2026-04-01
Norvie Jalani, Jaybee Bazan, Jaime Kristoffer Punzalan
Background: Artificial intelligence (AI)–enabled digital health kiosks are increasingly used in workplaces and communities to promote health awareness, especially in low- and middle-income countries. However, evidence on their real-world use, user acceptability, and immediate behavioral responses remains limited, especially outside formal clinical care. Objective: This study evaluated the implementation experience, user acceptability, and immediate self-reported actions associated with the use of an AI-enabled workplace health kiosk among public school teachers in an urban, low-resource setting in the Philippines. Methods: We conducted a study involving 384 teachers who used an AI health kiosk during wellness activities. The kiosk provided informational health indicators. Postuse surveys assessed usability; trust; privacy concerns; and self-reported actions, such as health consultations and sharing results. Analyses were descriptive and exploratory. The study did not evaluate diagnostic accuracy, clinical validity, disease prevalence, or health outcomes. Results: Most participants (162/189, 85.7%) rated the kiosk experience as good or excellent, and 93.1% (176/189) found it easy to use. Overall, trust in kiosk results was high, although 31.7% (60/189) of the participants expressed privacy concerns. After using the kiosk, 70.9% (134/189) of the participants consulted a health care professional, and 66.7% (126/189) made lifestyle changes. A small percentage (32/189, 16.9%) reported no follow-up actions, mainly due to uncertainty about the next steps. User feedback highlighted convenience and accessibility but also noted operational issues such as queuing and connectivity problems. Conclusions: In this workplace setting, an AI health kiosk was feasible, acceptable, and linked to immediate self-reported health actions. Findings are preliminary and context specific. Formal validation, follow-up studies, and further evaluation are needed before use in diagnostic, population health, or policy contexts.
2026-03-30
Wanying Mao, Reham Shalaby, Ernest Owusu, Hossam Eldin Elgendy, Belinda Agyapong, Pierre Chue, Peter H Silverstone, Andrew J Greenshaw, Xin-Min Li, Ejemai Eboreime, Wesley Vuong, Arto Ohinmaa, Frank P MacMaster, Vincent Israel Opoku Agyapong
Background: The period following discharge from psychiatric inpatient care represents a critical transition phase marked by heightened vulnerability to relapse, including increased risks of emergency department (ED) utilization. Understanding the risk factors for ED utilization after hospital discharge will help identify individuals who should be targeted for enhanced follow up care in the community. Objective: This study aimed to examine the sociodemographic and clinical factors associated with psychiatric ED utilization within six months of discharge from inpatient psychiatric care among individuals assigned to different postdischarge interventions. The goal is to identify high-risk groups to inform targeted follow up strategies and enhance transitional care planning. Methods: This study analyzed secondary data from a pragmatic stepped-wedge cluster-randomized trial which recruited patients across ten health care sites in Alberta, Canada, from March 2022 to February 2024. For the primary study, a total of 1098 psychiatric inpatients were allocated to one of three post-discharge conditions: treatment as usual (TAU), SMS, or SMS plus peer support (SMS+ PS). Sociodemographic and clinical data were collected at discharge. ED visits 6-months postdischarge were recorded. tests identified variables associated with ED utilization. Significant predictors were entered into a logistic regression model to determine adjusted odds ratios (ORs) and 95% CIs. Results: Of the 1098 participants, demographic and clinical variables were examined for association with mental health ED visits at 6-months post discharge. Univariate analysis identified six significant predictors: age, ethnicity, relationship status, employment, housing status, and prior ED use. Logistic regression analysis identified several predictors of mental health ED visits 6-months postdischarge. Compared to participants under 25 years, those aged 26‐40 was less likely to revisit the ED (OR 0.66, 95% CI 0.46‐0.95), as were those over 40 years (OR 0.58, 95% CI 0.37‐0.92). Individuals identifying as mixed or other ethnicity were less likely than White people to return to the ED (OR 0.52, 95% CI 0.28‐0.96). Unemployed participants had higher odds of ED use than those employed (OR 1.66, 95% CI 1.18‐2.34). Prior ED attendance was the strongest predictor (OR 2.45, 95% CI 1.03‐5.80). Housing status showed varied but nonsignificant effects. Conclusions: This study highlights key demographic and clinical factors influencing psychiatric ED use following inpatient discharge. The findings emphasize the importance of targeted transitional care interventions, particularly for high-risk groups such as younger, unemployed, and previously ED-utilizing individuals, and support the integration of scalable approaches like SMS and peer support into discharge planning. Trial Registration: ClinicalTrials.gov NCT05133726; https://clinicaltrials.gov/study/NCT05133726
