Stress is a prevalent concern in modern society, affecting mental and physical health. Accurate and timely stress detection can enable individuals to take preventive actions, reducing its adverse effects. This work presents the CalmMe app, an AI-driven and mobile-based system that uses heart rate variability (HRV) data to predict stress levels using sensor technology and machine learning models, and then provide personalized and evidence-based interventions. HRV data, automatically collected via Apple Watch, is processed using statistical and time-domain features, with SDNN (standard deviation of Normal-To-Normal intervals) as the primary metric. The comparative evaluation of convolutional neural network (CNN), Support Vector Machine (SVM), and three other models (Random Forest, Logistic Regression, and LSTM) show that CNN is the best performing model overall with an accuracy and F1-score of 98.5% and 98%, respectively. The app visualizes stress trends, categorizes stress into chronic, mild, and low levels, and recommends personalized interventions to manage stress effectively. This research showcases the practicality of integrating wearables and artificial intelligence (AI) for stress monitoring and management by designing and developing the CalmMe app which holds promise as a personalized and adaptive system for promoting the physical and mental well-being of people globally.
This study investigates the impact of a gamified intervention, inspired by the Gamiflow framework, on promoting composting behaviors in a workplace setting. Using a hybrid approach combining physical compost bins and a Slack-based gamified system, the intervention engaged 20 participants, with half assigned to a control group and the other half participating in the gamified program over three days. Results showed significant improvements in composting confidence among participants in the gamified program compared to the control group (t(18) = 4.05, p < 0.001). Although knowledge and motivation differences were not statistically significant (p > 0.05), a trend was observed for improved composting behavior (Chi(2) = 3.232, p = 0.072). Post-intervention, the Slack channel continued to serve as a space for discussions on composting and eco-friendly practices, highlighting its role in fostering long-term community engagement. Limitations such as the relatively small sample size and short duration suggest future research should explore long-term effects and larger-scale implementations.
Despite the prevalence of mental health issues such as anxiety and depression, access to timely and personalized care remains limited. SerenCoach is an AI-driven, persuasive, and mobile-based digital coach designed to support anxiety and depression management through multimodal analysis of facial expressions and voice. By leveraging advanced technologies, including Facial Expression Recognition (FER) model, Large Language Models (LLMs) such as Llama3, and persuasive strategies, SerenCoach assesses users' anxiety and depression risk levels and provides personalized interventions. SerenCoach's methodology involves engaging in a conversation/dialogue with users while analyzing facial expressions and verbal expression of personal experiences or health condition (which is automatically converted to text) to assess their risk level. Based on the assessed risk - categorized as low, medium, or high - the app delivers personalized and evidence-based interventions including guided meditation, gratitude journaling, AI-powered therapist, and access to emergency services. SerenCoach motivates users through goal setting, reminder, and progress tracking to enhance user engagement. This paper discusses the design and development of SerenCoach, and demonstrates its ability to improve mental wellbeing through interactive, adaptive, and real-time support.
This study builds on a previous umbrella review that highlighted the effectiveness of combining Extended Reality (XR) and Game-Based Interventions (GBI) in mental health treatment, showing positive results in reducing anxiety, depression, and stress. XR included augmented, virtual, and mixed reality, while GBI encompassed serious games, gamification, game-based learning and training, exergames, and commercial video games. The review analyzed 201 studies and selected 16 (nine meta-analyses, six systematic reviews, and one scoping review). Given the role of design in digital mental health solutions, here, we conducted a reverse engineering analysis to understand how these interventions worked by reviewing descriptions and visual representations from each study, breaking down XR-GBI into core game elements. This allowed us to identify design features and motivational purposes linked to their effectiveness, as well as underused elements to inform future research and innovation. Frequently used game elements included “Emotions”, “Single-player”, “Consequence”, “Simulation”, “Customization”, “Meaning”, “Level”, “Exploration”, “Narrative”, and “Feedback”. The knowledge of frequent and underused game elements offers insights to advance XR-GBI design knowledge and support their use in digital mental health to boost intrinsic motivation, supporting cognitive and behavioral change. However, the absence of multiplayer features reveals a research gap, suggesting XR-GBI could be improved by adding cooperative, competitive, or collaborative elements. Future research and interventions should build on the game elements identified here to enhance mental health outcomes while exploring new elements, particularly social dynamics, to strengthen engagement and therapeutic impact.
