Aug 2026· Proceedings of the International Symposium on Human Factors and Ergonomics in Health Care· Vol 15, pp. 12 - 16· 0 citations· 24 references
TL;DR
Results indicate that the configuration flow was perceived as easy to learn and use, with generally positive acceptance, and offer concrete design directions for researchers and developers building AI-assisted mental health tools, particularly for users blocked by cost, stigma, or geography.
Abstract
Limited access to mental health care, driven by clinician shortages and systemic barriers, highlights the need for scalable and accessible support solutions. The integration of generative artificial intelligence (GenAI) and virtual reality (VR) offers a promising direction by enabling personalized, immersive, and continuously available mental health interventions. This study presents the design and formative evaluation of a low-fidelity GenAI-VR prototype aimed at supporting individuals with mild to moderate depressive symptoms. Rather than evaluating a full AI-VR therapy system, the prototype simulated only the onboarding and configuration components, specifically AI-guided avatar selection, environment choice, and the guided setup flow, using a paper-based interface. Ten participants who screened positive for at least mild depressive symptoms (PHQ-9 5) completed interaction tasks, followed by the Usefulness, Satisfaction, and Ease of Use (USE) questionnaire and semi-structured interviews. Results indicate that the configuration flow was perceived as easy to learn and use, with generally positive acceptance. Qualitative findings highlight both ongoing barriers in traditional care and user- identified design needs for AI- and VR-based systems, including personalization, anonymity, and culturally adaptable design, alongside concerns about privacy and the limits of AI emotional understanding. Overall, findings offer concrete design directions for researchers and developers building AI-assisted mental health tools, particularly for users blocked by cost, stigma, or geography. Future work should evaluate fully implemented systems to assess real-time interaction quality and sustained engagement.
Virtual reality (VR) has increasingly been explored to support mental health interventions, including those informed by Cognitive Behavioural Therapy (CBT). However, many VR-based CBT systems report limited usability evaluation and minimal practitioner involvement, raising questions about their applicability beyond clinical settings. This study aimed to conduct a usability-focused validation of a gamified VR platform translating selected CBT-informed techniques for non-clinical use. Selected CBT techniques were implemented as short VR mini-games guided by a design rationale emphasising simplicity, symbolic interaction, and ease of use. A user study involving 58 university students evaluated usability using the System Usability Scale (SUS), ISO 9241-11-informed usability categories, and brief anxiety-related self-report measures. In addition, three psychological practitioners reviewed the platform and assessed therapeutic coherence and design alignment. Findings demonstrated good overall usability, positive immediate experiential responses, and practitioner support for the platform’s therapeutic coherence and suitability as a supportive digital wellbeing tool. The study demonstrates a structured usability-based validation approach for VR systems translating CBT-informed techniques and offers practical guidance for the design and evaluation of immersive mental health technologies.
Mashael Bin Sabbar, Gary Ushaw, Rich Davison· Multimodal Technologies and...· 0 citations
Extended Reality (XR) technologies, such as Virtual Reality (VR), are increasingly explored in mental health and therapeutic contexts, offering controlled and immersive environments for awareness, behavioral observation, and adaptive guidance. In this paper, we investigate how a set of interconnected XR experiences can support the early-stage understanding of progressively complex mental health conditions, including phobias, social anxiety, and psychosis-related and cognitive disorders. Rather than focusing on a single application, the proposed approach follows an incremental design, beginning with graded exposure scenarios targeting specific phobias, extending to interactive social experiences for social anxiety, and including cognitive simulations oriented toward psychosis-related challenges. Across these experiences, structured scenario progression, behavioral monitoring, and adaptive guidance mechanisms are employed to observe emotional reactions and stress-related patterns while maintaining user comfort and ethical safeguards. The research remains exploratory, and the current work outlines the conceptual framework, architectural considerations, and representative use cases supporting this design philosophy. Preliminary usability observations in academic settings indicate that immersive progression can enhance emotional awareness and interaction flow; structured questionnaire agreement percentages are reported in Table I. Although not clinically validated, the study contributes toward the development of immersive and connected mental health research environments aligned with smart and connected health principles, bridging awareness, early behavioral observation, and adaptive support within XR-based systems.
George-Gabriel Constantinescu, Adrian Iftene· Annual International Compute...· 0 citations
Virtual reality (VR) is an emerging modality for cognitive rehabilitation, but evidence in Singapore is limited. This pilot study examined the feasibility and preliminary effectiveness of a localized cognitive VR-based training program (COVERT) for individuals with post-stroke cognitive impairment, delivered using a hybrid model.
Nine participants (mean age = 54.0, SD = 10.0) were recruited from Hospital A and Hospital B over 19 months. Participants completed a 4-week VR program through tele-rehabilitation and conventional therapy. This single-arm feasibility pilot study assessed feasibility, cognitive function (Montreal Cognitive Assessment, Repeatable Battery for the Assessment of Neuropsychological Status (RBANS), Trail Making Test (TMT)), health-related quality of life (EuroQol Five-Dimension Questionnaire), usability (System Usability Scale), and motivation (Intrinsic Motivation Inventory, Virtual Reality Neuroscience Questionnaire).
Feasibility was high with 100% retention. RBANS total scores improved significantly (73.4–78.9,
p
= 0.020), with all participants showing delayed memory gains. Processing speed improved (TMT-A) and there was a trend toward better executive function (TMT-B). EuroQuol-5D scores increased. Usability was moderate and declined with age, while motivation remained high. Recruitment was challenging.
