Elizabeth Alvarez

Artificial intelligence (AI) chatbots are being explored to deliver health coaching across multiple contexts. However, the quality and safety of chatbot-generated advice is influenced by how prompts are constructed, and prompt design remains inconsistently described in the literature. This scoping review examined how prompt design has been applied and evaluated in AI health coaching chatbots and summarized the study designs, prompt strategies, and outcomes reported across studies. We conducted a scoping review following PRISMA-ScR guidance and searched PubMed, Embase/Ovid MEDLINE ALL, PsycINFO, IEEE Xplore, and Scopus for peer-reviewed studies published up to October 2025. Eligible studies examined prompt design in large language model–based health coaching chatbots. Data were extracted using a standardized form and synthesized narratively. Twelve studies were included, spanning mental health, medication use, physical activity, and nutrition contexts. Study designs were primarily simulation-based, with few involving real users. Prompt strategies were grouped into structural modifications, prompting techniques, and role-based approaches. Structural modifications, such as increasing specificity and adding constraints, were most common and were reported to improve response quality and clarity. Prompting techniques were reported to improve task performance but sometimes reduced focus or consistency. Role-based prompting influenced tone, specificity, and guideline alignment. Outcomes focused mainly on response quality, with fewer studies assessing safety or user experience and only one evaluating clinical outcomes. Prompt design is a key, modifiable determinant of chatbot performance. However, current evidence is limited by heterogeneous study designs and minimal real-world evaluation. Greater focus on prompt design is needed to improve the quality and safety of AI-delivered health coaching and its real-world impact on health outcomes.

In this secondary analysis of a pilot randomized controlled trial of university students aged 18 to 29 years, we assessed the feasibility of providing wearable devices to measure physical activity over 6 months, finding that daily adherence declined over time in both groups, while moderate and vigorous physical activity levels remained similar between the control and intervention groups.

This cross‑sectional study examined HIV/AIDS knowledge as a determinant of preventative and self‑protective sexual behaviour. The HIV Knowledge Questionnaire-18 (HIV-KQ-18) is one of the most widely used HIV knowledge scales. The objective of this study was to test the psychometric properties of the HIV-KQ-18 in Black people in Ontario. We analyzed the data from 1302 participants who completed the HIV-KQ-18 in a study conducted among Black people in Ontario. We estimated the internal consistency of this scale using Cronbach’s alpha. We analyzed the construct validity of the scale, testing hypotheses about HIV knowledge and age, education, employment status, gender, language and city using one-way ANOVA and independent sample t-tests. Cronbach’s alpha for the scale was 0.82 (95% CI: 0.80–0.84) suggesting good internal consistency. We observed significant differences in HIV knowledge scores across age, employment status, education, and gender. Higher HIV knowledge scores were also observed among participants residing in Toronto compared to Ottawa and among those who completed the questionnaire in English compared to French. The HIV-KQ-18 is a valid instrument to assess the level of HIV/AIDS knowledge among Black Ontarians, with robust internal consistency and construct validity. The HIV-KQ-18 identified important differences in HIV knowledge based on the characteristics examined, indicating the need for targeted initiatives to increase HIV-related knowledge.

Previous research identified high levels of burnout in the Canadian public health workforce during the COVID-19 pandemic. This study presents the prevalence of burnout, associated participant demographic and workplace characteristics, and associated secondary outcomes among Canadian public health physicians and residents one year after the end of the COVID-19 pandemic. Data were collected using an online survey distributed through Canadian public health associations and professional networks between April and May 2024. Validated tools were used to measure burnout (Oldenburg Burnout Inventory (OLBI)), screen for anxiety (GAD-2) and depression (PHQ-2), and professional fulfillment (Stanford Professional Fulfillment Index). Additional binary (yes/no) questions were asked on workplace safety topics (e.g., threats, assaults, being bullied) and professional plans. Fisher’s exact test and logistic regressions were used to model the association between burnout and sequelae of burnout, including symptoms of depression and anxiety, and professional fulfillment. Among 118 physicians who completed the OLBI, the prevalence of burnout was 63.6%. Additionally, 41.2% of physicians reported being threatened, assaulted or bullied during the pandemic. Physicians who screened positive for anxiety (19.3%) and depression (7.6%) had higher odds of burnout (OR 4.79, 95% CI 1.29-26.90, p = 0.01 and OR 2.10, 95% CI 0.38-21.65, p = 0.48, respectively). Moreover, physicians who had low levels of professional fulfillment (84.9%) also had higher odds of burnout (OR 12.5, 95% CI 3.21-72.76, p < 0.001). The prevalence of burnout among Canadian public health physicians and residents remains high post-pandemic and was associated with symptoms of depression, anxiety and low professional fulfillment. By implementing interventions to prevent and mitigate burnout, and promote recovery, the public health system will be better positioned to recruit and retain physicians to serve the population.

