Artificial intelligence in primary care practice: Qualitative study to understand perspectives on using AI to derive patient social data.

OBJECTIVE: To understand the perspectives of primary care clinicians and health system leaders on the use of artificial intelligence (AI) to derive information about patients' social determinants of health. DESIGN: Qualitative study. SETTING: Ontario, Canada. METHODS: Semistructured, 30-minute virtual interviews were conducted with eligible participants across Ontario wherein they were asked about their perceptions of using AI to derive social data for patients. A descriptive content analysis was used to elicit themes from the data. MAIN FINDINGS: A total of 12 interviews were conducted with 7 family physicians, 3 clinical team members of various health professions, and 2 health system leaders. Five main themes described the current state of social determinants of health information, perceived benefits of and concerns with using AI to derive social data, how participants would want to see and use AI-derived social data, and suggestions for ethical principles that should underpin the development of this AI tool. CONCLUSION: Most participants were enthusiastic about the possibility of using AI to derive social data for patients in primary care but noted concerns that should be addressed first. These findings can guide the development of AI-based tools for use in primary care settings.

Exploring Machine Learning Applications in Pediatric Asthma Management: Scoping Review.

BACKGROUND: The integration of machine learning (ML) in predicting asthma-related outcomes in children presents a novel approach in pediatric health care. OBJECTIVE: This scoping review aims to analyze studies published since 2019, focusing on ML algorithms, their applications, and predictive performances. METHODS: We searched Ovid MEDLINE ALL and Embase on Ovid, the Cochrane Library (Wiley), CINAHL (EBSCO), and Web of Science (core collection). The search covered the period from January 1, 2019, to July 18, 2023. Studies applying ML models in predicting asthma-related outcomes in children aged <18 years were included. Covidence was used for citation management, and the risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool. RESULTS: From 1231 initial articles, 15 met our inclusion criteria. The sample size ranged from 74 to 87,413 patients. Most studies used multiple ML techniques, with logistic regression (n=7, 47%) and random forests (n=6, 40%) being the most common. Key outcomes included predicting asthma exacerbations, classifying asthma phenotypes, predicting asthma diagnoses, and identifying potential risk factors. For predicting exacerbations, recurrent neural networks and XGBoost showed high performance, with XGBoost achieving an area under the receiver operating characteristic curve (AUROC) of 0.76. In classifying asthma phenotypes, support vector machines were highly effective, achieving an AUROC of 0.79. For diagnosis prediction, artificial neural networks outperformed logistic regression, with an AUROC of 0.63. To identify risk factors focused on symptom severity and lung function, random forests achieved an AUROC of 0.88. Sound-based studies distinguished wheezing from nonwheezing and asthmatic from normal coughs. The risk of bias assessment revealed that most studies (n=8, 53%) exhibited low to moderate risk, ensuring a reasonable level of confidence in the findings. Common limitations across studies included data quality issues, sample size constraints, and interpretability concerns. CONCLUSIONS: This review highlights the diverse application of ML in predicting pediatric asthma outcomes, with each model offering unique strengths and challenges. Future research should address data quality, increase sample sizes, and enhance model interpretability to optimize ML utility in clinical settings for pediatric asthma management.

Developing an AI Tool to Derive Social Determinants of Health for Primary Care Patients: Qualitative Findings From a Codesign Workshop.

PURPOSE: Information about social determinants of health (SDOH) is essential for primary care clinicians in the delivery of equitable, comprehensive care, as well as for program planning and resource allocation. SDOH are rarely captured consistently in clinical settings, however. Artificial intelligence (AI) could potentially fill these data gaps, but it needs to be designed collaboratively and thoughtfully. We report on a codesign process with primary care clinicians to understand how an AI tool could be developed, implemented, and used in practice. METHODS: We conducted semistructured, 50-minute workshops with a large urban family health team in Toronto, Ontario, Canada asking their feedback on a proposed AI-based tool used to derive patient SDOH from electronic health record data. An inductive thematic analysis was used to describe participants' perspectives regarding the implementation and use of the proposed tool. RESULTS: Fifteen participants contributed across 4 workshops. Most patient SDOH information was not available or was difficult to find in their electronic health record. Discussions focused on 3 areas related to the implementation and use of an AI tool to derive social data: people, process, and technology. Participants recommended starting with 1 or 2 social determinants (income and housing were suggested as priorities) and emphasized the need for adequate resources, staff, and training materials. They noted many challenges, including how to discuss the use of AI with patients and how to confirm their social needs identified by the AI tool. CONCLUSIONS: Our codesign experience provides guidance from end users on the appropriate and meaningful design and implementation of an AI-based tool for social data in primary care.