Miscarriage, the involuntary fetal death before the 20th week of gestation, is a common event that can result in negative mental health responses. In Portugal, symptoms of psychological morbidities have been reported by nearly half of women who suffered a miscarriage. Still, very few reported being offered psychological support although in need of immediate support. Considering the lack of health practitioners worldwide, Virtual Reality (VR) is a valid alternative for psychological support in this context. We present a multi-scenario VR system that leverages traditional protocols from Cognitive- Behavioral and Grief therapy to deliver a preventive intervention targeted at miscarriage. We ran a user study to evaluate usability and presence of tasks that address emotions, social support, and adaptation to the loss. We measured presence and usability, and conducted a thematic analysis on the qualitative data gathered. The results showed that the scenarios provided adequate levels of positive factors of presence, low negative effect, and above-average usability. Users' feedback highlighted high immersion and feelings of embodiment with their avatar. However, difficulties when writing on a virtual keyboard, controller settings and visual cues are amongst the issues that need improvement.
Nystagmus is a condition of rapid, uncontrollable eye movement. It affects ca. 24 out of 10,000 people in the general population. Measuring the impact of nystagmus on visual acuity remains challenging, as patients often perform well on standard tests like Snellen charts. For this reason we have created a suite of games, BRIGHTSIGHT BURGERS, with simple mechanics measuring specific player performance metrics related to nystagmus. Our preliminary result indicate the potential effectiveness of games as tools for health assessment in this context. We provide a detailed description of the games developed, the incorporation of player performance metrics for assessment of the severity of the nystagmus condition, and describe results of a preliminary analysis and insights gained. These preliminary results indicate that healthy subjects take significant less time to finish any of the assigned tasks in any of the games developed, as compared to subjects with nystagmus.
The emergence of Large Language Models (LLMs) such as ChatGPT has led to applications like digital interventions across diverse domains, including digital dietary behavior change interventions (DBCIs). While various AI-based apps, web-based platforms, and gamified mobile applications have shown their effectiveness as persuasive tools for promoting dietary behavioral change, the capabilities of ChatGPT in this domain remain unexplored. This study examines qualitative responses from users informing the different persuasive strategies employed by ChatGPT in dietary management. Through a mixed study, we evaluated ChatGPT's overall persuasiveness for diet management and user insights on the strengths and gaps of its use and persuasive capabilities. We recruited 17 ChatGPT-4 users and engaged them in interactions with AI-generated meal plans. Subsequently, they provided feedback through interviews and a perceived persuasiveness scale questionnaire. Our findings reveal that users generally perceive ChatGPT as persuasive in promoting healthy eating behaviors (p<.006). Thematic analysis emerging from our interview transcripts showed that ChatGPT has implemented some persuasive strategies while indicating the need to include additional ones e.g. self-monitoring, reminders, and trustworthiness. Based on our findings, we contribute to the field by providing recommendations for developers on integrating additional persuasive strategies while considering the ethical implications of using LLMs for dietary management.
Acculturative stress creates barriers to mental health and intergenerational communication in Latine-American families. This paper presents a preliminary usability study of a serious game designed to address this challenge. Tu Jardin, developed using the Acculturative Game Design (AGD) framework and principles of Self-Determination Theory, fosters family dialogue, empathy, and cultural understanding through interactive gameplay. A mixed-methods study with 8 participants (4 migrantgeneration parents and their first-generation adult children) evaluated usability, engagement, and communication over two weeks. Results indicate high usability (UMUX = 85.71/100), strong autonomy (M = 6.33/7.00) and competence satisfaction (M = 6.00/7.00), and effectiveness in facilitating conversations about cultural and generational challenges. Participants reported high comfort discussing sensitive topics (M = 4.63/5.00) and increased empathy (M = 4.75/5.00). However, technological barriers for older users and pre-existing communication patterns influenced effectiveness. This study highlights the potential of serious games to address acculturative stress while emphasizing the need for age-inclusive and customizable designs. To support further research, we openly share the complete Unity project files and Figma design assets for adaptation and extension.
