Search results
Found 20014 matches for
We lead multidisciplinary applied research and training to rethink the way health care is delivered in general practice and across the community.
Food beliefs and practices among British Bangladeshis with diabetes: implications for health education
In order successfully to promote ‘healthier’ food choices, health professionals must first understand how people classify and select the foods they eat. We explored the food beliefs and classification system of British Bangladeshis by means of qualitative interviews with 40 first-generation adult immigrants with diabetes. Methods included audiotaped, unstructured narrative interview in which participants were invited to ‘.tell the story’ of how diabetes affects them, pile sorting of food items, and participant observation of meals. We found considerable heterogeneity of individual food choices against a background of structural and economic factors (i.e. food choices were partly determined by affordability and availability), as well as cultural influences. Important themes included strong religious restrictions on particular food items (chiefly the Islamic prohibition of pork), and widely held ethnic customs based on the availability of foods in rural Bangladesh. Modification of the diet on immigration did not generally incorporate many Western’ foods but included increased quantities of ‘special menu’ Bangladeshi foods such as meat and traditional sweets. Foods were not classified or selected according to Western notions of food values (protein, carbohydrate, etc.). Rather, within religious and ethnic patterns, further food choices were determined by two interrelated and intersecting binary classification systems: ‘strong’/‘weak’ and ‘digestible’/‘indigestible’, which appear to replace the ‘hot’/‘cold’ classification prevalent elsewhere in South Ada. Different methods of cooking (especially baking and grilling) were perceived to alter the nature of the food. A desire for dietary balance, and a strong perceived link with health, was apparent. These findings have important implications for the design of health education messages. Dietary advice should reflect religious restrictions, ethnic customs and the different cultural meaning of particular foods, while also acknowledging the ability of the individual to exercise choice within those broad limits.
LOng COvid Multidisciplinary consortium Optimising Treatments and servIces acrOss the NHS (LOCOMOTION): Protocol for a mixed-methods study in the UK
Introduction Long COVID, a new condition whose origins and natural history are not yet fully established, currently affects 1.5 million people in the UK. Most do not have access to specialist long COVID services. We seek to optimise long COVID care both within and outside specialist clinics, including improving access, reducing inequalities, helping self-management and providing guidance and decision support for primary care. We aim to establish a 'gold standard' of care by systematically analysing current practices, iteratively improving pathways and systems of care. Methods and analysis This mixed-methods, multisite study is informed by the principles of applied health services research, quality improvement, co-design, outcome measurement and learning health systems. It was developed in close partnership with patients (whose stated priorities are prompt clinical assessment; evidence-based advice and treatment and help with returning to work and other roles) and with front-line clinicians. Workstreams and tasks to optimise assessment, treatment and monitoring are based in three contrasting settings: workstream 1 (qualitative research, up to 100 participants), specialist management in 10 long COVID clinics across the UK, via a quality improvement collaborative, experience-based co-design and targeted efforts to reduce inequalities of access, return to work and peer support; workstream 2 (quantitative research, up to 5000 participants), patient self-management at home, technology-supported monitoring and validation of condition-specific outcome measures and workstream 3 (quantitative research, up to 5000 participants), generalist management in primary care, harnessing electronic record data to study population phenotypes and develop evidence-based decision support, referral pathways and analysis of costs. Study governance includes an active patient advisory group. Ethics and dissemination LOng COvid Multidisciplinary consortium Optimising Treatments and servIces acrOss the NHS study is sponsored by the University of Leeds and approved by Yorkshire & The Humber - Bradford Leeds Research Ethics Committee (ref: 21/YH/0276). Participants will provide informed consent. Dissemination plans include academic and lay publications, and partnerships with national and regional policymakers.