2026-03-30
Jacob Gordon, Julianna Lorenzo, Andrés Alvarado Avila, Bryant Norton, Eva Minahan, George J Greene, Ariel W Halle, Kathryn Macapagal
Background: Lesbian, gay, bisexual, transgender, and queer/questioning, plus (LGBTQ+) youth experience significant health challenges relative to their peers, including higher rates of HIV, sexually transmitted infections, and mental health symptoms, partly due to minority stressors. Digital health interventions hold promise for addressing these issues, but their effectiveness hinges on human-centered co-design that ensures relevance and engagement. Objective: This study aimed to examine the use of Discord as a platform for conducting human-centered design (HCD) activities to adapt a digital text-based intervention designed to improve HIV testing rates among LGBTQ+ youth. Methods: We recruited 21 LGBTQ+ youth (aged 13-18 years) in the United States via social media and participant registries, oversampling minoritized gender, racial, and ethnic identities to ensure diverse representation. Over 9 months, participants engaged in structured HCD activities on a private Discord server, including polls, open-ended discussions, and interactive feedback tasks. Design insights were collected iteratively and used to refine the intervention in real time. We also surveyed participants to examine the acceptability of Discord as a tool for hosting the HCD process. Results: We identified best practices for integrating HCD methods within Discord, including cocreating the server environment with participants and enabling real-time iteration of intervention components based on youth input. The privacy of the Discord server supported psychological safety; facilitated open and effective communication between participants and the research team; and fostered an informal, familiar atmosphere. Conclusions: Discord provides an effective and acceptable environment for conducting HCD processes in the design of digital health interventions. Its structural features, including anonymity, accessibility, and community-driven interaction, facilitated meaningful youth engagement in co-design activities. These insights offer a model for leveraging social media platforms to support participatory intervention development for LGBTQ+ populations.
2026-03-30
Chanchanok Aramrat, Poppy Alice Carson Mallinson, Papangkorn Inkaew, Pusit Seepheung, Nutchar Wiwatkunupakarn, Nida Buawangpong, Nick Birk, Judith Lieber, Santhi Bhogadi, Hemant Mahajan, Santosh Kumar Banjara, Bharati Kulkarni, Sanjay Kinra, Chaisiri Angkurawaranon
Background: Gait assessment is an important tool for evaluating health risks in older adults but remains underused in low-resource settings. We explored the feasibility of using a low-cost, simple walking protocol with smartphone video capture to extract health-related gait signals by classifying sex and age. Sex and age are fundamental biological factors linked to most health- and aging-related outcomes. Establishing baseline classification performance provides justification for future exploration of more complex health-related conditions using this protocol. Objective: This study aimed to assess whether pose parameters derived from smartphone-based gait videos can be used by machine learning models to classify age and sex. Methods: A cross-sectional study was conducted with 155 participants (Thailand: n=59, 38.1%; India: n=96, 61.9%). Participants performed a simple walking protocol while being recorded using smartphones. Pose estimation was conducted using the MediaPipe algorithm to extract 109 features related to joint distances, angles, and walking speed. For feasibility assessment, we calculated the proportion of recordings for which pose estimation could be extracted. Elastic-net logistic regression and histogram-based gradient boosting classifiers were used for analysis. Model performance was evaluated using 5-fold cross-validation. Outcomes were sex (male vs female) and age group (aged<65 vs ≥65 y). Results: Pose parameters were successfully extracted from 145 (93.5%) of the 155 video recordings. Among the 145 participants, 94 (64.8%) were female, and 55 (37.9%) were aged 65 years or older. The 2 analytic models demonstrated comparable performance. Sex classification achieved a maximum mean area under the receiver operating characteristic curve of approximately 0.90 (SD 0.06), whereas age classification achieved a maximum mean area under the receiver operating characteristic curve of approximately 0.70 (SD 0.09). Classification performance was primarily influenced by the number of features used, clothing characteristics, and the quality of pose estimation. Conclusions: This simple smartphone-based gait assessment protocol was able to extract meaningful pose parameters and classify biological features (age and sex). Further studies are warranted to evaluate its potential utility for disease screening, risk stratification, and longitudinal health monitoring.