BETTER LIFE- guidelines for chronic disease preventive care for people aged 18-39 years: a literature review.

BACKGROUND: The original 'BETTER' (Building on Existing Tools To Improve Chronic Disease Prevention and Screening in Primary Care) approach consisted of a prevention-focused visit between participants aged 40-65 years and a "Prevention Practitioner" (PP), who empowered the participant to set achievable prevention and screening goals for cancers and chronic diseases. BETTER was successfully adapted for economically deprived communities (BETTER HEALTH) in Canada. Our objective was to conduct a review of guidelines in preparation for adapting the 'BETTER HEALTH' approach for younger adults aged 18-39 years living with lower income, a group known to have earlier mortality due to a higher prevalence of preventable chronic diseases than their peers with higher income. METHODS: We searched multiple electronic databases and grey literature for clinical practice guidelines on prevention/screening and included those that met the following criteria: published in English from 2008-2020 in Canada or any of the following countries (Australia, Ireland, New Zealand, Scotland, United States and England); and addressed prevention or screening. We assessed quality using the Appraisal of Guidelines for Research and Evaluation (AGREE) II tool and extracted data (publication details, recommendations, and Quality/Level of evidence as reported by authors) from sources with overall scores of 5 or higher. Final recommendations were compiled after harmonization with input from diverse stakeholders (co-investigators, PPs, and the Community Advisory Committee). RESULTS: We included a total of 85 guidelines, and developed a final list of 42 recommendations for 18-39 year-olds across 21 topics. Specific recommendations fell under the following topics: cancers, cardiovascular disease, diabetes, obesity, lifestyle (alcohol; healthy nutrition/physical activity); healthy relationships and healthy sexuality, immunization, oral health, social determinants of health, and substance use. CONCLUSION: We identified evidence-based guidelines on individual-level prevention/screening actions for adults 18-39 years old and relevant for those living with lower income which will directly inform development and implementation of the BETTER LIFE intervention.

Quantitative and qualitative outcomes associated with inpatient addiction consultation: a scoping review.

Background: Rates of acute care use, including hospital admission and readmission, are high for people who misuse substances. Hospitalization provides a valuable opportunity for intervention, but addiction treatment is often not addressed in the inpatient setting. Addiction consult services are a novel intervention intended to change hospital practices.Objectives: Comprehensively summarize outcomes (quantitative and qualitative) associated with inpatient addiction consult services.Methods: English-language searches of: Medline, CINAHL, Embase, The Cochrane Database of Systematic Reviews, PubMed, PsychInfo and Google Scholar were conducted from 2000 to November 2022. Studies reporting outcomes associated with addiction specialist consultation in the hospital setting were included. Four independent reviewers screened abstracts, and three reviewers screened full-text articles.Results: A total of 1,113 results underwent title and abstract screening and 43 studies were included. Outcomes associated with addiction specialist consultation were heterogeneous. Quantitative clinical outcomes focused on pharmacotherapy, healthcare utilization, and outpatient follow-up. Consultation improved rates of pharmacotherapy use, but had inconsistent effects on health care use, and overall follow-up rates were low. Consultation was associated with reduced overdose rates and 90-day mortality. Additional outcomes related to medical learners' educational achievements and qualitative results described positive effects on trainees, healthcare providers, and patients seen by specialized consult services. Access to dedicated providers improved experiences in hospitals for both people who misuse substances and their healthcare providers.Conclusion: Addiction specialist consultations are related to several clinical metrics, but some outcomes (e.g. pharmacotherapy initiation) may be more amenable to intervention than others (healthcare utilization). Qualitative findings provide important context for quantitative clinical results.

Exploring the pharmacist's role in supporting newcomer international students and their families with the transition to the Canadian healthcare system including medication use: Protocol for a qualitative study.

