Stakeholder perspectives towards diagnostic artificial intelligence: a co-produced qualitative evidence synthesis.

Background: Diagnosis is a cornerstone of medical practice. Worldwide, there is increased demand for diagnostic services, exacerbating workforce shortages. Artificial intelligence (AI) technologies may improve diagnostic efficiency, accuracy, and access. Understanding stakeholder perspectives is key to informing implementation of complex interventions. We systematically reviewed the literature on stakeholder perspectives on diagnostic AI, including all English-language peer-reviewed primary qualitative or mixed-methods research. Methods: We searched PubMed, Ovid MEDLINE/Embase, Scopus, CINAHL and Web of Science (22/2/2023 and updated 8/2/2024). The Critical Appraisal Skills Programme Checklist informed critical appraisal. We used a 'best-fit' framework approach for analysis, using the Non-adoption, Abandonment, Scale-up, Spread, Sustainability (NASSS) framework. This study was pre-registered (PROSPERO CRD42022313782). Findings: We screened 16,577 articles and included 44. 689 participants were interviewed, and 402 participated in focus groups. Four stakeholder groups were described: patients, clinicians, researchers and healthcare leaders. We found an under-representation of patients, researchers and leaders across articles. We summarise the differences and relationships between each group in a conceptual model, hinging on the establishment of trust, engagement and collaboration. We present a modification of the NASSS framework, tailored to diagnostic AI. Interpretation: We provide guidance for future research and implementation of diagnostic AI, highlighting the importance of representing all stakeholder groups. We suggest that implementation strategies consider how any proposed software fits within the extended NASSS-AI framework, and how stakeholder priorities and concerns have been addressed. Funding: RK is supported by an NIHR Doctoral Research Fellowship grant (NIHR302562), which funded patient and public involvement activities, and access to Covidence.

A Web-Based Tool to Assess Social Inclusion and Support Care Planning in Mental Health Supported Accommodation: Development and Preliminary Test Study.

BACKGROUND: Individuals with severe mental illness living in supported accommodation are often socially excluded. Social inclusion is an important aspect of recovery-based practice and quality of life. The Social Inclusion Questionnaire User Experience (SInQUE) is a measure of social inclusion that has been validated for use with people with mental health problems. Previous research has suggested that the SInQUE could also help support care planning focused on enabling social inclusion in routine mental health practice. OBJECTIVE: This study aims to develop a web-based version of the SInQUE for use in mental health supported accommodation services, examine its acceptability and perceived usefulness as a tool to support care planning with service users, determine the extent of uptake of the tool in supported accommodation settings, and develop a program theory and logic model for the online SInQUE. METHODS: This study involved a laboratory-testing stage to assess the acceptability of the SInQUE tool through "think-aloud" testing with 6 supported accommodation staff members and a field-testing stage to assess the acceptability, utility, and use of the SInQUE tool over a 5-month period. An implementation strategy was used in 1 London borough to encourage the use of the SInQUE. Qualitative interviews with 12 service users and 12 staff members who used the tool were conducted and analyzed using thematic analysis. The use of the SInQUE was compared with that in 2 other local authority areas, 1 urban and 1 rural, where the tool was made available for use but no implementation strategy was used. RESULTS: Overall, 17 staff members used the SInQUE with 28 different service users during the implementation period (approximately 10% of all service users living in supported accommodation in the study area). The staff and service users interviewed felt that the SInQUE was collaborative, comprehensive, user-friendly, and relevant. Although some staff were concerned that particular questions might be too personal, service users did not echo this view. Participants generally felt that the SInQUE could help identify individuals' priorities regarding different aspects of social inclusion by prompting in-depth conversations and tailoring specific support to address service users' inclusion goals. Some interviewees also suggested that the tool could highlight areas of unmet or unmeetable needs across the borough that could feed into service planning. The SInQUE was not used in the comparison areas that had no implementation strategy. CONCLUSIONS: The online SInQUE is an acceptable and potentially useful tool that can be recommended to assess and support care planning to enable social inclusion of people living in mental health supported accommodation services. Despite this, uptake rates were modest during the study period. A concerted implementation strategy is key to embedding its use in usual care, including proactive endorsement by senior leaders and service managers.

