Tyrone Tai On Kwok

BACKGROUND As artificial intelligence (AI) becomes embedded in health sciences education and clinical practice, understanding the AI literacy of teaching faculty has emerged as a pressing institutional priority. Existing instruments were largely developed for students or general adult populations, leaving limited validation evidence for tools tailored to health sciences educators. OBJECTIVE This study reports psychometric findings from an AI literacy survey administered to teaching faculty members in health sciences education at a university in Hong Kong. Specifically, it (1) describes the empirically derived factor structure of a 44-item generative AI literacy instrument and evaluates its coherence against the original four-domain theoretical model; (2) assesses the reliability and subscale score profiles of the empirically derived factors to characterize the current AI literacy levels of health sciences teaching faculty; and (3) discusses the implications of these findings for targeted professional development and institutional AI governance, with specific reference to the health sciences education context and identifies future research directions for further psychometric validation. METHODS A cross-sectional census-approach survey was administered to teaching faculty members involved in health sciences education at a university in Hong Kong. A 52-item instrument underwent expert review and cognitive interviewing, yielding a refined 44-item version. Exploratory factor analysis with maximum likelihood extraction and varimax rotation examined the preliminary latent structure. Unit-weighted subscale scores were computed, and internal consistency was assessed using Cronbach's α. RESULTS Of 140 eligible teaching faculty members, 126 completed the survey (response rate 90%). Five interpretable factors emerged: Foundational AI Knowledge and Basic Operational Skills; Pedagogical Integration and Classroom Application; Institutional and Collaborative AI Governance; Prompt Engineering and Output Quality Assurance; and Personal Ethical Stance and Responsible Practice. The 44-item pool showed excellent internal consistency (Cronbach's α = 0.965), and empirical subscales showed acceptable to good internal consistency (α = 0.78 - 0.85). Staff reported the strongest scores on Prompt Engineering (mean 7.45 out of 10, SD 1.70) and Personal Ethical Stance (mean 7.15, SD 1.80). Institutional Governance was the only subscale below the midpoint 5.5 (mean 4.35, SD 2.19), indicating a potential collective governance gap. CONCLUSIONS AI literacy among health sciences teaching faculty may be more differentiated than the four-domain frameworks anticipate. Our findings distinguish personal ethics from institutional governance and general tool use from advanced prompt engineering. Further multisite validation is required before standardized use. These findings provide an empirically grounded foundation for the design of targeted staff development programs and inform a revised instrument for wider deployment across comparable health sciences education institutions.

Background: Generative artificial intelligence (GenAI) is enhancing virtual patient simulations in health care education by enabling dynamic, adaptive interactions, reshaping how clinical skills are taught. A synthesis of the current evidence is needed to guide implementation and future research, given the pace of technological advancement. Objective: This systematic review aims to synthesize empirical research on the design, implementation, and educational impact of GenAI-supported virtual patients in health care education. Methods: A systematic search was conducted across 5 databases (CINAHL, Medline, Embase, Scopus, and Web of Science) from their inception to March 19, 2026. Reference lists of included studies and relevant systematic reviews were also screened. Peer-reviewed studies in English that evaluated GenAI-supported virtual patients using quantitative or mixed methods were included. Two reviewers independently screened studies and extracted data. Study quality and risk of bias were assessed critically using JBI (Joanna Briggs Institute) checklists, with disagreements resolved by consensus. Results: A total of 15 studies met the inclusion criteria (total participants N=645), spanning health care disciplines, including nursing, medicine, pharmacy, radiography, and medical first-responder training. The virtual patients varied in design; input modalities included text (9 studies), voice (5 studies), or hybrid (1 study); output was text (9 studies), speech (5 studies), or both (1 study); 6 studies used 3D-embodied avatars, while 9 used nonembodied interfaces. A total of 13 studies used OpenAI GPT models (eg, ChatGPT), 1 used a fine-tuned model from a different provider, and 1 evaluated multiple model families (Claude, GPT, and open-source). Further, 6 studies used controlled experimental designs, including 3 randomized controlled trials (RCTs); the remainder were cross-sectional or prepost evaluations. Primary outcomes included user perceptions (14 studies), communication skills (4 studies), clinical reasoning (3 studies), and performance (7 studies). In controlled comparisons, GenAI-supported virtual patients consistently improved outcomes relative to control conditions: for example, enhanced clinical decision-making (RCT, n=21), ophthalmology history-taking skills (RCT, n=26), and medical history-taking performance (crossover RCT, n=20). The evidence base is characterized by brief intervention durations, a predominant reliance on single-session interactions, and a general lack of underpinning educational theory. No meta-analysis was performed due to the limited number of studies and significant heterogeneity in designs, interventions, and outcome measures. Conclusions: The evidence supports the feasibility and acceptability of GenAI-supported virtual patients, with positive learner perceptions and promising outcomes for skills development. However, critical limitations remain in emotional-behavioral complexity, simulation adaptability, and research design rigor (eg, limited use of control groups and validated instruments). The review offers educators, instructional designers, and policymakers actionable insights for integrating dynamic, artificial intelligence–driven simulations while identifying crucial gaps—such as the need for theoretical grounding, longitudinal studies, and standardized design protocols—that must be addressed for safe and effective implementation.