Canada welcomes a large number of newcomers every year including international students and their families. The over 800,000 international students who arrived in Canada in 2022, are twice as likely to face difficulties in accessing healthcare services compared to those who were born in Canada. Lack of access to healthcare services may jeopardize their full participation in Canadian society. Pharmacists are highly accessible healthcare providers due to their regular contact with the public, extended working hours, and wide distribution of pharmacies. Given the expanding role of pharmacists in Canada, pharmacists can be a great resource for international newcomers to address their healthcare needs when transitioning to the Canadian healthcare system and exploring available services. In this study, we will explore how international students and their families, who make up a significant segment of newcomers to Canada each year, transition to Canada's healthcare system and identify their main challenges related to developing coping skills for managing diseases and navigating the complexities of prescription and nonprescription medication use. To do so, we will conduct virtual interviews with newcomer international students who have lived experience with transitioning to the Canadian healthcare system. This study will help understand the international student experience and identify how pharmacists can deliver a tailored package of pharmaceutical services to this population to best address their healthcare needs when transitioning to the Canadian healthcare system with the goal of reducing healthcare gaps and inequities. By exploring the healthcare challenges faced by these students, our findings will help pinpoint precise areas where pharmacists can practice to their full scope including medication management, patient education, and transitional care. Consequently, the study will offer detailed recommendations on how pharmacists can better support this population and thereby help alleviate the overall strain on the primary healthcare system.

Role of Antioxidant Therapy in the Treatment and Prognosis of COVID-19: A Systematic Review and Meta-analysis of Randomized Controlled Trials.

Background: A significant aspect of the SARS-CoV-2 pathology involves oxidative stress, characterized by an imbalance between the production of harmful free radicals and the body's antioxidant defenses. With the ongoing evolution of SARS-CoV-2, the investigation into non-virus-specific therapeutic options, such as antioxidant therapy, has gained importance. Objectives: This systematic review and meta-analysis aimed to summarize data from randomized control trials (RCTs) to evaluate the effectiveness and safety of antioxidant therapy in patients with SARS-CoV-2 infection. Methods: We searched the peer-reviewed indexed literature on MEDLINE, Cochrane Central Register of Controlled Trials (CENTRAL), CINAHL, EMBASE, International Pharmaceutical Abstracts, and Scopus, from inception to July 2023. Results: The search identified 3306 articles from which 25 were included for quantitative synthesis, with 5 studies eligible for meta-analysis. Antioxidant therapies included zinc, vitamin A, vitamin C, and combination treatments. Zinc interventions showed mixed results regarding intensive care unit admissions and hospital stays. Vitamin A studies indicated improvements in inflammatory markers. Vitamin C studies displayed inconsistent effects on clinical improvement and hospitalization. Combination treatments suggested benefits in symptom clearance and cytokine storm reduction. Meta-analysis of vitamin C studies found no significant difference in C-reactive protein concentrations (-0.50; 95% CI: -3.63, 2.63; I2 = 0%), intensive care unit stay duration (pooled mean difference: 1.44; 95% CI: 0.07, 2.81; I2 = 0%), or mortality (pooled odds ratio: 0.55; 95% CI: 0.28, 1.09; I2 = 0%), with a slight trend favoring reduced hospitalization duration (pooled mean difference: -2.37; 95% CI: -2.99, -1.76; I2 = 49%). Of the 25 studies, 8 were high quality with low bias, 6 had some concerns, and 11 were low quality with high bias. Conclusions: The review presents mixed efficacy of antioxidant therapies for SARS-CoV-2, with some studies indicating potential benefits. Further well-designed large-scale RCTs are warranted to determine the definitive role of antioxidants in SARS-CoV-2 treatment.This systematic review was registered at PROSPERO as CRD42023430805.

Interventions in ambulatory healthcare settings to reduce social isolation among adults aged 18-64: a systematic review.

BACKGROUND: Social isolation is associated with increased all-cause and premature mortality, poor chronic disease management, and mental health concerns. Limited research exists on interventions addressing social isolation among individuals under 65 despite its increasing prevalence among young and middle-aged adults. AIM: To identify interventions from the extant literature that address social isolation and loneliness in ambulatory healthcare settings in adults aged 18-64, and to identify elements of successful studies for future intervention design. DESIGN & SETTING: Systematic review of interventions targeting social isolation in community-dwelling adults aged 18-64 within ambulatory healthcare settings. METHOD: A search strategy was developed to identify relevant articles in the following databases: Ovid MEDLINE, Embase, EBM Reviews, Scopus, CINAHL and PsychInfo. Data were extracted on study design and setting, intervention type, outcome related to social isolation/loneliness and scale of measure used. RESULTS: 25,078 citations were identified and underwent title and abstract screening. 75 articles met our inclusion criteria and were synthesised, including an assessment of bias. Effective interventions were delivered in community health settings, incorporated a group component, and used digital technologies. They also addressed the association between mental health and social isolation using CBT approaches and enhanced self-management and coping strategies for chronic conditions through psycho-educational interventions. CONCLUSION: Future research should prioritise adults living in low- and middle-income countries, racialized individuals, as well as those with fewer educational opportunities. There is also a need to advance research in primary care settings, where longitudinal patient-provider relationships would facilitate the success of interventions.

