Tweaking algorithms. Technopolitical issues associated with artificial intelligence based tuberculosis detection in global health.

Computer-aided detection algorithms based on artificial intelligence are increasingly being tested and used as a means for detecting tuberculosis in countries where the epidemic is still present. Computer-aided detection tools are often presented as a global solution that can be deployed in all the geographical areas concerned by tuberculosis, but at the same time, they need to be adjusted and calibrated according to local populations' characteristics. The aim of this article is to analyze the tensions between the standardization of computer-aided detection algorithms and their local adaptation and the political issues associated with these tensions. We undertook a qualitative analysis of practices associated with tuberculosis detection algorithms in different contexts, contrasting the perspectives of various stakeholders. Algorithms embed the promise of standardization through automation and the bypassing of variable human expertise such as that of radiologists, they are nonetheless objects of local practices that we have characterized as "tweaking." This work of tweaking reveals how the technology is situated but also the many concerns of the users and workers (insertion in care, control over infrastructure, and political ownership). This should be better considered to truly make computer-aided detection innovative tools for tuberculosis management in global health.

Understanding drug exceptional access programs (DEAPs) in Canada, and their associated social and political issues.

Drug exceptional access programs (DEAPs) exist across Canada to address gaps in access to pharmaceuticals. These programs circumvent standard procedures, raising epistemic, economic, social and political issues. This commentary provides insights into these issues by revealing the context and procedures on which these programs depend.

AI for Detection of Tuberculosis: Implications for Global Health.

Tuberculosis, which primarily affects developing countries, remains a significant global health concern. Since the 2010s, the role of chest radiography has expanded in tuberculosis triage and screening beyond its traditional complementary role in the diagnosis of tuberculosis. Computer-aided diagnosis (CAD) systems for tuberculosis detection on chest radiographs have recently made substantial progress in diagnostic performance, thanks to deep learning technologies. The current performance of CAD systems for tuberculosis has approximated that of human experts, presenting a potential solution to the shortage of human readers to interpret chest radiographs in low- or middle-income, high-tuberculosis-burden countries. This article provides a critical appraisal of developmental process reporting in extant CAD software for tuberculosis, based on the Checklist for Artificial Intelligence in Medical Imaging. It also explores several considerations to scale up CAD solutions, encompassing manufacturer-independent CAD validation, economic and political aspects, and ethical concerns, as well as the potential for broadening radiography-based diagnosis to other nontuberculosis diseases. Collectively, CAD for tuberculosis will emerge as a representative deep learning application, catalyzing advances in global health and health equity. Keywords: Computer-aided Diagnosis (CAD), Conventional Radiography, Thorax, Lung, Machine Learning Supplemental material is available for this article. © RSNA, 2024.

Vaccine promotion strategies in community pharmacy addressing vulnerable populations: a scoping review.

CONTEXT: Social determinants of health are drivers of vaccine inequity and lead to higher risks of complications from infectious diseases in under vaccinated communities. In many countries, pharmacists have gained the rights to prescribe and administer vaccines, which contributes to improving vaccination rates. However, little is known on how they define and target vulnerable communities. OBJECTIVE: The purpose of this study is to describe how vulnerable communities are targeted in community pharmacies. METHODS: We performed a systematic search of the Embase and MEDLINE database in August 2021 inspired by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses protocols (PRISMA ScR). Articles in English, French or Spanish addressing any vaccine in a community pharmacy context and that target a population defined as vulnerable were screened for inclusion. RESULTS: A total of 1039 articles were identified through the initial search, and 63 articles met the inclusion criteria. Most of the literature originated from North America (n = 54, 86%) and addressed influenza (n = 29, 46%), pneumococcal (n = 14, 22%), herpes zoster (n = 14, 22%) or human papilloma virus vaccination (n = 14, 22%). Lifecycle vulnerabilities (n = 48, 76%) such as age and pregnancy were most often used to target vulnerable patients followed by clinical factors (n = 18, 29%), socio-economical determinants (n = 16, 25%) and geographical vulnerabilities (n = 7, 11%). The most frequently listed strategy was providing a strong recommendation for vaccination, promotional posters in pharmacy, distributing leaflet/bag stuffers and providing staff training. A total of 24 barriers and 25 facilitators were identified. The main barriers associated to each vulnerable category were associated to effective promotional strategies to overcome them. CONCLUSION: Pharmacists prioritize lifecycle and clinical vulnerability at the expense of narrowing down the definition of vulnerability. Some vulnerable groups are also under targeted in pharmacies. A wide variety of promotional strategies are available to pharmacies to overcome the specific barriers experienced by various groups.