Evaluating video and hybrid group consultations in general practice: mixed-methods, participatory study protocol (TOGETHER 2)
Background: General practice is facing an unprecedented challenge in managing the consequences of the pandemic. In the midst of a policy drive to balance remote and in-person service provision, substantial workload pressures remain, together with increasing prevalence of long-term conditions, and declining staff numbers and morale. To address these challenges, some practices in the UK have been delivering video and hybrid group consultations (VHGCs) providing clinical care to multiple patients at the same time. Despite positive initial findings and enthusiasm, there are still gaps in our understanding of the influence VHGCs have on patient experience, healthcare utilisation, quality, safety, equity and affordability. Objectives: To generate an in-depth understanding of VHGCs for chronic conditions in general practice, surface assumptions and sociotechnical dynamics, inform practice and extend theorisation. Methods: Mixed-methods, multi-site research study using co-design and participatory methods, from qualitative, quantitative and cost-related perspectives. WP1 includes a national, cross-sectional survey on VHGC provision across the UK. In WP2 we will engage patients and general practice staff in co-design workshops to develop VHGC models with emphasis on digital inclusion and equity. In WP3 we will carry out a mixed-methods process evaluation in up to 10 GP practices across England (5 sites already running VHGCs and 5 comparison sites). Qualitative methods will include interviews, focus groups and ethnographic observation to examine the experiences of patients, carers, clinical and non-clinical NHS staff, commissioners and policy-makers. Quantitative methods will examine the impact of VHGCs on healthcare utilisation in primary and secondary care, patient satisfaction, engagement and activation. We will also assess value for money of group and individual care models from a health economics perspective. Conclusions: We aim to develop transferable learning on sociotechnical change in healthcare delivery, using VHGCs as an exemplar of technology-supported innovation. Findings will also inform the design of a future study.
What is quality in long covid care? Lessons from a national quality improvement collaborative and multi-site ethnography
Background: Long covid (post covid-19 condition) is a complex condition with diverse manifestations, uncertain prognosis and wide variation in current approaches to management. There have been calls for formal quality standards to reduce a so-called “postcode lottery” of care. The original aim of this study—to examine the nature of quality in long covid care and reduce unwarranted variation in services—evolved to focus on examining the reasons why standardizing care was so challenging in this condition. Methods: In 2021–2023, we ran a quality improvement collaborative across 10 UK sites. The dataset reported here was mostly but not entirely qualitative. It included data on the origins and current context of each clinic, interviews with staff and patients, and ethnographic observations at 13 clinics (50 consultations) and 45 multidisciplinary team (MDT) meetings (244 patient cases). Data collection and analysis were informed by relevant lenses from clinical care (e.g. evidence-based guidelines), improvement science (e.g. quality improvement cycles) and philosophy of knowledge. Results: Participating clinics made progress towards standardizing assessment and management in some topics; some variation remained but this could usually be explained. Clinics had different histories and path dependencies, occupied a different place in their healthcare ecosystem and served a varied caseload including a high proportion of patients with comorbidities. A key mechanism for achieving high-quality long covid care was when local MDTs deliberated on unusual, complex or challenging cases for which evidence-based guidelines provided no easy answers. In such cases, collective learning occurred through idiographic (case-based) reasoning, in which practitioners build lessons from the particular to the general. This contrasts with the nomothetic reasoning implicit in evidence-based guidelines, in which reasoning is assumed to go from the general (e.g. findings of clinical trials) to the particular (management of individual patients). Conclusion: Not all variation in long covid services is unwarranted. Largely because long covid’s manifestations are so varied and comorbidities common, generic “evidence-based” standards require much individual adaptation. In this complex condition, quality improvement resources may be productively spent supporting MDTs to optimise their case-based learning through interdisciplinary discussion. Quality assessment of a long covid service should include review of a sample of individual cases to assess how guidelines have been interpreted and personalized to meet patients’ unique needs. Study registration: NCT05057260, ISRCTN15022307.
From ‘A Rapid and Necessary Revolution’ to ‘Telemedicine Killed the PE Teacher’: Changing Representations of Remote GP Consultations in UK Media During the COVID-19 Pandemic
The abrupt shift from face-to-face general practitioner (GP) consultations to remote ones was one of the most radical changes to the UK National Health Service (NHS) since it was set up in 1948. Overnight, people were blocked from turning up at their GP’s surgery and instead offered telephone, video or email contacts. This chapter considers how the lay press interpreted and conveyed this shift. We systematically collected UK newspaper stories about remote general practice from early 2020, mid 2020 and late 2021, and analysed these for their narrative content and form. The three time periods represented three distinct ‘eras’. Early in the pandemic, newspapers depicted remote consultations positively as an essential component of the country’s war against the virus (‘technology as superhero’). By summer 2020, the incidence of COVID-19 had fallen to a low level, lockdown had ended and many aspects of life were returning to normal. But the Secretary of State for Health (a technology enthusiast) had declared that virtual consultations should continue in order to make the NHS more efficient and modern. The mainstream media made much of this misalignment through funny and tragic stories of remote consultations which were clearly inappropriate or unsafe (‘technology as farce’). In 2021, the pandemic grumbled on and a backlog of unmet needs began to surface. The NHS was busier than ever; staff were exhausted; secondary care sought to redistribute work to primary care; and many key posts were unfilled because of early retirement, long-term staff illness and Brexit. In this context—a system under extreme stress—GPs used remote triage as a tool to control their workload. The media responded aggressively, running front-page campaigns to demand a better service from ‘lazy’ GPs who were depicted as being on the golf course while making occasional calls to sick patients on their smartphones. In this period, the focus of media stories was on the perceived lack of traditional face-to-face appointments and patients who had been ‘fobbed off’ with telephone calls (‘technology as cop-out’). Over the course of 2 years, media narratives on technology-mediated consultations thus shifted from hopeful (reproducing a discourse of modernity and efficiency) to nostalgic (demanding a return to a golden era when patients could be seen ‘properly’). We discuss the implications of these depictions for the future of remote (and face-to-face) consultations.