Chronic disease prevention and screening outcomes for patients with and without financial difficulty: a secondary analysis of the BETTER WISE cluster randomised controlled trial.

OBJECTIVE: Building on Existing Tools To improvE chronic disease pRevention and screening in primary care Wellness of cancer survIvorS and patiEnts (BETTER WISE) was designed to assess the effectiveness of a cancer and chronic disease prevention and screening (CCDPS) programme. Here, we compare outcomes in participants living with and without financial difficulty. DESIGN: Secondary analysis of a cluster-randomised controlled trial. SETTING: Patients of 59 physicians from 13 clinics enrolled between September 2018 and August 2019. PARTICIPANTS: 596 of 1005 trial participants who responded to a financial difficulty screening question at enrolment. INTERVENTION: 1-hour CCDPS visit versus usual care. OUTCOME MEASURES: Eligibility for a possible 24 CCDPS actions was assessed at baseline and the primary outcome was the percentage of eligible items that were completed at 12-month follow-up. We also compared the change in response to the financial difficulty screening question between baseline and follow-up. RESULTS: 55 of 265 participants (20.7%) in the control group and 69 of 331 participants (20.8%) in the intervention group reported living with financial difficulty. The primary outcome was 29% (95% CI 26% to 33%) for intervention and 23% (95% CI 21% to 26%) for control participants without financial difficulty (p=0.01). Intervention and control participants with financial difficulty scored 28% (95% CI 24% to 32%) and 32% (95% CI 27% to 38%), respectively (p=0.14). In participants who responded to the financial difficulty question at both time points (n=302), there was a net decrease in the percentage of participants who reported financial difficulty between baseline (21%) and follow-up (12%, p<0.001) which was similar in the control and intervention groups. The response rate to this question was only 51% at follow-up. CONCLUSION: The BETTER intervention improved uptake of CCDPS manoeuvres in participants without financial difficulty, but not in those living with financial difficulty. Improving CCDPS for people living with financial difficulty may require a different clinical approach or that social determinants be addressed concurrently with clinical and lifestyle needs or both. TRIAL REGISTRATION NUMBER: ISRCTN21333761.

The Conceptualization and Measurement of Research Impact in Primary Health Care: Protocol for a Rapid Scoping Review.

BACKGROUND: The generation of research evidence and knowledge in primary health care (PHC) is crucial for informing the development and implementation of interventions and innovations and driving health policy, health service improvements, and potential societal changes. PHC research has broad effects on patients, practices, services, population health, community, and policy formulation. The in-depth exploration of the definition and measures of research impact within PHC is essential for broadening our understanding of research impact in the discipline and how it compares to other health services research. OBJECTIVE: The objectives of the study are (1) to understand the conceptualizations and measures of research impact within the realm of PHC and (2) to identify methodological frameworks for evaluation and research impact and the benefits and challenges of using these approaches. The forthcoming review seeks to guide future research endeavors and enhance methodologies used in assessing research impact within PHC. METHODS: The protocol outlines the rapid review and environmental scan approach that will be used to explore research impact in PHC and will be guided by established frameworks such as the Canadian Academy of Health Sciences Impact Framework and the Canadian Health Services and Policy Research Alliance. The rapid review follows scoping review guidelines (PRISMA-ScR; Preferred Reporting Items for Systematic Review and Meta-Analysis Extension for Scoping Reviews). The environmental scan will be done by consulting with professional organizations, academic institutions, information science, and PHC experts. The search strategy will involve multiple databases, citation and forward citation searching, and manual searches of gray literature databases, think tank websites, and relevant catalogs. We will include gray and scientific literature focusing explicitly on research impact in PHC from high-income countries using the World Bank classification. Publications published in English from 1978 will be considered. The collected papers will undergo a 2-stage independent review process based on predetermined inclusion criteria. The research team will extract data from selected studies based on the research questions and the CRISP (Consensus Reporting Items for Studies in Primary Care) protocol statement. The team will discuss the extracted data, enabling the identification and categorization of key themes regarding research impact conceptualization and measurement in PHC. The narrative synthesis will evolve iteratively based on the identified literature. RESULTS: The results of this study are expected at the end of 2024. CONCLUSIONS: The forthcoming review will explore the conceptualization and measurement of research impact in PHC. The synthesis will offer crucial insights that will guide subsequent research, emphasizing the need for a standardized approach that incorporates diverse perspectives to comprehensively gauge the true impact of PHC research. Furthermore, trends and gaps in current methodologies will set the stage for future studies aimed at enhancing our understanding and measurement of research impact in PHC. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/55860.