Supporting Reassigned Hospital Staff During the COVID-19 Pandemic in the Montreal Region: What Does it say About Leadership Styles?

Globally, the COVID-19 pandemic took a high toll on health human resources, especially in contexts where these resources were already fragile. In Quebec, to make up for the shortage of health human resources, and to contain the COVID-19 outbreaks in long-term care facilities, many hospital staff (including a majority of nurses) were sent to those facilities, with varying degrees of support. Building on the body of evidence linking leadership style and resilience, we conducted a qualitative comparative analysis of two hospitals in the Montreal Metropolitan Area, Quebec. We explored respondents' experience of psychosocial support tools provided to hospital staff reassigned to COVID-affected facilities. Data from 27 in-depth interviews with high- and mid-level managers, and front-line workers, was analyzed through the lens of leadership styles. Our findings highlighted how the design and implementation of support tools revealed major differences across the two hospitals' leadership styles (i.e., one hospital expressing leader-centered styles vs. the other expressing follower-centered leadership styles). The expression of these leadership styles was largely shaped by recent policies, notably a major political reform of 2015, which enforced more centralized decision-making. Our study offered additional empirical evidence that leadership styles fostering the recovery of health human resources may be a key indicator of successful response to crises.

Communication and Information Strategies Implemented by Four Hospitals in Brazil, Canada, and France to Deal with COVID-19 Healthcare-Associated Infections.

During the COVID-19 pandemic outbreak, COVID-19 healthcare-associated infections (HAI) and risk management became major challenges facing hospitals. Using evidence from a research project, this commentary presents: 1) various communication and information strategies implemented by four hospitals and their staff in Brazil, Canada and France to reduce the risks of COVID-19 HAIs, and how they were perceived by hospital staff; 2) the flaws in communication in the hospitals; and 3) a proposed agenda for research on and action to improve institutional communications for future pandemics. By analyzing "top-down" strategies at the organizational level and spontaneous strategies initiated by and between professionals, this study shows that during the first waves of the pandemic, reliable information and clear communication about guidelines and health protocols' changes can help alleviate fears among staff and avoid misapplication of protocols, thereby reducing infection risks. There was a lack of a "bottom-up" communication channel, while, when making decisions, it is crucial to listen to and fully take into account staff's voices, experiences, and feelings. More balanced communication between hospital administrators and staff could strengthen team cohesion and lead to better enforcement of protocols, which in turn will reduce the risk of contamination, alleviate the potential impacts on staff health, and improve the quality of care provided to patients.

Lessons Learned from Field Experiences on Hospitals' Resilience to the COVID-19 Pandemic: A Systematic Approach.

In this concluding article of the special issue, we examine lessons learned from hospitals' resilience to the COVID-19 pandemic in Brazil, Canada, France, Japan, and Mali. A quality lesson learned (QLL) results from a systematic process of collecting, compiling, and analyzing data derived ideally from sustained effort over the life of a research project and reflecting both positive and negative experiences. To produce QLLs as part of this research project, a guide to their development was drafted. The systematic approach we adopted to formulate quality lessons, while certainly complex, took into account the challenges faced by the different stakeholders involved in the fight against the COVID-19 pandemic. Here we present a comparative analysis of the lessons learned by hospitals and their staff with regard to four common themes that were the subject of empirical analyses: 1) infrastructure reorganization; 2) human resources management; 3) prevention and control of infection risk; and 4) logistics and supply. The lessons learned from the resilience of the hospitals included in this research indicate several factors to consider in preparing for a health crisis: 1) strengthening the coordination and leadership capacities of hospital managers and health authorities; 2) improving communication strategies; 3) strengthening organizational capacity; and 4) adapting resources and strategies, including for procurement and infection risk management.