Erratum: Practical Indicators for Risk of Airborne Transmission in Shared Indoor Environments and Their Application to COVID-19 Outbreaks (Environmental Science and Technology (2022) 56:2 (1125-1137) DOI: 10.1021/acs.est.1c06531)
We shown have in identi Table fied 2c an of error the paper. on some This of is the only calculations significant for a few cells on the bottom right corner (dark red) and it reduces the risk of infection at those locations. However, it does not change the numerical or color trends on the table, and those locations continue to have the highest risk. The error does not affect anything else on the paper or any of the conclusions.
Physician associates and anaesthetic associates in UK: rapid systematic review of recent UK based research
Objective: To summarise research on the efficacy and safety of UK physician associates and anaesthetic associates in the context of an ongoing policy review. Design: Rapid systematic review. Search strategy: Keyword and author search of three databases; citation tracking; search of previous systematic reviews. Eligible studies: Empirical research (any design) on physician associates/anaesthetic associates in UK healthcare published between 2015 and January 2025. Main outcomes: Any measure of clinical efficacy or safety. Methods: Eligible papers were grouped into categories and appraised using Critical Appraisal Skills Programme checklists. Two reviewers independently extracted data on study designs, samples, methods, and findings. Each paper was scored for trustworthiness, generalisability, and relevance; differences were resolved by discussion. Studies meeting a minimum inclusion standard were described and critiqued. Results: Of approximately 5000 titles, 52 papers were eligible (48 on physician associates, four on anaesthetic associates), of which 29 met the inclusion standard. The total number of physician associates studied was very small, especially in primary care; no studies reported direct assessment of anaesthetic associates. Only one study, of four physician associates, involved any assessment by a doctor of their clinical competence by direct observation. No studies examined safety incidents. Some studies suggested that physician associates could support the work of ward based teams and work in emergency departments when appropriately deployed and supervised in low risk clinical settings, but the number of individuals and settings studied was small, and those findings should be considered preliminary. Physician associates seemed to struggle in primary care, however, because the role was more autonomous, the case mix was more diverse, decisions were more uncertain, institutional support was more limited, and supervision arrangements were more challenging. Staff expressed concern about physician associates' and anaesthetic associates' competence to manage undifferentiated, clinically complex, or high dependency patients; order ionising radiation; or prescribe. Physician associates reported a range of experiences and desired a clear role within the team. No evidence was found that physician associates add value in primary care or that anaesthetic associates add value in anaesthetics; some evidence suggested that they do not. Conclusions: The UK literature on physician associates and anaesthetic associates is sparse and of variable quality, and some is outdated. In this context, the absence of evidence of safety incidents should not be misinterpreted as evidence that deployment of physician associates and anaesthetic associates is safe. Findings of apparent non-inferiority in non-randomised studies may obscure important unmeasured differences in quality of care. New research is urgently needed to explore staff concerns, examine safety incidents, and inform a national scope of practice for these relatively new and contested staff roles. The findings from this UK based study should be interpreted in the context of the wider international evidence base.