Adaptation and qualitative evaluation of the BETTER intervention for chronic disease prevention and screening by public health nurses in low income neighbourhoods: views of community residents.

BACKGROUND: The BETTER intervention is an effective comprehensive evidence-based program for chronic disease prevention and screening (CDPS) delivered by trained prevention practitioners (PPs), a new role in primary care. An adapted program, BETTER HEALTH, delivered by public health nurses as PPs for community residents in low income neighbourhoods, was recently shown to be effective in improving CDPS actions. To obtain a nuanced understanding about the CDPS needs of community residents and how the BETTER HEALTH intervention was perceived by residents, we studied how the intervention was adapted to a public health setting then conducted a post-visit qualitative evaluation by community residents through focus groups and interviews. METHODS: We first used the ADAPT-ITT model to adapt BETTER for a public health setting in Ontario, Canada. For the post-PP visit qualitative evaluation, we asked community residents who had received a PP visit, about steps they had taken to improve their physical and mental health and the BETTER HEALTH intervention. For both phases, we conducted focus groups and interviews; transcripts were analyzed using the constant comparative method. RESULTS: Thirty-eight community residents participated in either adaptation (n = 14, 64% female; average age 54 y) or evaluation (n = 24, 83% female; average age 60 y) phases. In both adaptation and evaluation, residents described significant challenges including poverty, social isolation, and daily stress, making chronic disease prevention a lower priority. Adaptation results indicated that residents valued learning about CDPS and would attend a confidential visit with a public health nurse who was viewed as trustworthy. Despite challenges, many recipients of BETTER HEALTH perceived they had achieved at least one personal CDPS goal post PP visit. Residents described key relational aspects of the visit including feeling valued, listened to and being understood by the PP. The PPs also provided practical suggestions to overcome barriers to meeting prevention goals. CONCLUSIONS: Residents living in low income neighbourhoods faced daily stress that reduced their capacity to make preventive lifestyle changes. Key adapted features of BETTER HEALTH such as public health nurses as PPs were highly supported by residents. The intervention was perceived valuable for the community by providing access to disease prevention. TRIAL REGISTRATION: #NCT03052959, 10/02/2017.

Advocating for Policy Change: Examples Emerging From a Medical-Legal Partnership in Primary Care.

Medical-legal partnerships bring legal services directly into clinical settings. Policy advocacy is often opportunistic and varies across partnerships. Our objective was to study policy advocacy that emerged from a medical-legal partnership in Toronto over a four-year period. This study consisted of a document review and thematic analysis, triangulated with data from interviews with legal team members and health providers. We defined policy advocacy as actions associated with attempts to change policy or legislation. The medical-legal partnership engaged in seven distinct cases of policy advocacy: disability support form requirements, changing workplace review, challenging barriers to citizenship, housing, publicly funded medication program (pharma care), safe injection sites, and the need for increased social assistance. Actions taken included presentations at conferences and submissions of briefs to government. We found that a medical-legal partnership resulted in policy advocacy with issues arising from both the health and the legal team with impacts likely greater than if each group had acted alone.

A Brief Tool to Screen Patients for Precarious Employment: A Validation Study.

PURPOSE: Precarious employment, defined by temporary contracts, unstable employment, or job insecurity, is increasingly common and is associated with inconsistent access to benefits, lower income, and greater exposure to physical and psycholosocial hazards. Clinicians can benefit from a simple approach to screen for precarious employment to improve their understanding of a patient's social context, help with diagnoses, and inform treatment plans and intersectional interventions. Our objective was to validate a screening tool for precarious employment. METHODS: We used a 3-item screening tool that covered key aspects of precarious employment: non-standard employment, variable income, and violations of occupational health and safety rights and protections. Answers were compared with classification using the Poverty and Employment Precarity in Southern Ontario Employment Index. Participants were aged 18 years and older, fluent in English, and employed. They were recruited in 7 primary care clinic waiting rooms in Toronto, Canada over 12 months. RESULTS: A total of 204 people aged 18-72 years (mean 38 [SD 11.3]) participated, of which 93 (45.6%) identified as men and 119 (58.3%) self-reported as White. Participants who reported 2 or more of the 3 items as positive were almost 4 times more likely to be precariously employed (positive likelihood ratio = 3.84 [95% CI, 2.15-6.80]). CONCLUSIONS: A 3-item screening tool can help identify precarious employment. Our tool is useful for starting a conversation about employment precarity and work conditions in clinical settings. Implementation of this screening tool in health settings could enable better targeting of resources for managing care and connecting patients to legal and employment support services.