Artificial intelligence-based computer aided detection (AI-CAD) in the fight against tuberculosis: Effects of moving health technologies in global health.

Computer Aided Detection software based on Artificial Intelligence (AI-CAD), combined with chest X-rays have recently been promoted as an easy fix for a complex problem: ending TB by 2030. WHO has recommended the use of such imaging devices in 2021 and many partnerships have helped propose benchmark analysis and technology comparisons to facilitate their "market access". Our aim is to examine the socio-political and health issues that stem from using AI-CAD technology in a global health context conceptualized as a set of practice and ideas organizing global intervention "in the life of others". We also question how this technology, which is not yet fully implemented in routine use, may limit or amplify some inequalities in the care of tuberculosis. We describe AI-CAD through Actor-Network-Theory framework to understand the global assemblage and composite activities associated with detection through AI-CAD, and interrogate how the technology itself may consolidate a specific configuration of "global health". We explore the various dimensions of AI-CAD "health effects model": technology design, development, regulation, institutional competition, social interaction and health cultures. On a broader level, AI-CAD represents a new version of global health's accelerationist model centered on "moving and autonomous-presumed technologies". We finally present key aspects in our research which help discuss the theories mobilized: AI-CAD ambivalent insertion in global health, the social lives of its data: from efficacy to markets and AI-CAD human care and maintenance it requires. We reflect on the conditions that will affect AI-CAD use and its promises. In the end, the risk of new detection technologies such as AI-CAD is indeed that the fight against TB could be reduced to one that is purely technical and technological, with neglect to its social determinants and effects.

How resilience affected public health research during COVID-19 and why we should abandon it.

Resilience has accompanied the COVID-19 pandemic as a rallying motto, with calls by governments for a resilient society, resilient families and schools, and, of course, resilient healthcare systems in the face of this unprecedented pandemic shock. Resilience had already gained traction as an analytical concept in public health research for approximately a decade. It became a key concept despite the recognition of its lack of conceptual consistency. The COVID-19 pandemic presented itself as a perfect test-case and encouraged a multiplicity of studies on resilience and health care systems. In this commentary, we add to the existing critiques of resilience in the social sciences by reflecting on the effects of resilience when used to frame empirical inquiries and to draw lessons from the crisis. Resilience as a concept is unable to address crucial structural issues that health systems already faced throughout the world, and it remains a non-neutral political notion. We argue that we need to resist a generalised view of resilience and work with alternative imaginaries.

Hospital Governance During the COVID-19 Pandemic: A Multiple-Country Case Study.

In response to the disruptions caused by COVID-19, hospitals around the world proactively or reactively developed and/or re-organized their governance structures to manage the COVID-19 response. Hospitals' governance played a crucial role in their ability to reorganize and respond to the pressing needs of their staff. We discuss and compare six hospital cases from four countries on different continents: Brazil, Canada, France, and Japan. Our study examined how governance strategies (e.g., special task forces, communications management tools, etc.) were perceived by hospital staff. Key findings from a total of 177 qualitative interviews with diverse hospital stakeholders were analyzed using three categories drawn from the European Observatory on Health Systems and Policies framework on health systems resilience during the COVID-19 pandemic: 1) delivering a clear and timely COVID-19 response strategy; 2) coordinating effectively within (horizontally) and across (vertically) levels of decision-making; and 3) communicating clearly and transparently with the hospital's diverse stakeholders. Our study gleaned rich accounts for these three categories, highlighting significant variations across settings. These variations were primarily determined by the hospitals' environment prior to the COVID-19 crisis, namely whether there already existed a culture of managerial openness (including spaces for social interactions among hospital staff) and whether preparedness planning and training had been routinely integrated into their activities.

Adapting Hospital Work During COVID-19 in Quebec (Canada).