In what context and by which mechanisms can creative arts interventions improve wellbeing in older people? A realist review protocol
Background: In recent years, there has been growing interest at national and international policy level in the potential of creative arts to support individual and community wellbeing. Creative arts encompass a wide range of activities, including performing arts, visual arts, design and craft, literature, culture and digital and electronic arts. Participation in creative arts has been linked to lower mental distress, increased social connection, improved quality of life, personal growth and empowerment. Despite this, it remains unclear exactly how participation in creative arts interventions can improve wellbeing in older individuals. This realist review aims to synthesize evidence on how elements of creative arts interventions improve wellbeing amongst older people, in particular when, how, for whom and to what extent they work. Methods and analysis This review will follow the RAMESES (Realist And Meta-narrative Evidence Syntheses: Evolving Standards) quality standards and Pawson’s five iterative stages to locate existing theories, search for evidence, select literature, extract data, and draw conclusions. It will be guided by stakeholder engagement with policymakers, practitioners, commissioners, and people with lived experience. A realist approach will be used to analyse data and develop causal explanations, in the form of context-mechanism-outcome-configurations (CMOCs), which explain how creative arts interventions impact wellbeing in older people. The CMOCs will be organised into one or more programme theories. Our refined programme theory will then be used to develop guidance for service providers of creative arts who want to use their services to improve wellbeing of older people. Ethics and dissemination This research will comply with the UK Policy Framework for Health and Social Care Research. Dissemination will be guided by our stakeholder group, building on links with policymakers, commissioners, providers, and the public. A final stakeholder event focused on knowledge mobilisation will aid development of recommendations. PROSPERO registration CRD42024580770.
Masks and respirators for prevention of respiratory infections: a state of the science review
This narrative review and meta-analysis summarizes a broad evidence base on the benefits—and also the practicalities, disbenefits, harms and personal, sociocultural and environmental impacts—of masks and masking. Our synthesis of evidence from over 100 published reviews and selected primary studies, including re-analyzing contested meta-analyses of key clinical trials, produced seven key findings. First, there is strong and consistent evidence for airborne transmission of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and other respiratory pathogens. Second, masks are, if correctly and consistently worn, effective in reducing transmission of respiratory diseases and show a dose-response effect. Third, respirators are significantly more effective than medical or cloth masks. Fourth, mask mandates are, overall, effective in reducing community transmission of respiratory pathogens. Fifth, masks are important sociocultural symbols; non-adherence to masking is sometimes linked to political and ideological beliefs and to widely circulated mis- or disinformation. Sixth, while there is much evidence that masks are not generally harmful to the general population, masking may be relatively contraindicated in individuals with certain medical conditions, who may require exemption. Furthermore, certain groups (notably D/deaf people) are disadvantaged when others are masked. Finally, there are risks to the environment from single-use masks and respirators. We propose an agenda for future research, including improved characterization of the situations in which masking should be recommended or mandated; attention to comfort and acceptability; generalized and disability-focused communication support in settings where masks are worn; and development and testing of novel materials and designs for improved filtration, breathability, and environmental impact.
Safety implications of remote assessments for suspected COVID-19: qualitative study in UK primary care
Background The introduction of remote triage and assessment early in the pandemic raised questions about patient safety. We sought to capture patients and clinicians’ experiences of the management of suspected acute COVID-19 and generate wider lessons to inform safer care. Setting and sample UK primary healthcare. A subset of relevant data was drawn from five linked in-pandemic qualitative studies. The data set, on a total of 87 participants recruited via social media, patient groups and snowballing, comprised free text excerpts from narrative interviews (10 survivors of acute COVID-19), online focus groups (20 patients and 30 clinicians), contributions to a Delphi panel (12 clinicians) and fieldnotes from an online workshop (15 patients, clinicians and stakeholders). Methods Data were uploaded onto NVivo. Coding was initially deductive and informed by WHO and Institute of Medicine frameworks of quality and safety. Further inductive analysis refined our theorisation using a wider range of theories—including those of risk, resilience, crisis management and social justice. Results In the early weeks of the pandemic, patient safety was compromised by the driving logic of’stay home’ and’protect the NHS’, in which both patients and clinicians were encouraged to act in a way that helped reduce pressure on an overloaded system facing a novel pathogen with insufficient staff, tools, processes and systems. Furthermore, patients and clinicians observed a shift to a more transactional approach characterised by overuse of algorithms and decision support tools, limited empathy and lack of holistic assessment. Conclusion Lessons from the pandemic suggest three key strategies are needed to prevent avoidable deaths and inequalities in the next crisis: (1) strengthen system resilience (including improved resourcing and staffing; support of new tools and processes; and recognising primary care’s role as the’risk sink’ of the healthcare system); (2) develop evidence-based triage and scoring systems; and (3) address social vulnerability.