An evaluation of an employment assistance program focused on people living with HIV in Toronto, Canada.

Unemployment is more common among people living with HIV (PLWH) compared to the general population. PLWH who are employed have better physical and mental health outcomes compared to unemployed PLWH. The main objective of this mixed-methods study was to conduct a program evaluation of Employment Action (EACT), a community-based program that assists PLWH in Toronto, Ontario, Canada to maintain meaningful employment. We extracted quantitative data from two HIV services databases used by EACT, and collected qualitative data from 12 individuals who had been placed into paid employment through EACT. From 131 clients included in the analysis, 38.1% (n = 50) maintained their job for at least 6 weeks within the first year of enrollment in the EACT program. Gender, ethnicity, age, and first language did not predict employment maintenance. Our interviews highlighted the barriers and facilitators to effective service delivery. Key recommendations include implementing skills training, embedding PLWH as EACT staff, and following up with clients once they gain employment. Investment in social programs such as EACT are essential for strengthening their data collection capacity, active outreach to service users, and sufficient planning for the evaluation phase prior to program implementation.

Screening for poverty and related social determinants to improve knowledge of and links to resources (SPARK): development and cognitive testing of a tool for primary care.

BACKGROUND: Healthcare organizations are increasingly exploring ways to address the social determinants of health. Accurate data on social determinants is essential to identify opportunities for action to improve health outcomes, to identify patterns of inequity, and to help evaluate the impact of interventions. The objective of this study was to refine a standardized tool for the collection of social determinants data through cognitive testing. METHODS: An initial set of questions on social determinants for use in healthcare settings was developed by a collaboration of hospitals and a local public health organization in Toronto, Canada during 2011-2012. Subsequent research on how patients interpreted the questions, and how they performed in primary care and other settings led to revisions. We administered these questions and conducted in-depth cognitive interviews with all the participants, who were from Saskatchewan, Manitoba, Ontario, and Newfoundland and Labrador. Cognitive interviewing was used, with participants invited to verbalize thoughts and feelings as they read the questions. Interview notes were grouped thematically, and high frequency themes were addressed. RESULTS: Three hundred and seventy-five individuals responded to the study advertisements and 195 ultimately participated in the study. Although all interviews were conducted in English, participants were diverse. For many, the value of this information being collected in typical healthcare settings was unclear, and hence, we included descriptors for each question. In general, the questions were understood, but participants highlighted a number of ways the questions could be changed to be even clearer and more inclusive. For example, more response options were added to the question of sexual orientation and the "making ends meet" question was completely reworded in light of challenges to understand the informal phrasing cited by English as a Second Language (ESL) users of the tool. CONCLUSION: In this work we have refined an initial set of 16 sociodemographic and social needs questions into a simple yet comprehensive 18-question tool. The changes were largely related to wording, rather than content. These questions require validation against accepted, standardized tools. Further work is required to enable community data governance, and to ensure implementation of the tool as well as the use of its data is successful in a range of organizations.

Exploring patient perspectives on how they can and should be engaged in the development of artificial intelligence (AI) applications in health care.

BACKGROUND: Artificial intelligence (AI) is a rapidly evolving field which will have implications on both individual patient care and the health care system. There are many benefits to the integration of AI into health care, such as predicting acute conditions and enhancing diagnostic capabilities. Despite these benefits potential harms include algorithmic bias, inadequate consent processes, and implications on the patient-provider relationship. One tool to address patients' needs and prevent the negative implications of AI is through patient engagement. As it currently stands, patients have infrequently been involved in AI application development for patient care delivery. Furthermore, we are unaware of any frameworks or recommendations specifically addressing patient engagement within the field of AI in health care. METHODS: We conducted four virtual focus groups with thirty patient participants to understand of how patients can and should be meaningfully engaged within the field of AI development in health care. Participants completed an educational module on the fundamentals of AI prior to participating in this study. Focus groups were analyzed using qualitative content analysis. RESULTS: We found that participants in our study wanted to be engaged at the problem-identification stages using multiple methods such as surveys and interviews. Participants preferred that recruitment methodologies for patient engagement included both in-person and social media-based approaches with an emphasis on varying language modalities of recruitment to reflect diverse demographics. Patients prioritized the inclusion of underrepresented participant populations, longitudinal relationship building, accessibility, and interdisciplinary involvement of other stakeholders in AI development. We found that AI education is a critical step to enable meaningful patient engagement within this field. We have curated recommendations into a framework for the field to learn from and implement in future development. CONCLUSION: Given the novelty and speed at which AI innovation is progressing in health care, patient engagement should be the gold standard for application development. Our proposed recommendations seek to enable patient-centered AI application development in health care. Future research must be conducted to evaluate the effectiveness of patient engagement in AI application development to ensure that both AI application development and patient engagement are done rigorously, efficiently, and meaningfully.