The Serious Games and Applications for Health (SEGAH) conference, established in 2011, has become a central venue for research on serious games, virtual reality, and gamification in health-related applications. This bibliometric analysis examines publication trends, citation patterns, keyword evolution, and geographic contributions across 12 editions of SEGAH (2011-2024). A total of 502 papers authored by 1,606 contributors were analyzed using a custom Python-based pipeline that leveraged libraries such as pandas, networkx, matplotlib, and seaborn, as well as APIs from IEEE, Crossref, and OpenCitations. Results show a steady growth in publications, with notable peaks in 2017 and 2023. The total citation count ranges from 2,045 to 2,373 depending on the data source, as values differ across IEEE, Crossref, and Google Scholar. The most cited papers focus on serious games for health applications, braincomputer interfaces, and virtual reality-based training. While earlier papers have had more time to accumulate citations, recent years (2023-2024) show a higher percentage of non-cited papers. Keyword analysis reveals that Serious Games is the most frequently occurring research theme (148 occurrences), followed by Virtual Reality (85) and Rehabilitation (36). The geographic distribution highlights Portugal as the leading contributor, followed by Brazil, Canada, and Australia, with increasing participation from European and Asian countries. Collaboration networks show strong interdisciplinary cooperation across institutions. These findings provide a comprehensive overview of SEGAH's research landscape and its evolving contributions to serious games in healthcare.
Sex education plays an important role in developing a comprehensive understanding of sexual health, and empowering individuals to make responsible choices. However, in countries like India, sex education is often neglected due to societal stigma surrounding discussions about sex. This lack of proper sexual health knowledge frequently leads to risky sexual choices. We present Sex-Educated, a theory-driven, persuasive mobile application specifically designed to promote sexual health awareness among Indians. The app aims to increase knowledge about healthy sexual behavior and encourage changes in risky sexual behaviors. A quantitative study of 46 participants who used the app for 7 days and completed a questionnaire about their experience followed by an interview with 21 participants to uncover more qualitative insights. Results showed a positive change in sexual behavior and knowledge of sexual health. Based on our findings, we offer recommendations for designing mHealth interventions that improve knowledge and awareness within underserved populations.
This study introduces the “AR Magic Plate game”, a WebAR-based, gamified augmented reality system designed to support cognitive function and social participation among elders with dementia. Integrating interactive food group identification tasks with reflexive sensory cues rather than didactic nutrition instruction, the platform delivers automatic prompts and rewards to reinforce healthy eating responses. Users engage by scanning AR markers on food cards and selecting the missing category from six major food groups; correct selections earn points that contribute to personalized rankings. A pilot deployment with 12 participants aged 71-103 years demonstrated that the system's intuitive interface and gamified incentives successfully motivated engagement across the entire age span, with most users achieving high scores (4-5 out of 5). Statistical analysis confirmed no significant association between age and performance, underscoring the intervention's capacity to evoke active participation irrespective of chronological age. These results suggest that the AR Magic Plate game offers a scalable, low-barrier, non-pharmacological approach for delivering cognitive stimulation and social interaction in dementia care.
The prevalence of non-communicable diseases (NCDs) is increasing. NCDs, such as cardiovascular diseases, cancers, diabetes, and chronic respiratory diseases, are not contagious but are typically caused by unhealthy behaviors. However, many of these diseases are largely preventable. Research shows that 80 % of heart diseases, strokes, and type 2 diabetes, as well as over one-third of cancers, can be prevented by eliminating tobacco use, adopting a healthy diet, maintaining good mental health, staying physically active, and reducing harmful alcohol consumption. For many individuals, changing behavior to minimize the aforementioned risk factors can be challenging and often leads to short-term results only. Previous research in NCD prevention has mainly focused on developing interventions that target specific behavior categories in isolation, disregarding the interconnected nature of human behavior, where improvements in one area can influence others. This work proposes a novel and holistic approach that acknowledges the complexity and interdependence of multiple factors influencing behavior change. The result is a gamified mobile app designed and developed to support long-term behavior change. A psychologist and a total of 25 members of the target group evaluated the application during different stages of development. The mobile app promotes positive attitudes toward behavior change, offering rewards for healthy actions and engaging users through a meaningful narrative, which enhances the effectiveness of interventions aimed at reducing NCD risk factors.