Starting a conversation about estimands with public partners involved in clinical trials: a co-developed tool.

BACKGROUND: Clinical trials aim to draw conclusions about the effects of treatments, but a trial can address many different potential questions. For example, does the treatment work well for patients who take it as prescribed? Or does it work regardless of whether patients take it exactly as prescribed? Since different questions can lead to different conclusions on treatment benefit, it is important to clearly understand what treatment effect a trial aims to investigate-this is called the 'estimand'. Using estimands helps to ensure trials are designed and analysed to answer the questions of interest to different stakeholders, including patients and public. However, there is uncertainty about whether patients and public would like to be involved in defining estimands and how to do so. Public partners are patients and/or members of the public who are part of, or advise, the research team. We aimed to (i) co-develop a tool with public partners that helps explain what an estimand is and (ii) explore public partner's perspectives on the importance of discussing estimands during trial design. METHODS: An online consultation meeting was held with 5 public partners of mixed age, gender and ethnicities, from various regions of the UK. Public partner opinions were collected and a practical tool describing estimands, drafted before the meeting by the research team, was developed. Afterwards, the tool was refined, and additional feedback sought via email. RESULTS: Public partners want to be involved in estimand discussions. They found an introductory tool, to be presented and described to them by a researcher, helpful for starting a discussion about estimands in a trial design context. They recommended storytelling, analogies and visual aids within the tool. Four topics related to public partners' involvement in defining estimands were identified: (i) the importance of addressing questions that are relevant to patients and public in trials, (ii) involving public partners early on, (iii) a need for education and communication for all stakeholders and (iv) public partners and researchers working together. CONCLUSIONS: We co-developed a tool for researchers and public partners to use to facilitate the involvement of public partners in estimand discussions.

Understanding the social inclusion needs of people living in mental health supported accommodation.

OBJECTIVES: To identify the social inclusion needs that were (i) most commonly identified and (ii) most and least commonly prioritised as support planning goals for mental health service users living in supported accommodation, using the online Social Inclusion Questionnaire User Experience (SInQUE). We qualitatively examined mental health supported accommodation staff and servicer users' views on barriers to offering support with two less commonly prioritised areas: help finding a partner and feeling less lonely. METHODS: Anonymous SInQUE data were collected during a completed study in which we developed and tested the online SInQUE. Four focus groups were conducted with mental health supported accommodation staff (N = 2) and service users (N = 2). RESULTS: The most common social inclusion needs identified by service users (N = 31) were leisure activities, finding transport options, and feeling less lonely. Of the needs identified, those that service users and staff least frequently prioritised as support planning goals were having company at mealtimes, getting one's own furniture, feeling less lonely, help with finances, and help finding a partner. In the focus groups, staff and service users identified barriers to helping with loneliness and finding a partner which related to staff and service users themselves, supported accommodation services, and wider societal factors.

Estudio comparativo de la estadificación de pacientes con EPOC según GOLD 2007, 2011 y 2019 / Comparative study of the categorization of COPD patients based on GOLD 2007, 2011 and 2019

INTRODUCCIÓN: La Enfermedad Pulmonar Obstructiva Crónica afecta a 260 millones de personas a nivel mundial y representará la tercera causa de muerte para el año 2020. MATERIALES Y MÉTODOS: Se realizó un estudio observacional descriptivo transversal con la finalidad de comparar la estadificación de un grupo de pacientes venezolanos con EPOC según la Global Initiative for Chronic Obstructive Lung Disease (GOLD) 2007, 2011 y 2019. RESULTADOS: La muestra estuvo constituida por ochenta y nueve (89) pacientes con una edad promedio de 66,7 ± 0,9 años, siendo el 60,7% de los pacientes del sexo masculino y 82% fumadores. El 14,6% de los pacientes presentaban EPOC leve, 36% EPOC moderado, 41,6% EPOC severo y 7,9% EPOC muy severo. El valor del test Kappa de Cohen entre las escalas mMRC y CAT (COPD Assessment Test) fue de 0,529 (GOLD 2011) y 0,555 (GOLD 2019). CONCLUSIONES: 1) la poca concordancia entre el VEF1, grado de disnea e historial de exacerbaciones impacta la clasificación de la severidad de la EPOC al utilizar GOLD 2011; 2) la concordancia moderada entre las escalas mMRC y CAT sugiere que el tipo de cuestionario utilizado afecta la categorización de la severidad de la enfermedad; 3) los pacientes del grupo B mostraron una importante afectación en el intercambio gaseoso dado por valores más bajos de DLCO y oximetría arterial y 4) una proporción significativa de pacientes fueron clasificados en los grupos de alto riesgo (B y D) en GOLD 2011 y 2019.