VR-based cognitive rehabilitation delivered through an experienced occupational therapy-led hybrid model is feasible and potentially effective for post-stroke cognitive impairment in Singapore. Larger trials are warranted to establish efficacy.
Shan Wei, Tan Amanda Pei Xuan, Teoh Ai Lin et al.· British Journal of Occupatio...· 0 citations
Background Suicide risk is disproportionately higher for rural veterans who often lack access to specialty-trained health professionals equipped to deliver effective prevention interventions. Virtual reality offers a scalable training solution to address these gaps. This mixed-methods feasibility study systematically developed and evaluated a prototype virtual reality simulation for a training module in suicide risk identification and lethal means safety counseling during rural veteran home visits. Methods Thirty participants (10 nursing/social work students, 10 health professionals, and 10 rural community members) completed the veteran suicide prevention simulation using Meta Quest 2 headsets. Sense of presence (including negative effects) was assessed with the ITC-Sense of Presence Inventory; additional outcomes included representativeness, acceptability, and cue recall. Results Participants reported high engagement, with moderate spatial presence, and ecological validity, and low negative effects (e.g., nausea). Prominent lethal means cues were highly recalled (firearms: 93.3%; alcohol: 83.3%), while subtler cues (e.g., isolation) were less frequently noted. Most endorsed representational accuracy, with qualitative feedback praising authenticity and suggesting improvements in interactivity and navigation. Conclusions Findings support the preliminary feasibility and acceptability of the VET-SAVR prototype for suicide risk identification and lethal means counseling training. Refinements to navigation, cue salience, and mitigation of negative VR effects are warranted before future efficacy testing.
Donna L. Schuman, Micki Washburn, Regina T. Praetorius et al.· PLoS ONE· 0 citations
Traditional mental health assessments for anxiety and depression often face limitations due to their overtly clinical nature and susceptibility to self-report and social desirability biases. To overcome these barriers, this preliminary study explores the feasibility and user acceptance of decision-based games as immersive, early-screening tools specifically targeting university students. Employing a qualitative descriptive design, the research integrated a multimedia production methodology with semi-structured interviews and user acceptance testing (UAT) involving clinical psychologists, academic experts, and student volunteers. The findings indicate that decision-based games can successfully and practically integrate standard psychometric tools, such as the GAD-7 and PHQ-9, yielding high user acceptance. However, experts stressed that to maintain psychological safety and clinical validity, these games must be strictly classified as preliminary screening tools rather than diagnostic instruments, and they must retain the exact original wording of the assessments. Furthermore, targeted design mechanics, including culturally resonant scenarios, minimalist anxiety-sensitive visuals, and brief 5- to 10-minute gameplay sessions, significantly enhance user engagement. Ultimately, well-designed decision-based games offer a viable, engaging, and less stigmatizing alternative to traditional questionnaires for routine mental health screening.
S. Samsuri, Zakaria Mohiuddin Khandaker, Syamil Rosli et al.· International Journal on Per...· 0 citations
Abstract Background Mobile health (mHealth) interventions with virtual coaches offer scalable and potentially cost-effective solutions for health behavior change. However, these interventions commonly present challenges, such as limited personalization and insufficient grounding in evidence-based strategies. Perfect Fit (PF; Perfect Fit consortium), a personalized mHealth intervention with a text-based virtual coach, supports adults in quitting smoking and becoming more physically active. By combining innovative techniques, including sensor technology, end user involvement, and evidence-based strategies, PF aims to address common challenges faced by mHealth interventions, including those with virtual coaches. Objective The study primarily investigated the feasibility and acceptability of PF. The secondary aim was to explore associations between sociodemographic, smoking-, and physical activity–related characteristics and the feasibility and acceptability outcomes. The third aim was to evaluate the feasibility of conducting the research study. Methods A single-arm, pre-post, mixed methods study was conducted in the Netherlands with 100 adults who smoked. The intervention lasted approximately 16 weeks. Data were collected at baseline, during the intervention, and postintervention (4 months). Quantitative data included usage data and self-report questionnaires on feasibility, acceptability, and baseline characteristics. Qualitative data were gathered through postintervention semistructured interviews. Analyses included descriptive and inferential analyses, as well as the framework approach for the qualitative data. Results PF usage varied considerably across participants (n=87). The mean satisfaction rating was 2.79 (SD 0.73; scale range 1‐4), and perceived usability had a median score of 67.50 (range 12.50‐87.50; scoring range 0‐100), indicating OK-to-good usability. The mean virtual coach acceptance rating was –0.27 (SD 1.30; scale range −3 to 3; n=77). Higher PF usage was associated with greater satisfaction, usability, and coach acceptance (all P≤.004). Frequent connection issues with the smartwatch were a disruptive factor. Qualitative findings (n=12) provided in-depth insights into PF’s feasibility and acceptability, encompassing both positive and negative experiences. For instance, some participants valued the virtual coach for its anonymity, low-threshold access, and the sense of control it offered, while others preferred a human coach for greater accountability. Suggested improvements included more varied content and enhanced adaptability of the coach to users’ input and personal situations. Exploratory analyses suggested that high PF users were older than moderate (P=.01) and low PF users (P=.05). Importantly, PF was perceived as similarly feasible and acceptable across socioeconomic groups (P>.05), aligning with one of the project’s goals. Finally, research procedures and recruitment strategies proved feasible. Conclusions PF shows potential as an accessible and inclusive strategy for multiple health behavior changes, contributing to public health. Findings highlight areas for improvement and can guide the future development of virtual coach interventions.
Milon H. M. van Vliet, E. Meijer, N. Albers et al.· JMIR Human Factors· 0 citations