This review focuses on foundation models in radiology and describes their key characteristics and methods for training, adapting, and evaluating; in addition, cautions and future directions associated with their responsible deployment in radiologic practices are discussed.

Background: The COVID-19 pandemic has resulted in a number of negative health related consequences, including impacts on mental health. More than 22% of Canadians reported that they had felt depressed in the last week, in response to a December 2020 national survey. Given the need to physically distance during the pandemic, and the increase in demand for mental health services, digital interventions that support mental health and wellness may be beneficial. Objective: The purpose of this research was to identify digital interventions that could be used to support the mental health of the Canadian general population during the COVID-19 pandemic. The objectives were to identify (1) the populations these interventions were developed for, inclusive of exploring areas of equity such as socioeconomic status, sex/gender, race/ethnicity and culture, and relevance to Indigenous peoples and communities; (2) the effect of the interventions; and (3) any barriers or facilitators to the use of the intervention. Methods: This study was completed using a Cochrane Rapid Review methodology. A search of Embase, PsycInfo, Medline, and Web of Science, along with Google, Million Short, and popular mobile app libraries, was conducted. Two screeners were involved in applying inclusion criteria using Covidence software. Academic articles and mobile apps identified were screened using the Standard Quality Assessment Criteria for Evaluating Primary Research Papers from a Variety of Fields resource, the American Psychiatric Association App Evaluation Framework, and the Mental Health Commission of Canada’s guidance on app assessment and selection. Results: A total of 31 mobile apps and 114 web-based resources (eg, telemedicine, virtual peer support groups, discussion forums, etc) that could be used to support the mental health of the Canadian population during the pandemic were identified. These resources have been listed on a publicly available website along with search tags that may help an individual make a suitable selection. Variability exists in the populations that the interventions were developed for, and little assessment has been done with regard to areas of equity. The effect of the interventions was not reported for all those identified in this synthesis; however, for those that did report the effect, it was shown that they were effective in the context that they were used. A number of barriers and facilitators to using these interventions were identified, such as access, cost, and connectivity. Conclusions: A number of digital interventions that could support population mental health in Canada during the global COVID-19 pandemic were identified, indicating that individuals have several options to choose from. These interventions vary in their purpose, approach, design, cost, and targeted user group. While some research and digital interventions addressed equity-related considerations, more research and focused attention should be given to this area.

The integration of artificial intelligence (AI) into health care promises to address long-standing challenges, offering innovative solutions to improve patient outcomes, health equity, clinician productivity, and system efficiency.^1,2 As the deployment of AI interventions expands, clinical evidence becomes increasingly crucial in validating their efficacy and safety.^3-7 However, there exists a notable gap between the extensive theoretical research on ethical concerns in AI applications in health care and the practical challenges encountered by clinical investigators in clinical settings.⁸ This empirical study aims to bridge this gap by examining the practical ethical considerations in the design and implementation of clinical trials involving AI.

Objective The aim of this study is to examine patients’ experiences in integrated care (IC) settings. Design Qualitative study using semistructured interviews. Settings Two IC sites in Toronto, Canada: (1) a community-based primary healthcare centre, supporting patients with hepatitis C and comorbid mental health and substance use issues; and (2) an integrated bariatric surgery programme, an academic tertiary care centre. Participants The study included patients (n=12) with co-occurring mental and physical health conditions. Seven participants (58%) were female and five (42%) were male. Methods Twelve indepth semistructured interviews were conducted with a purposeful sample of patients (n=12) with comorbid mental and physical conditions at two IC sites in Toronto between 2017 and 2018. Data were collected and analysed using grounded theory approach. Results Four themes emerged in our analysis reflecting patients’ perspectives on patient-centred care experience in IC: (1) caring about me; (2) collaborating with me; (3) helping me understand and self-manage my care; and (4) personalising care to address my needs. Patients’ experiences of care were primarily shaped by quality of relational interactions with IC team members. Positive interactions with IC team members led to enhanced patient access to care and fostered personalising care plans to address unique needs. Conclusion This study adds to the literature on creating patient-centredness in IC settings by highlighting the importance of recognising patients’ unique needs and the context of care for the specific patient population.

Advances in algorithm development have shown that artificial intelligence (AI) and machine learning can augment clinical decision-making, promoting diagnostic excellence.^1-4 While there is consensus that data flow between organizations and developers is necessary to develop AI algorithms, many organizations remain reluctant to share health data for AI due to organizational apprehensions and competing priorities, affecting equitable AI development in the health care sector.^5-9

The development of artificial intelligence (AI) applications in healthcare is often positioned as a solution to the greatest challenges facing global health. Advocates propose that AI can bridge gaps in care delivery and access, improving healthcare quality and reducing inequity, including in resource-constrained settings. A broad base of critical scholarship has highlighted important issues with healthcare AI, including algorithmic bias and inequitable and inaccurate model outputs. While such criticisms are valid, there exists a much more fundamental challenge that is often overlooked in global health policy debates: the dangerous mismatch between AI’s imagined benefits and the material realities of healthcare systems globally. AI cannot be deployed effectively or ethically in contexts lacking sufficient social and material infrastructure and resources to provide effective healthcare services. Continued investments in AI within unprepared, under-resourced contexts risk misallocating resources and potentially causing more harm than good. The article concludes by providing concrete questions to assess AI systemic capacity and socio-technical readiness in global health.