INTRODUCTION: Chronic Obstructive Pulmonary Disease (COPD) affects 260 million people worldwide and it is thought to become the third leading cause of mortality by the year 2020. MATERIAL AND METHODS: A transversal descriptive observational study was conducted to compare the categorization of a group of Venezuelan COPD patients according to the Global Initiative for Chronic Obstructive Lung Disease (GOLD) 2007, 2011 and 2019. RESULTS: Eighty-nine (89) patients with a mean age of 66.7 ± 0.9 years were included, 60.7% were male and 82% smokers. 14.6% of the patients had mild COPD, 36% moderate COPD, 41.6% severe COPD and 7.9% very severe COPD. Cohen's Kappa coefficient value between mMRC and COPD Assessment test (CAT) was 0,529 (GOLD 2011) and 0,555 (GOLD 2019). CONCLUSIONS: 1) the lack of concordance between FEV1 values, degree of dyspnea and history of exacerbations impacts COPD severity classification when using GOLD 2011; 2) moderate agreement between mMRC and CAT scales suggests that the type of questionnaire used to evaluate perception of dyspnea can affect disease severity categorization; 3) group B patients showed a significant gas exchange impairment due to lower values of DLCO and arterial oxymetry and 4) a significant proportion of patients were categorized in the high-risk groups (B and D) both in GOLD 2011 and 2019. Optimization of the evaluation of COPD severity is important to allow a better standardization of care and pharmacological management of patients with this disease.

Hallazgos tomográficos pulmonares y su asociación con niveles de linfocitos T CD4+ en pacientes portadores del virus de inmunodeficiencia humana / CT pulmonary findings and their association with CD4+ T lymphocytes levels in human immunodeficiency virus carriers

Respiratory diseases are frequent complications in HIV infection. High Resolution Computed Tomography (HRCT) has proven superior to conventional imaging techniques to establish a pulmonary disease diagnosis. A study was conducted in order to establish the association between tomographic pulmonary patterns and immune status of HIV-infected patients. We evaluated 35 patients with respiratory symptoms and / or abnormal chest radiograph. An association was observed between the presence of ground glass pattern and P jirovecii infection. Likewise, a correlation between pulmonary histoplasmosis diagnosis and honeycomb pattern, lung cysts and nodules was established. Few correlation between tomographic patterns and CD4 + T lymphocyte counts was observed. In summary, HRCT findings can predict certain types of infection; nevertheless, further studies are required to extrapolate this association to other noninfectious lung diseases in HIV-infected patients.

Las enfermedades respiratorias constituyen complicaciones frecuentes en la infección por VIH. La Tomografía Axial Computarizada de Alta Resolución (TACAR) ha demostrado ser superior a las técnicas de imagen convencionales para establecer diagnóstico de enfermedad pulmonar. Se realizó un estudio con la finalidad de establecer la asociación entre patrones tomográficos pulmonares y el estado inmunológico de pacientes VIH+. Se evaluaron 35 pacientes sintomáticos respiratorios y/o con radiografía torácica patológica. Se observó una asociación entre la presencia de patrón en vidrio esmerilado e infección por P jirovecii. Asimismo, se observó una asociación entre diagnóstico de histoplasmosis pulmonar y patrón de panal de abejas, quistes pulmonares y nódulos. Se demostraron pocas correlaciones entre patrones tomográficos y conteo de linfocitos T CD4+. En conclusión, los hallazgos en la TACAR pueden predecir determinados tipos de infección requiriendo de más estudios para extrapolar esta asociación a otras enfermedades pulmonares no infecciosas en el paciente VIH+.