Among hospital responses to the COVID19 pandemic worldwide, service reorganization and staff reassignment have been some of the most prominent ways of adapting hospital work to the expected influx of patients. In this article, we examine work reorganization induced by the pandemic by identifying the operational strategies implemented by two hospitals and their staff to contend with the crisis and then analyzing the implications of those strategies. We base our description and analysis on two hospital case studies in Quebec. We used a multiple case study approach, wherein each hospital is considered a unique case. In both cases, work adaptation through staff reassignment was one of the critical measures undertaken to ensure absorption of the influx of patients into the hospitals. Our results showed that this general strategy was designed and applied differently in the two cases. More specifically, the reassignment strategies revealed numerous healthcare resource disparities not only between health territories, but also between different types of facilities within those territories. Comparing the two hospitals' adaptation strategies showed that past reforms in Quebec determined what these reorganizations could achieve, as well as how they would affect workers and the meaning they gave to their work.

How Did an Integrated Health and Social Services Center in the Quebec Province Respond to the COVID-19 Pandemic? A Qualitative Case Study.

During the first and second waves of the pandemic, Quebec was among the Canadian provinces with the highest COVID-19 mortality rates. Facing particularly large COVID-19 outbreaks in its facilities, an integrated health and social services center in the province of Quebec (Canada), developed resilience strategies. To explore these diverse responses to the crisis, we conducted a case study analysis of a Quebec integrated health and social services center, building on a conceptualization of resilience strategies using "configurations" of effects, strategies, and impacts. Qualitative data from 14 indepth interviews conducted in the summer and fall of 2020 with managers and frontline practitioners were analyzed through the lens of situations of "anticipation," "reaction," or "inaction." The findings were discussed in three results dissemination workshops, two with practitioners and one with managers, to discern lessons they learned. Three major configurations emerged: 1) reorganization of services and spaces to accommodate more COVID-19 patients; 2) management of contamination risks for patients and professionals; and 3) management of personal protective equipment (PPE), supplies, and medications. Within these configurations, the responses to the crisis were strongly shaped by the 2015 health care system reforms in Quebec and were constrained by organizational challenges that included a centralized model of governance, a history of substantial budget cuts to longterm care facilities, and a systematic lack of human resources.

Digital Therapies (DTx) as New Tools within Physicians' Therapeutic Arsenal: Key Observations to Support their Effective and Responsible Development and Use.

In recent years, there has been a swift rise in the development of digital therapies (DTx). As a result of various technological advances and accessibility to patients, it is now possible to develop and offer therapeutic interventions in a digital manner. These take the form of an evidence-based intervention that is administered in digital form to prevent, manage, or treat a medical condition. What makes DTx significantly different from other types of digital applications or services (e.g., wellness applications) is that they are interventions authorised by regulatory agencies for the treatment, like a drug, of a health condition. Yielding actual therapeutic benefits and being at the crossroads of health and digital means that DTx are subject to both the upsides and downsides of both sectors. Thus, it is of particular interest to look at the facilitators and barriers to be foreseen in the development, assessment, and implementation of DTx. In this article, we will present key observations and outline the main challenges that may be faced in the development and integration of DTx into practice. It is certain that DTx can represent an interesting avenue for physicians to bring their prescribing role into the 21st century. We conclude with broad lessons that the emerging field of DTx can learn from decades of drug industry practice to avoid history repeating itself and to fast-track the development and ethical and optimal use of DTx.

Community Pharmacists and Influenza Vaccination: Opportunities and Challenges From a Public Health Perspective.

Context: In Quebec, Bill 31, adopted on March 18, 2020, extended vaccination to pharmacists. Despite many advantages, this new practice comes with public health issues reinforced in the context of COVID-19. Therefore, it is essential to understand the opportunities and challenges of the participation of community pharmacists in influenza vaccination, from a public health perspective by (i) describing the year of 2020-2021 influenza vaccination offer, (ii) its opportunities and challenges, and (iii) its impact on the accessibility of this service newly offered by pharmacists to the most vulnerable people. Methods: This research is a case study from one of the most affected areas by COVID-19 in Canada: Laval. Our method combines documentary analysis and semi-structured interviews with health professionals and public health actors (n = 23). Researchers used a thematic analysis to analyze these results. Results: Most partners (pharmacists, public health administrators) underlined multiple opportunities of this new practice, ie, pharmacists who can vaccinate, particularly for chronically ill patients. However, structural and strategical challenges remain. More specifically, vaccination seemed to only rely on a "first come, first served" basis, which questions public health objectives of vaccination, such as equitable access. Conclusion: The introduction of new actors, such as pharmacists, represents a major opportunity to improve vaccination coverage and reduce the burden of COVID-19 on the health system. However, this delegation of a public health activity to the private sector undoubtedly requires closer coordination with public health institutions.