Autism is a wide spectrum, with each child presenting unique needs. Many assistive technologies for autism are excessively expensive, lack tangibility, or are not adapted to specific preferences. Those best positioned to design for these needs are individuals closest to them: family members, therapists, and teachers. With new means of rapid prototyping (user-friendly electronics, digital fabrication, and AI tools) and a 4-step method of our own, 15 novice designers from universities in the USA and Spain created assistive technology prototypes tailored to specific profiles. These prototypes were evaluated by 14 participants (families, teachers, therapists, and designers) via an online survey. Findings suggest rapid prototyping enables inexperienced designers to develop functional products that improve the well-being of children with autism. This work explores structured guidance for designing for autism, enabling even novice designers to effectively develop assistive technologies with proper mentorship.
Serious games have emerged as a valuable tool for enhancing learning across various fields, extending beyond entertainment to improve education and training outcomes. This research investigates the use of serious games as a tool for enhancing learning and identifies key requirements and aspects essential for improving their design process. We propose a conceptual framework that supports the development of impactful serious games, focusing on their educational and entertainment aspects. The framework includes three models-structure, behavioral dynamics, and user experience-that facilitate collaboration among multidisciplinary development teams and align game mechanics with learning objectives. It also provides a “dictionary” to help the development team adapt game mechanics to the game's educational goals. To validate the framework, we designed a serious game as a web application, redesigned an existing game, and compared our approach with existing frameworks. Results demonstrate that our framework offers more precise models for integrating the gaming and educational aspects, allows a detailed decomposition of game components, and provides clearer graphical and textual representations. This, in turn, simplifies the comparison of different games and provides deeper insights into game challenges and player engagement.
This study introduces a pioneering drone-based spatial gait analysis approach for scalable and ecologically valid urban health monitoring. Leveraging a processing pipeline integrating Drone-YOLO for object detection, YOLOv11-pose for pose estimation, ByteTrack for multi-object tracking, and geographical coordinate mapping, we achieved high-fidelity extraction of pedestrian keypoints and trajectories from drone imagery. Rigorous testing on 1679 pedestrians across age groups in Qingxiu Mountain Park, Nanning, China, revealed significant inter-group differences in gait speed, trunk inclination, and stride length variability. Spatial analysis highlighted elevated gait speeds in open, flat areas of the Main Gate Plaza, contrasting with significantly reduced speeds in congested, topographically complex Flower Plaza. “Cold spots” of gait speed, coinciding with high pedestrian density and uneven terrain, were identified in Flower Plaza, while “hot spots” were observed in open pathways of the Main Gate Plaza. These findings demonstrate the transformative potential of drone-based spatial gait analysis for urban health surveillance, evidence-based urban planning, and understanding the complex interplay between human movement, health proxies, and urban environments. Future research should enhance pipeline robustness in occluded urban settings and explore multi-modal sensor fusion to refine dynamic walking behavior analysis from aerial perspectives.
Accessibility in video games is essential to enable people with severe motor impairments to engage in interactive experiences. Traditional input methods, such as controllers and keyboards, create barriers for these players, requiring alternative interaction techniques. This paper presents Etherea, a video game that uses eye-tracking technology as the primary input method, allowing players with limited mobility to navigate and interact within a 3D environment. To evaluate user engagement and responsiveness to in-game stimuli, a case-study research was conducted on an individual affected by Spinal Muscular Atrophy (SMA). Adolescents with SMA often face limited gaming options, as few 3D games are developed with their unique needs in mind, given the condition's short life expectancy. ElectroDermal Activity (EDA) data was collected using a medical-grade wrist-worn device. Heatmaps were generated to visualize these physiological responses, providing insight into the emotional and cognitive engagement of the player. The findings highlight feasibility, potential, and challenges of real-time gaze-based interaction when individuals with severe motor impairments are involved.