Eviction filings during bans on enforcement throughout the COVID-19 pandemic: an interrupted time series analysis.

OBJECTIVE: Bans on evictions were implemented to reduce the spread of COVID-19 and to protect vulnerable populations during a public health crisis. Our objective was to examine how three bans on eviction enforcement impacted eviction filings from March 2020 through January 2022 in Ontario, Canada. METHODS: Data were derived from eviction application records kept by the Ontario Landlord and Tenant Board. We used segmented regression analysis to model changes in the average weekly filing rates for evictions due to non-payment of rent (L1 filings) and reasons other than non-payment of rent (L2 filings). RESULTS: The average number of weekly L1 and L2 applications dropped by 67.5 (95% CI: 55.2, 79.9) and 31.7 (95% CI: 26.7, 36.6) filings per 100,000 rental dwellings, respectively, following the first ban on eviction enforcement (p < 0.0001). Notably, they did not fall to zero. Level changes during the second and third bans were insubstantial and slope changes for L2 applications varied throughout the study period. The L1 filing rate appeared to increase towards the end of the study period (slope change: 1.3; 95% CI: 0.1, 2.6; p = 0.0387). CONCLUSION: Our findings suggest that while the first ban on eviction enforcement appeared to substantially reduce filing rates, subsequent bans were less effective and none of them eliminated eviction filings altogether. Enacting upstream policies that tackle the root causes of displacement would better equip jurisdictions during future public health emergencies.

RéSUMé: OBJECTIF: Les ordonnances d'expulsion résidentielles ont été suspendues pour réduire la propagation de la COVID-19 et pour protéger les populations vulnérables pendant une crise de santé publique. Notre objectif était d'examiner l'impact de trois interdictions d'exécution d'ordonnance d'éviction sur les requêtes d'expulsion de mars 2020 à janvier 2022 en Ontario, au Canada. MéTHODES: Les données ont été tirées des dossiers de requêtes d'expulsion conservés par la Commission de la location immobilière de l'Ontario. Nous avons utilisé une analyse de régression segmenté pour modéliser les changements dans les taux hebdomadaires moyens de requêtes d'expulsion pour non-paiement du loyer (requêtes L1) et pour des raisons autres que le non-paiement du loyer (requêtes L2). RéSULTATS: Le nombre moyen de demandes hebdomadaires de dépôts de requêtes L1 et L2 a chuté de 67,5 % (IC à 95% : 55,2, 79,9) et de 31,7 % (IC à 95% : 26,7, 36,6) pour 100 000 logements locatifs, respectivement, suite à la première interdiction d'exécution des expulsions. Il est à noter qu'elles ne sont pas tombées à zéro. Les changements du taux de requêtes au cours de la deuxième et la troisième interdictions n'étaient pas substantiels et les changements de pente pour les applications L2 ont varié tout au long de la période d'étude. Le taux de dépôt de L1 a semblé augmenter vers la fin de la période d'étude (changement de pente : 1,3; IC à 95% : 0,1, 2,6; p = 0,0387). CONCLUSION: Nos résultats suggèrent qu'alors que la première interdiction d'exécution des expulsions a semblé réduire considérablement les taux de dépôt d'expulsion, les interdictions ultérieures ont été moins efficaces et aucune d'entre elles n'a complètement éliminé les dépôts d'expulsion. L'adoption de politiques en amont qui s'attaquent plutôt aux causes profondes des expulsions permettrait de mieux équiper les juridictions lors de futures urgences de santé publique.

Addressing health inequity during the COVID-19 pandemic through primary health care and public health collaboration: a multiple case study analysis in eight high-income countries.