Promoting regular physical exercise is crucial for healthy ageing, yet many older adults remain physically inactive. Artificial intelligence (AI), evolving

Background: The widespread prevalence of chronic pain (CP) significantly impacts daily functioning worldwide. In mainland China, maintaining engagement in biopsychosocial interventions remains challenging. Gamification, designed based on self-determination theory, can enhance motivation, while machine learning (ML) algorithms can assist clinicians in dynamically optimizing pain management. Objective: This study aimed to (1) evaluate the preliminary effectiveness of a gamified pain management (GPM) program on CP and psychological outcomes and (2) identify key factors of significant pain improvements through the application of ML to guide intervention adjustments. Methods: A single-arm, pre-post study was conducted with 16 participants with CP in mainland China, recruited via social media using convenience sampling. Participants engaged in a 10-week web-based GPM intervention consisting of education, physical activities, and gamified elements, including points, avatars, and feedback. Primary outcomes were pain intensity and interference measured by the Brief Pain Inventory. Secondary outcomes included anxiety, depression, and quality of life. Analysis included paired t tests, and ML models were trained to predict clinically meaningful pain reductions. Shapley additive explanations, least absolute shrinkage and selection operator regression, association rule mining, and Kaplan-Meier survival analysis were used to identify key predictors and optimal sessions and intervention durations across subgroups. Results: A total of 16 participants were engaged, with a mean age of 27.63 (SD 9.584) years. Results from paired t tests reported significant improvements in pain intensity (decreased by 27.3%, 95% CI 1.061 to 3.064; P =.001), pain interference (decreased by 27.3%, 95% CI 8.159-17.216; P <.001), and psychological distress, including anxiety ( t ₁₅ =3.538, 95% CI 0.969 to 3.906; P =.003) and depression ( t ₁₅ =4.559, 95% CI 2.230 to 6.145; P <.001). The gradient boosting model demonstrated the highest predictive accuracy (area under the curve=0.89 and accuracy=0.82). Least absolute shrinkage and selection operator regression identified session 3 (β=−0.45, 95% CI −0.68 to −0.22; P <.001) and session 5 (β=−0.32, 95% CI −0.59 to −0.05; P =.02) as most predictive of clinical success, while association rule mining revealed effective session combinations for different patient subgroups. Time-to-event analyses indicated that individuals with low back pain and higher baseline severity required longer intervention durations for improvement (5 wk; P =.03). Conclusions: This pilot study presents an innovative method that combines ML with dynamic engagement data from a GPM program during interventions, rather than relying on static baseline data in prior studies. The results show preliminary efficacy and identify specific optimal session combinations and personalized treatment durations for different pain subgroups. These exploratory findings contribute to the field by providing a data-driven method for adaptive, personalized digital health interventions that move beyond one-size-fits-all strategies, potentially enabling clinicians to modify content and dosage to improve engagement and outcomes if validated in larger sample trials.