Structuring and organizing interprofessional healthcare in partnership with patients with diabetes: the INterprofessional Management and Education in Diabetes care (INMED) pathway.

Type 2 diabetes is a complex chronic disease that requires ongoing monitoring by an interprofessional team to prevent complications. The INMED (INterprofessional Management and Education in Diabetes) care pathway was developed by our team to optimize primary care services for these patients and their families. The objective of this study is to describe the preliminary results of its adoption and implementation. The INMED care pathway is organized into four axes: (a) continuing professional education, (b) self-management support, (c) case management, and (d) ongoing evaluation of the quality of diabetes care and services. A multiple-case study is underway to document its effects on practice change using the Reach, Effectiveness, Adoption, Implementation, and Maintenance (RE-AIM) framework. Preliminary results on the adoption and implementation revealed some strengths: (a) regular patient follow-up by the case manager, (b) scheduling of physician appointments when required, and (c) regular screening for risk factors. Barriers were also identified: (a) lack of clear understanding of the case manager role, (b) lack of referrals to team members, and (c) lack of use of the motivational interview approach. The INMED care pathway is being adopted by primary care teams but challenges need to be overcome to improve its reach and effectiveness.

Impact of individualized feedback letters on adherence to surgical antibiotic prophylaxis guidelines: an interrupted time series study (FEEDBACK-ASAP).

BACKGROUND: Surgical antibiotic prophylaxis (SAP) has been proved to decrease the rate of surgical site infections (SSI), but compliance to SAP guidelines remains suboptimal. AIM: This study evaluated the impact of periodically sending individualized feedback letters to surgeons and anesthesiologists on their compliance rate to SAP guidelines. METHODS: A total of 1491 surgeries were evaluated by retrospective chart review during the pre-intervention period and 668 surgeries were evaluated by prospective chart review during the per-intervention period. Finally, 295 letters were sent to 64 surgeons and 45 anesthesiologists. Compliance rate was assessed as an outcome composed of: indication for SAP, choice of antibiotic agent, antibiotic dose, postoperative duration, timing of the preoperative dose and intraoperative redosing. An interrupted time series design was used to assess a difference on compliance rates before and during the intervention period. FINDINGS: Sending individualized feedback letters to surgeons and anesthesiologists did not significantly improve the overall compliance to local SAP guidelines. CONCLUSION: Individualized feedback letters could be part of future interventions directed at improving compliance to SAP guidelines, but are likely insufficient by themselves to provide significant results.

Implementation of targeted deprescribing of potentially inappropriate medications in patients on hemodialysis.

PURPOSE: Patients on hemodialysis have a high risk of medication-related problems. Studies using deprescribing algorithms to reduce the number of inappropriate medications in this population have been published, but none have used a patient-partnership approach. Our study evaluated the impact of a similar intervention with a patient-partnership approach. METHODS: The objective was to describe the implementation of a pharmacist-led intervention with a patient-partnership approach using deprescribing algorithms and its impact on the reduction of inappropriate medications in patients on hemodialysis. Eight algorithms were developed by pharmacists and nephrologists to assess the appropriateness of medications. Pharmacists identified patients taking targeted medications. Following patient enrollment, pharmacists assessed medications with patients and applied the algorithms. With patient consent, deprescription was suggested to nephrologists if applicable. Specific data on each targeted medication were collected at 4 and 16 weeks. Descriptive statistics were used to examine the effects of the deprescribing intervention. RESULTS: Of 270 patients, 256 were taking at least one targeted medication. Of the 122 patients taking at least one targeted medication who were approached to participate, 66 were included in the study. At enrollment, these patients were taking 252 targeted medications, of which 59 (23.4%) were determined to be inappropriate. Deprescription was initiated for 35 of these 59 medications (59.3%). At 4 weeks, 33 of the 59 medications (55.9%) were still deprescribed, while, at 16 weeks, 27 of the 59 medications (45.8%) were still deprescribed. Proton pump inhibitors and benzodiazepines or Z-drugs were the most common inappropriate medications, and allopurinol was the most deprescribed medication. CONCLUSION: A pharmacist-led intervention with a patient-partnership approach and using deprescribing algorithms reduced the number of inappropriate medications in patients on hemodialysis.

