physiological questionnaires and reported measurable outcomes; non–peer-reviewed, non-English/Chinese, ethically noncompliant, or AI-unrelated studies were excluded. Five databases (PubMed, Embase, Cochrane Library, Web of Science, and CNKI) were searched from inception through September 2024. Three independent reviewers conducted data extraction, quality appraisal using the Joanna Briggs Institute tools, and narrative synthesis of AI applications across questionnaire assessment, development, and prediction tasks. Results: Of 49,091 publications, a total of 14 (0.03%) studies met the inclusion criteria. AI technologies showed advantages in assessment, such as distinguishing myalgic encephalomyelitis or chronic fatigue syndrome from long COVID-19 with 92.18% accuracy. In questionnaire development, natural language processing using generative models such as ChatGPT was used to construct culturally competent scales. In terms of disease prediction, one study had an area under the curve of 0.790 for cataract surgery risk prediction. Overall, 24 AI technologies were identified, covering traditional algorithms such as random forest, support vector machine, and k-nearest neighbor, as well as deep learning models such as convolutional neural networks, Bidirectional Encoder Representations From Transformers, and ChatGPT. Despite the positive findings, only 21% (3/14) of the studies had entered the clinical validation phase, whereas the remaining 79% (11/14) were still in the exploratory phase of research. Most of the studies (10/14, 71%) were rated as being of moderate methodological quality, with major limitations including lack of a control group, incomplete follow-up data, and inadequate validation systems. Conclusions: In summary, the integrated application of AI in medical questionnaires has significant potential to improve diagnostic efficiency, accelerate scale development, and promote early intervention. Future research should pay more attention to model interpretability, system compatibility, validation standardization, and ethical governance to effectively address key challenges such as data privacy, clinical integration, and transparency.

Lung cancer remains the leading cause of cancer-related mortality globally, with environmental pollutants identified as significant risk factors, especially for nonsmokers. The intersection of these pollutants with epigenetic mechanisms has emerged as a critical area of interest for understanding the etiology and progression of lung cancer. Epigenetic changes, including DNA methylation, histone modifications, and non-coding RNAs, can induce alterations in gene expression without affecting the DNA sequence and are influenced by environmental factors, contributing to the transformation of normal cells into malignant cells. This review assessed the literature on the influence of environmental pollutants on lung cancer epigenetics. A comprehensive search across databases such as PubMed, Web of Science, Cochrane Library, and Embase yielded 3,254 publications, with 22 high-quality papers included for in-depth analysis. These studies demonstrated the role of epigenetic markers, such as DNA methylation patterns of genes like F2RL3 and AHRR and alterations in the miRNA expression profiles, as potential biomarkers for lung cancer diagnosis and treatment. The review highlights the need to expand research beyond homogenous adult male groups typically found in high-risk occupational environments to broader population demographics. Such diversification can reduce biases and enhance the relevance of findings to various clinical contexts, fostering the development of personalized preventive and therapeutic measures. In conclusion, our findings underscore the potential of innovative epigenetic therapies, such as DNA demethylating drugs and histone modification agents, to counter environmental toxins’ carcinogenic effects. The growing interest in miRNA therapies and studies aiming to correct aberrant methylation patterns indicate significant strides toward better lung cancer management and a healthier future for global communities.

Background and objective: The COVID-19 global pandemic has necessitated the urgency for innovative mental health interventions. We performed a comprehensive review of the available literature on the utility and efficacy of arts therapies in treating mental health problems, with special emphasis on their deployment during the COVID-19 pandemic, aiming to provide some evidence for the application of this therapy.Methods: The potential studies were systematically sourced from five authoritative databases: PubMed, Embase, the Cochrane Library, Web of Science, and the CNKI database. The evaluation of these studies was conducted based on stringent criteria, including validity, suitability, therapeutic potential, and consistency. Each piece of included literature was meticulously scored in accordance with these criteria, thus ensuring the inclusion of only the most robust studies in this review. The data from these Randomized Controlled Trials (RCTs) were carefully extracted using the PICO(S) framework, ensuring a comprehensive and systemic approach to data collection. In order to emphasize the variability in the effects of differing arts therapies on COVID-19-induced psychiatric disturbances, the sourced literature was systematically categorized and scrutinized based on distinct modalities.Results: Out of the 7,250 sourced articles, 16 satisfied the inclusion conditions. The therapies were predominantly meditation (n = 7), supplemented by individual studies on color therapy (n = 3), music therapy (n = 2), and single studies on horticultural therapy, dance therapy, mindfulness and music therapy, and yoga and music therapy (n = 4 collectively). These various forms of arts therapies had a positive short to medium-term impact on the mental health of COVID-19 patients. Besides improving patients' physical and mental health, these therapies can also be employed to mitigate mental health issues among healthcare professionals.Conclusion: The COVID-19 pandemic has profound and long-lasting implications for public mental health. Diverse forms of arts therapies are potentially effective in addressing related psychiatric symptoms. The integration of artificial intelligence might further enhance the efficacy and scalability of arts therapies in future implementations.