Background: Parents of autistic children frequently experience elevated stress levels, depressive symptoms, and reduced well-being. Positive psychology interventions (PPIs) can strengthen resilience, and chatbots offer a scalable channel through which such skills can be delivered. However, evidence on the evaluation of large language model–guided PPI-based chatbots for this population is limited. Objective: This study evaluated the feasibility and acceptability of a GPT-powered chatbot (“Allie”). This study was designed to deliver culturally adapted PPIs to parents of autistic children and to explore their preliminary effects on well-being, depression, stress, and health-related quality of life. Methods: We conducted a single-arm mixed-methods pilot study with 19 parents with autistic children. These parents engaged with Allie for 2 weeks to complete 8 structured PPI exercises. The primary outcomes were feasibility (completion, ease of use, and practicality) and acceptability (multidimensional user ratings). Secondary outcomes were the World Health Organization–Five Well-Being Index (WHO-5), Patient Health Questionnaire-9, Perceived Stress Scale-10, and Short Form-12 Health Survey (version 2) Physical and Mental Component Summary scores. Outcomes were analyzed using paired t tests or Wilcoxon signed-rank tests. Optional postintervention interviews were analyzed using reflexive thematic analysis. Results: A total of 17 (89.5%) participants completed all the exercises, which indicated a high degree of procedural feasibility. There were also high ratings for ease of use and practicality (means 4.47/5, SD 0.70, and 4.32/5, SD 0.67, respectively). Acceptability was favorable (overall satisfaction mean=5.68/7, SD 0.70; prompt response time=6.37/7, SD 0.68). The WHO-5 score improved significantly from 32.84 to 46.11 (t18=2.48, P=.02; Cohen d=0.52). Changes in the Patient Health Questionnaire-9 (z=−0.49, P=.63; r=0.11), Perceived Stress Scale-10 (t18=−0.82, P=.43; Cohen d=0.12), and Short Form-12 Health Survey (version 2) Physical Component Summary (t18=−0.94, P=.36; Cohen d=0.18) and Mental Component Summary (t18=−0.89, P=.39; Cohen d=0.17) scores were not significant. Qualitative feedback (14/19) described benefits aligned with PPI mechanisms such as greater self-reflection, a more positive orientation, perspective-taking, emotional support, and coping skills. However, participants also suggested refinements, such as more natural conversation (colloquial Cantonese), shorter or less repetitive outputs, user-chosen sequencing with reminders and progress tracking, multimodal features, and autism spectrum disorder–specific resources. Conclusions: This pilot study revealed the feasibility, acceptability, and preliminary improvement in well-being (WHO-5) of a PPI-based GPT-powered chatbot, Allie, among parents of autistic children. Although there was no significant short-term change in other outcomes, the findings provide insights into design priorities, including personalization, conversational naturalness, multimodal content, and autism spectrum disorder–specific guidance. Larger, controlled trials with longer exposures and more diverse samples are needed to establish efficacy and durability. Trial Registration: ClinicalTrials.gov NCT06438120; https://clinicaltrials.gov/study/NCT06438120

Background: Although digital interventions have been widely used in chronic pain management, evidence on their effectiveness has demonstrated heterogeneity. They have low retention rates, which are exacerbated by a lack of feedback, social interaction, and engaging content, contributing to boredom and higher attrition. Gamification offers a possibility to overcome these barriers and enhance user motivation and engagement. Objective: This study aims to investigate the effects of an online gamified pain management program in a sample of adults with chronic noncancer pain. Methods: A 2-arm, single-blind randomized controlled trial will recruit 172 participants through Chinese hospitals and online platforms. Eligible participants will be randomized to 2 groups: a 10-week gamified pain management program for the experimental group and routine online pain management materials for the control group. Primary outcomes, including pain intensity and pain interference, and secondary outcomes, including fear avoidance, emotion, exercise adherence, quality of life, and user satisfaction, will be assessed at baseline, after the intervention (10 weeks), and at a 3-month follow-up. A mixed-design ANOVA and intention-to-treat analysis will be used to evaluate intervention effects. Results: The trial is registered, with recruitment ongoing from July 2025 to August 2026. A total of 172 participants (86 per group) will be recruited. As of November 17, 2025, we have recruited 19 participants. Results are expected to be published in March 2027 Conclusions: The findings will address a critical gap by examining a novel gamified intervention within a theory-driven design to provide an engaging solution to improve self-management in people with chronic pain. Trial Registration: Chinese Clinical Trial Registry ChiCTR2400094247; https://www.chictr.org.cn/hvshowproject.html?id=266029&v=1.0 International Registered Report Identifier (IRRID): DERR1-10.2196/80542