Introduction: Hospitalisation is one of the most stressful life events for older adults, particularly for those who are pre-frail or frail. Multi-component community-based interventions have the potential to address the complex needs of older adults post-acute care admission. While some available interventions have been developed with end-user engagement, fully involving older people who are pre-frail or frail in the design of interventions has been less common. Multi-component community-based interventions that address the needs of older adults and their care partners with potential implementation barriers informed by healthcare providers, community partners and health system decision makers are needed. This protocol paper describes the planned process of co-designing for older patients discharged into the community, a Post-Acute Care Intervention for Frailty using Information and Communication technology. Methods and analysis: The development of a complex multi-component frailty intervention which meets older people’s needs involves several concurrent tasks and methodologies, each informed by co-design and conducted with consideration to eventual implementation. These tasks include: (1) establishing a Research Advisory Board, (2) assessing the feasibility and validity of using hospital administrative data to identify frail or pre-frail older adults and their needs, (3) conducting a needs assessment of patients returning to the community, (4) mapping community assets to identify existing programmes and services to help tailor the intervention, (5) co-designing a multicomponent frailty intervention, (6) selecting study outcome measures and (7) selecting and tailoring a digital health patient portal to support intervention delivery, data capture and communication. Ethics and dissemination: Each task requiring ethics approval will be submitted to the Hamilton Integrated Research Ethics Board at McMaster University. Results will be disseminated through peer-reviewed journal articles, conferences and networks of relevant knowledge users who have the capacity to promote dissemination of the results. A toolkit will be developed to help researchers and healthcare providers replicate the methodology for other populations.

Background: Lifestyle or behavioural changes can help to address the burden associated with chronic diseases. However, they take time and use of multiple techniques or strategies tailored to a person’s needs. The primary objective of this study was to assess the feasibility of the Healthy Lifestyles Program (HLP), a novel 12-month complex intervention based in cognitive behavioural therapy and theories of behaviour change, delivered in a community-based setting in Hamilton, Canada. The secondary objective of the study was to explore implementation factors of the HLP. Methods: This pilot pragmatic randomised controlled trial used quantitative and qualitative evaluation methods. Participants were randomly allocated to either intervention group (n = 15) or comparator group (n = 15). The intervention group attended weekly group education sessions and met with the program intervention team monthly to create and review personalized health goals and action plans. The comparator group met with a trained research assistant every three months to develop health goals and action plans. We assessed program feasibility by measuring recruitment, participation and retention rates, missing data, and attendance. Implementation was assessed in accordance with the Reach, Effectiveness, Adoption, Implementation, Maintenance (RE-AIM) framework. Participant-directed and clinical outcome measures were analyzed for between and within group changes using Generalized Estimating Equations (GEE). Thematic analysis was conducted for qualitative data. Results: Retention rate was 60% (9/15) for the intervention group and 47% (7/15) for the comparator group. Less than 1% of participant-directed and clinical outcomes were missing for those that completed the study. Participants attended an average of 29 of 43 educational sessions and 100% of one-to-one sessions. The program intervention team valued the holistic approach to care, increased time and interaction with participants, professional collaboration, and the ability to provide counselling and health support. Location accessibility was an important factor facilitating implementation. Reducing the number of psycho-social education sessions and having access to a gym could improve retention and program delivery for a larger trial. Conclusion: This study demonstrated the feasibility of the HLP with minor modifications recommended for a larger trial and for the intervention.