Face masks while exercising trial (MERIT): a cross-over randomised controlled study
Objectives Physical exertion is a high-risk activity for aerosol emission of respiratory pathogens. We aimed to determine the safety and tolerability of healthy young adults wearing different types of face mask during moderate-to-high intensity exercise. Design Cross-over randomised controlled study, completed between June 2021 and January 2022. Participants Volunteers aged 18-35 years, who exercised regularly and had no significant pre-existing health conditions. Interventions Comparison of wearing a surgical, cloth and filtering face piece (FFP3) mask to no mask during 4×15 min bouts of exercise. Exercise was running outdoors or indoor rowing at moderate-to-high intensity, with consistency of distance travelled between bouts confirmed using a smartphone application (Strava). Each participant completed each bout in random order. Outcomes The primary outcome was change in oxygen saturations. Secondary outcomes were change in heart rate, perceived impact of face mask wearing during exercise and willingness to wear a face mask for future exercise. Results All 72 volunteers (mean age 23.9) completed the study. Changes in oxygen saturations did not exceed the prespecified non-inferiority margin (2% difference) with any mask type compared with no mask. At the end of exercise, the estimated average difference in oxygen saturations for cloth mask was -0.07% (95% CI -0.39% to 0.25%), for surgical 0.28% (-0.04% to 0.60%) and for FFP3 -0.21% (-0.53% to 0.11%). The corresponding estimated average difference in heart rate for cloth mask was -1.20 bpm (95% CI -4.56 to 2.15), for surgical 0.36 bpm (95% CI -3.01 to 3.73) and for FFP3 0.52 bpm (95% CI -2.85 to 3.89). Wearing a face mask caused additional symptoms such as breathlessness (n=13, 18%) and dizziness (n=7, 10%). 33 participants broadly supported face mask wearing during exercise, particularly indoors, but 22 were opposed. Conclusion This study adds to previous findings (mostly from non-randomised studies) that exercising at moderate-to-high intensity wearing a face mask appears to be safe in healthy, young adults. Trial registration number NCT04932226
Access and triage in contemporary general practice: A novel theory of digital candidacy
To access contemporary healthcare, patients must find and navigate a complex socio-technical network of human and digital actors linked in multi-modal pathways. Asynchronous, digitally-mediated triage decisions have largely replaced synchronous conversations between humans. In this paper, we draw on a large qualitative dataset from a multi-site study of remote and digital technologies in general practice to understand widening inequities of access. We theorise our data by bringing together traditional candidacy theory (in particular, concepts of self-assessment, help-seeking, adjudication and negotiation) and socio-technical and technology structuration theories (in particular, concepts of user configuration, articulation, distanciation, disembedding, and recursivity), thus producing a novel theory of digital candidacy. We propose that both human and technological actors (in different ways) embody social structures which affect how they ‘act’ in social situations. Digital technologies contain inbuilt assumptions about users' capabilities, needs, rights, and skills. Patients' ability to self-assess as sick, access digital platforms, self-advocate, and navigate multiple stages in the pathway, including adapting to and compensating for limitations in the technology, vary widely and are markedly patterned by disadvantage. Not every patient can craft an accurate digital facsimile on which the subsequent adjudication decision will be made; those who create incomplete, flawed or unpersuasive digital facsimiles may be deprioritised or misdirected. Staff who know about such patients may use articulation measures to ensure a personalised and appropriate access package, but they cannot identify or fully mitigate all such cases. The decisions and actions of human and technological agents at the time of an attempt to access care can significantly influence, disrupt, and reconstitute candidacy both immediately and recursively over time, and also recursively shape the system itself. These findings underscore the need for services to be (co-)designed with attention to the exclusionary tendencies of digital technologies and technology-supported processes and pathways.