Background: The role of technology in disease management has gained significant attention, mobile health technology for obstructive sleep apnea (OSA) remains underdeveloped, with limited research exploring its applications. This study explored OSA individuals’ health literacy, perceived needs for improvement, information preferences, and acceptance of smartphone-based messaging interventions. Methods: The study comprised two parts. Part 1 was a cross-sectional, self-administered online survey using non-probability convenience sampling conducted in the inpatient ward and outpatient clinic of Queen Mary Hospital, Hong Kong, from May to July 2020. The questionnaire assessed health literacy, perceived needs, and views on smartphone-based messaging interventions to enhance self-management of OSA. Written consent was obtained, and the survey took approximately 10 minutes to complete. Part 2 involved a focus group interview in August 2020 with nine randomly selected participants from Part 1, exploring their views on perceived needs and smartphone-based messaging interventions. Results: A total of 108 participants (82% men; 40.7% aged ≥60 years) were included. Participants self-reported their OSA severity as mild (21.3%), moderate (17.6%), and severe (23.1%), while 38% were unaware of their severity. The results showed low OSA-related health literacy among participants, with no significant differences by age or years since diagnosis. Most participants (76.8%) expressed a strong desire to improve their health. High demand for OSA-related information was reported, including sleep quality (83.3%), OSA-related knowledge (82.4%), weight control (81.5%), habit improvement (78.7%), and emotional management (66.7%). The messaging intervention was well accepted, with high feasibility (82.4%) and usability (72.2%). Conclusions: This study highlights low OSA-related health literacy and a strong demand for authoritative health information. Most found that the messaging intervention was feasible and useful in improving health-related habits and OSA management. The study underscores the need for tailored health education, personalized interventions targeting perceived needs, and innovative messaging solutions to enhance treatment adherence and self-management in OSA individuals.

BACKGROUND Parents of autistic children frequently experience elevated stress levels, depressive symptoms, and reduced well-being. Positive psychology interventions (PPIs) can strengthen resilience, and chatbots offer a scalable channel through which such skills can be delivered. However, evidence on the evaluation of large language model–guided PPI-based chatbots for this population is limited. OBJECTIVE This study evaluated the feasibility and acceptability of a GPT-powered chatbot (“Allie”). This study was designed to deliver culturally adapted PPIs to parents of autistic children and to explore their preliminary effects on well-being, depression, stress, and health-related quality of life. METHODS We conducted a single-arm mixed-methods pilot study with 19 parents with autistic children. These parents engaged with Allie for 2 weeks to complete 8 structured PPI exercises. The primary outcomes were feasibility (completion, ease of use, and practicality) and acceptability (multidimensional user ratings). Secondary outcomes were the World Health Organization–Five Well-Being Index (WHO-5), Patient Health Questionnaire-9, Perceived Stress Scale-10, and Short Form-12 Health Survey (version 2) Physical and Mental Component Summary scores. Outcomes were analyzed using paired t tests or Wilcoxon signed-rank tests. Optional postintervention interviews were analyzed using reflexive thematic analysis. RESULTS A total of 17 (89.5%) participants completed all the exercises, which indicated a high degree of procedural feasibility. There were also high ratings for ease of use and practicality (means 4.47/5, SD 0.70, and 4.32/5, SD 0.67, respectively). Acceptability was favorable (overall satisfaction mean=5.68/7, SD 0.70; prompt response time=6.37/7, SD 0.68). The WHO-5 score improved significantly from 32.84 to 46.11 (t18=2.48, P=.02; Cohen d=0.52). Changes in the Patient Health Questionnaire-9 (z=−0.49, P=.63; r=0.11), Perceived Stress Scale-10 (t18=−0.82, P=.43; Cohen d=0.12), and Short Form-12 Health Survey (version 2) Physical Component Summary (t18=−0.94, P=.36; Cohen d=0.18) and Mental Component Summary (t18=−0.89, P=.39; Cohen d=0.17) scores were not significant. Qualitative feedback (14/19) described benefits aligned with PPI mechanisms such as greater self-reflection, a more positive orientation, perspective-taking, emotional support, and coping skills. However, participants also suggested refinements, such as more natural conversation (colloquial Cantonese), shorter or less repetitive outputs, user-chosen sequencing with reminders and progress tracking, multimodal features, and autism spectrum disorder–specific resources. CONCLUSIONS This pilot study revealed the feasibility, acceptability, and preliminary improvement in well-being (WHO-5) of a PPI-based GPT-powered chatbot, Allie, among parents of autistic children. Although there was no significant short-term change in other outcomes, the findings provide insights into design priorities, including personalization, conversational naturalness, multimodal content, and autism spectrum disorder–specific guidance. Larger, controlled trials with longer exposures and more diverse samples are needed to establish efficacy and durability. CLINICALTRIAL ClinicalTrials.gov NCT06438120; https://clinicaltrials.gov/study/NCT06438120