Clinical decision-making is often complex and time-consuming due to the large amount of required data, contributing to an increase in mortality rates, particularly in non-cardiac surgery cases. To address this problem, we present an interactive artificial intelligence (AI) dashboard that combines visual analytics (VA) and machine learning (ML) to facilitate quick decision-making and enhance patient care. Visual analytics makes use of human perceptual and cognitive capabilities to quickly process complex data for decision-making. Machine learning is used to predict patients' states for quick decision-making. Though a lot of studies have emerged focusing on the application of VA for patient health care, such as diabetes and infectious diseases, little is known about its application to non-cardiac surgery. In this paper, we harness the capabilities of VA and ML to develop an interactive intelligent dashboard to enhance decision-making for non-cardiac surgery patients. This paper presents the design, development, and initial results of assessing the usability and usefulness of the dashboard with HCI experts and medical doctors. The results showed that users found the dashboard usable and useful. The qualitative analysis revealed six key themes, including the system's role in improving healthcare navigation and equity, its impact on patient-centered care delivery, and the ethical implications of predictive analytics in healthcare. We present our findings along with study limitations and future research directions.
Emergency departments (EDs) are high-pressure environments where factors like rapid decision-making, overcrowding and resource constraints can lead to errors and reduction in the quality of provided care. At the Aarhus University Hospital (AUH) in Denmark, patient data such as medical history is collected on a large scale and made available digitally through an Electronic Patient Journal (EPJ) to enhance overall patient care. However, the volume of data poses challenges for the medical staff in the ED, necessitating efficient ways to filter critical information. In this context, this paper describes the design of an application for “red flagging”, which will later be developed using Artificial Intelligence (AI). Its goal is to identify critical patient information and highlight potential risks that might otherwise be overlooked by the ED's medical staff. This research examines the topic from the user's perspective, exploring different methods to incorporate a red flagging system into existing healthcare workflows. The primary focus is on investigating the potential design and visualization of the red flagging functionality to ensure that the information delivered by the AI will benefit the ED staff. In this context, a user-centered design process was implemented, resulting in the creation and evaluation of a design prototype. This prototype serves as a practical exploration of how such an application can be tailored to meet the needs and requirements of its users while aligning with existing systems. It also gives an outlook on the potential of integrating such systems, as well as the concerns and requirements that must be addressed to implement AI-based software into clinical practice.
Research into social compliance, emotional contagion and behavioural synchronicity shows promise for various avenues of work concerning human-computer interaction, and a wider understanding of emotion. Despite their relevance, few studies have applied findings from these domains to player experience modelling in a multiplayer game, in itself having applications in entertainment, education and healthcare. Further to this, of the little work making use of inter-player data to model aspects of player experience, none considers the differences that may be found across common multiplayer game modes. This work therefore makes use of data collected across players in a series of common multiplayer game modes, considering the utility of inter-player data for predictive modelling using artificial neural networks in each. Results suggest that approaches modelling measures of players' experiences in terms of discrete emotion intensities are best made using their own facial expressions in nearly all circumstances, but past this, facial expression data from team based and competitive game modes shows the greatest promise. Considering the additional data separations available to team-based gameplay, we find that data collected from players on an opposing team shows greater utility for prediction of target player experience than data collected from a player on the same team. Regarding this, we make suggestions for the most applicable avenues for future research into the utilisation of inter-player data for emotional modelling.
The significance of physical activity (PA) in maintaining overall health and well-being is crucial, particularly in today's sedentary lifestyle and rising obesity rate. Participating in enjoyable activities such as dancing holds the potential to boost PA levels and positively impact one's mood. Technological advancements offer opportunities to enhance individuals' engagement in various physical activities. This study investigated the effectiveness of an augmented reality (AR)-driven persuasive intervention aimed at improving users' physical activity through dancing. To accomplish our objective, we developed ARDancee, a persuasive mobile health intervention that integrates Augmented Reality, Machine Learning, and persuasive technology to encourage adults to elevate their PA through dancing. A 15-day user study involving 104 participants revealed that the intervention successfully motivated participants' engagement in physical activity. The contribution of this work is twofold: (1) the design and evaluation of an AR-driven persuasive mobile app, and (2) the provision of insights and design recommendations.