Supporting your support staff during crises: recommendations for practice leaders to develop a relational workplace
Background The workload and wellbeing of support staff in general practice has been critically understudied. This includes reception, secretarial and administrative workers who are critical in the daily practice function. Currently, only reception staff are mentioned in the evidence base on general practice working conditions, and all support staff are excluded from studies about the impact of the pandemic on healthcare workers’ work and wellbeing. Aim To outline the unique work support staff do, the additional burden it places on them, and how the symphony of crises in 2020–2023 compounded those burdens. Additionally, to provide practical advice for practice leaders on how to support staff wellbeing through developing a relational and psychologically safe working environment. Methods These findings are drawn from qualitative research (case studies built through observations, interviews and focus groups) conducted in 2022–2023. Results Through theoretically informed analysis, we found that support staff do specialist intersectional guiding work to support patients, other staff, and the practice as a whole. We define this as lay translation, specialist-lay translation, and occupational translation. Under crises, the volume of this work grows, complexifies, and becomes more fragmented. Relational and supportive teams were more able to adapt to these challenges. Discussion Support staff should be recognised and enabled to perform these specialised roles. Therefore, we provide a set of recommendations for practice leaders to consider integrating into their own workplaces.
Mobilising context as complex and dynamic in evaluations of complex health interventions
Background: The relationship between healthcare interventions and context is widely conceived as involving complex and dynamic interactions over time. However, evaluations of complex health interventions frequently fail to mobilise such complexity, reporting context and interventions as reified and demarcated categories. This raises questions about practices shaping knowledge about context, with implications for who and what we make visible in our research. Viewed through the lens of case study research, we draw on data collected for the Triple C study (focused on Case study, Context and Complex interventions), to critique these practices, and call for system-wide changes in how notions of context are operationalised in evaluations of complex health interventions. Methods: The Triple C study was funded by the Medical Research Council to develop case study guidance and reporting principles taking account of context and complexity. As part of this study, a one-day workshop with 58 participants and nine interviews were conducted with those involved in researching, evaluating, publishing, funding and developing policy and practice from case study research. Discussions focused on how to conceptualise and operationalise context within case study evaluations of complex health interventions. Analysis focused on different constructions and connections of context in relation to complex interventions and the wider social forces structuring participant’s accounts. Results: We found knowledge-making practices about context shaped by epistemic and political forces, manifesting as: tensions between articulating complexity and clarity of description; ontological (in)coherence between conceptualisations of context and methods used; and reified versions of context being privileged when communicating with funders, journals, policymakers and publics. Conclusion: We argue that evaluations of complex health interventions urgently requires wide-scale critical reflection on how context is mobilised - by funders, health services researchers, journal editors and policymakers. Connecting with how scholars approach complexity and context across disciplines provides opportunities for creatively expanding the field in which health evaluations are conducted, enabling a critical standpoint to long-established traditions and opening up possibilities for innovating the design of evaluations of complex health interventions.
Developing user personas to capture intersecting dimensions of disadvantage in older patients who are marginalised: a qualitative study
Background Remote and digital services must be equitable, but some patients have difficulty using these services. Designing measures to overcome digital disparities can be challenging for practices. Personas (fictional cases) are a potentially useful tool in this regard. Aim To develop and test a set of personas to reflect the lived experiences and challenges that older people who are disadvantaged face when navigating remote and digital primary care services. Design and setting Qualitative study of digital disparities in NHS community health services offering video appointments. Method Following familiarisation visits and interviews with service providers, 17 older people with multiple markers of disadvantage (limited English, health conditions, and poverty) were recruited and interviewed using narrative prompts. Data were analysed using an intersectionality lens, underpinned by sociological theory. Combining data across all participant interviews, we produced personas and refined these following focus groups involving health professionals, patients, and advocates (n = 12). Results Digital services create significant challenges for older patients with limited economic, social, and linguistic resources and low digital, health, or system literacy. Four contrasting personas were produced, capturing the variety and complexity of how dimensions of disadvantage intersected and influenced identity and actions. The personas illustrate important themes including experience of racism and discrimination, disorientation, discontinuity, limited presence, weak relationships, loss of agency, and mistrust of services and providers. Conclusion Personas can illuminate the multiple and intersecting dimensions of disadvantage in patient populations who are marginalised and may prove useful when designing or redesigning digital primary care services. Adopting an intersectional lens may help practices address digital disparities.
How to read a paper involving artificial intelligence (AI)
This paper guides readers through the critical appraisal of a paper that includes the use of artificial intelligence (AI) in clinical settings for healthcare delivery. A brief introduction to the different types of AI used in healthcare is given, along with some ethical principles to guide the introduction of AI systems into healthcare. Existing publication guidelines for AI studies are highlighted. Ten preliminary questions to ask about a paper describing an AI based decision support algorithm are suggested.