Background: Despite a high burden of Human Papilloma Virus (HPV)-associated diseases, HPV vaccine uptake is disparate globally. The objective of this systematic review is to summarize the existing evidence on knowledge, attitudes, and practices (KAP) regarding HPV and the uptake of the HPV vaccine. Methods and analysis: We will conduct a systematic review of observational studies that report data on HPV KAP and vaccine uptake among people aged 16 and above. We will search MEDLINE, CINAHL, Embase, Emcare, Web of Science, Cochrane Library, Global Health, and PsycInfo. We will conduct screening, data extraction, and assessment of the methodological quality of the included studies in duplicate. A random-effects model will be used to pool data. Subgroup analysis will be done for age younger adults (≤ 26 years old) and older adults (> 26 years old), sex (men and women), income level (as per World Bank), and WHO region. This systematic review will be reported according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. The PROSPERO registration number for the review is CRD42024532230. Ethics and dissemination: Ethical approval is not necessary as this study will review secondary published data. Our findings will be disseminated as part of a doctoral thesis and through peer-reviewed journal publications and conferences.

A novel student-driven model of peer simulations using reverse case studies was developed during the COVID-19 pandemic to provide virtual instruction to fourth-year clinical veterinary students. Focus groups suggested that, while this teaching method could not replace hands-on clinical experience, it could be a valuable tool to clinically prepare students during their pre-clinical curriculum. The primary aim of this study was to determine whether this teaching method enhanced earlier curricular student comfort with clinical reasoning, communication, and peer role play as measured by pre- and post-surveys. A secondary aim was to evaluate clinical reasoning ability using the validated Modified Lasater Clinical Judgment Rubric (MCJR). Eighteen pre-clinical veterinary students participated in a 1-week course where they designed and presented clinical cases and participated through virtual role play as clients, clinicians, and observers. Our results demonstrated that students’ comfort in clinical reasoning and peer role play significantly improved ( p < .001 and p = .003, respectively) after participating in this activity. The role perceived to be the most helpful at developing clinical reasoning and communication skills was clinician, followed by client then observer. Results from the MCJR found significant discrepancies between facilitator scoring and student self- and peer-assessment ( p < .001). Common themes emerged including the benefits of engaging in self-reflection, peer-to-peer learning, experiencing case ownership and autonomy, and practicing communication and clinical reasoning skills. This teaching method provides a valuable alternative to client simulators and suggests having students create a case as a client offers a unique educational opportunity.

COVID-19 responses internationally have depended on physical distancing policies to manage virus transmission, given the initial absence of treatments and limitations on vaccine availability. Different jurisdictions have different contexts affecting their responses such as past epidemic experience, ratings of epidemic preparedness, and income level. COVID-19 responses in African countries have not been well-studied. A qualitative multiple embedded case study design was used to examine the COVID-19 policies in South Africa and Uganda from January 2020 to November 2021. This study included a documentary review using government websites and reports, news articles, and peer-reviewed journal articles to obtain data on policy responses and contextual factors. Epidemiological data were collected from public sources. Key informant interviews with relevant stakeholders were used to confirm findings and cover missing information. A comparative analysis was conducted to explore differences in implementation of different types of physical distancing policies and potential consequences of lifting or prolonging public health measures. South African and Ugandan policy responses included physical distancing measures such as lockdown, international travel bans, school closures, public transportation measures, and curfew, in addition to socioeconomic relief programs and vaccinations. Differences between jurisdiction policy responses existed in terms of overarching strategy, timing, and stringency. This study provided in-depth comparisons of COVID-19 policy responses and relevant contextual factors in South Africa and Uganda. The study showed how contextual factors such as population age, geographic distribution, and recent epidemic response experience can influence COVID-19 transmission and response. The study also showed differences in overall strategy, timing, and strictness of epidemic management policies in these jurisdictions. These findings suggest it may be important to have sustained, strict measures to limit the spread of COVID-19 and manage the course of a pandemic, which need to be further explored alongside other important social and economic pandemic outcomes.