BACKGROUND: The COVID-19 pandemic substantially magnified the inequity gaps among vulnerable populations. Both public health (PH) and primary health care (PHC) have been crucial in addressing the challenges posed by the pandemic, especially in the area of vulnerable populations. However, little is known about the intersection between PH and PHC as a strategy to mitigate the inequity gap. This study aims to assess the collaboration between PHC and PH with a focus on addressing the health needs of vulnerable populations during the COVID-19 pandemic across jurisdictions. METHODS: We analyzed and compared data from jurisdictional reports of COVID-19 pandemic responses in PHC and PH in Belgium, Canada (Ontario), Germany, Italy, Japan, the Netherlands, Norway, and Spain from 2020 to 2021. RESULTS: Four themes emerge from the analysis: (1) the majority of the countries implemented outreach strategies targeting vulnerable groups as a means to ensure continued access to PHC; (2) digital assessment in PHC was found to be present across all the countries; (3) PHC was insufficiently represented at the decision-making level; (4) there is a lack of clear communication channels between PH and PHC in all the countries. CONCLUSIONS: This study identified opportunities for collaboration between PHC and PH to reduce inequity gaps and to improve population health, focusing on vulnerable populations. The COVID-19 response in these eight countries has demonstrated the importance of an integrated PHC system. Consequently, the development of effective strategies for responding to and planning for pandemics should take into account the social determinants of health in order to mitigate the unequal impact of COVID-19. Careful, intentional coordination between PH and PHC should be established in normal times as a basis for effective response during future public health emergencies. The pandemic has provided significant insights on how to strengthen health systems and provide universal access to healthcare by fostering stronger connections between PH and PHC.

Promise and peril: how health system reforms impacted public health in three Canadian provinces.

OBJECTIVES: Several Canadian provinces and territories have reformed their health systems by centralizing power, resources, and responsibilities. Our study explored motivating factors and perceived impacts of centralization reforms on public health systems and essential operations. METHODS: A multiple case study design was used to examine three Canadian provinces that have undergone, or are in the process of undergoing, health system reform. Semi-structured interviews were conducted with 58 participants within public health at strategic and operational levels, from Alberta, Ontario, and Québec. Data were analyzed using a thematic analytical approach to iteratively conceptualize and refine themes. RESULTS: Three major themes were developed to describe the context and impacts of health system centralization reforms on public health: (1) promising "value for money" and consolidating authority; (2) impacting intersectoral and community-level collaboration; and (3) deprioritizing public health operations and contributing to workforce precarity. Centralization highlighted concerns about the prioritization of healthcare sectors. Some core public health functions were reported to operate more efficiently, with less duplication of services, and improvements in program consistency and quality, particularly in Alberta. Reforms were also reported to have diverted funding and human resources away from core essential functions, and diminished the public health workforce. CONCLUSION: Our study highlighted that stakeholder priorities and a limited understanding about public health systems influenced how reforms were implemented. Our findings support calls for modernized and inclusive governance, stable public health funding, and investment in the public health workforce, which may help inform future reforms.

RéSUMé: OBJECTIFS: Plusieurs provinces et territoires canadiens ont réformé leur système de santé en centralisant le pouvoir, les ressources et les responsabilités. Notre étude a exploré les facteurs sous-jacents et les impacts perçus des réformes de centralisation sur les systèmes et les opérations essentielles de santé publique. MéTHODES: Nous avons mené une étude de cas multiples pour examiner la situation de trois provinces canadiennes qui ont subi ou qui sont en train de réaliser une réforme du système de santé. Des entrevues semi-structurées ont été menées auprès de 58 participants de la santé publique aux niveaux stratégique et opérationnel, en Alberta, en Ontario et au Québec. De façon itérative, nous avons thématiquement analysé les données recueillies. RéSULTATS: Trois thèmes principaux ont été formulés pour décrire le contexte et les impacts des réformes de centralisation du système de santé sur la santé publique : 1) la promesse d'une « optimisation des ressources ¼ et la consolidation de l'autorité, 2) l'impact sur la collaboration intersectorielle et communautaire, et 3) la privatisation des opérations de santé publique et la précarisation de la main-d'œuvre. La centralisation a mis en lumière des préoccupations quant à la priorité accordée aux services de santé. Certaines fonctions essentielles de la santé publique fonctionneraient de manière plus efficace, avec moins de dédoublement des services et des améliorations de la cohérence et de la qualité des programmes, notamment en Alberta. Les réformes auraient aussi détourné des fonds et des ressources humaines des fonctions essentielles de base et auraient réduit les effectifs de la santé publique. CONCLUSION: Notre étude a mis en exergue les priorités des parties prenantes et une compréhension limitée des systèmes de santé publique qui ont influencé la manière dont les réformes ont été mises en œuvre. Nos résultats soutiennent les appels à une gouvernance plus modernisée et inclusive, à un financement stable de la santé publique et à un investissement dans le personnel de santé publique, pouvant ainsi contribuer à alimenter les futures réformes.