Chest X-ray Analysis With Deep Learning-Based Software as a Triage Test for Pulmonary Tuberculosis: An Individual Patient Data Meta-Analysis of Diagnostic Accuracy.

BACKGROUND: Automated radiologic analysis using computer-aided detection software (CAD) could facilitate chest X-ray (CXR) use in tuberculosis diagnosis. There is little to no evidence on the accuracy of commercially available deep learning-based CAD in different populations, including patients with smear-negative tuberculosis and people living with human immunodeficiency virus (HIV, PLWH). METHODS: We collected CXRs and individual patient data (IPD) from studies evaluating CAD in patients self-referring for tuberculosis symptoms with culture or nucleic acid amplification testing as the reference. We reanalyzed CXRs with three CAD programs (CAD4TB version (v) 6, Lunit v3.1.0.0, and qXR v2). We estimated sensitivity and specificity within each study and pooled using IPD meta-analysis. We used multivariable meta-regression to identify characteristics modifying accuracy. RESULTS: We included CXRs and IPD of 3727/3967 participants from 4/7 eligible studies. 17% (621/3727) were PLWH. 17% (645/3727) had microbiologically confirmed tuberculosis. Despite using the same threshold score for classifying CXR in every study, sensitivity and specificity varied from study to study. The software had similar unadjusted accuracy (at 90% pooled sensitivity, pooled specificities were: CAD4TBv6, 56.9% [95% confidence interval {CI}: 51.7-61.9]; Lunit, 54.1% [95% CI: 44.6-63.3]; qXRv2, 60.5% [95% CI: 51.7-68.6]). Adjusted absolute differences in pooled sensitivity between PLWH and HIV-uninfected participants were: CAD4TBv6, -13.4% [-21.1, -6.9]; Lunit, +2.2% [-3.6, +6.3]; qXRv2: -13.4% [-21.5, -6.6]; between smear-negative and smear-positive tuberculosis was: were CAD4TBv6, -12.3% [-19.5, -6.1]; Lunit, -17.2% [-24.6, -10.5]; qXRv2, -16.6% [-24.4, -9.9]. Accuracy was similar to human readers. CONCLUSIONS: For CAD CXR analysis to be implemented as a high-sensitivity tuberculosis rule-out test, users will need threshold scores identified from their own patient populations and stratified by HIV and smear status.

Assessment of community pharmacists' engagement in pharmacy-delivered influenza vaccination: a mixed-methods study.

OBJECTIVES: This study aimed to identify factors contributing to pharmacists' engagement in vaccination services during the first influenza vaccination campaign in 2019-2020 for the Canadian province of Quebec, led by community pharmacists. METHODS: A mixed-methods study was conducted using a sequential exploratory design. Semi-structured interviews were administered to pharmacists and key informants (n = 23) and data were analysed according to the Consolidated Framework for Implementation Research in community pharmacy. The findings were then used to construct a survey of community pharmacists' engagement in vaccination, which was tested in a Quebec urban community. The study participation rate was 34.6% (n = 29). KEY FINDINGS: Pharmacists expressed positive attitudes towards the implementation of vaccination services, following legislative reform. Factors such as previous involvement in vaccination campaigns and the number of pharmacists on duty were positively associated with engagement in influenza vaccination, whereas staff shortages and logistical problems were a barrier to engagement. Qualitative findings provided in-depth understanding of the value of interprofessional collaboration between pharmacists and nurses. CONCLUSIONS: Vaccination in pharmacies is currently more reflective of individual choice than an indication of collective change in the profession. Logistical factors are key to enhancing the uptake of vaccination in community pharmacies throughout Quebec. External support from professional associations and interprofessional collaboration should be enhanced to promote the implementation of vaccination services in pharmacies.