Artificial intelligence (AI) is rapidly evolving, offering an expanding suite of capabilities that go beyond the traditional focus on prediction and classification. Generative AI (GenAI) and agentic AI could create transformative practices to support real-world evidence (RWE) generation for health research by streamlining studies, accelerating insights and improving decision-making. However, there is no published overview available describing the range of applications in RWE generation. This review aims to describe where and how genAI and agentic AI are applied across the domains of healthcare research tasks for RWE generation. Additionally, to map applications by tasks and methods across the product lifecycle continuum, and to identify emerging gaps and opportunities.

This Living Scoping Review (LSR) will include studies reporting an application and/or evaluation of genAI or agentic AI applied to one or more RWE generation research tasks. Searches will be conducted in Embase, MEDLINE and additional sources (eg, grey literature). Citations will be independently screened by two human senior reviewers for a substantive training dataset and a commercially available screening algorithm (Robot Screener) will complete screening with a human reviewer. The LSR will include reports of studies (primary or reviews) describing and/or evaluating the application of any genAI model for RWE generation in healthcare, in English, published from 1 January 2025 to the date of search. Data will be extracted from all studies included in the LSR by one independent senior reviewer using a piloted template, with 10% quality check by a second senior reviewer. Descriptive statistics will be used to summarise the applications of genAI per RWE research task, and the results of genAI evaluations. Thematic analysis will be used to describe genAI application patterns, trends, gaps and opportunities. The LSR protocol and reports will be updated annually, and findings will be published on a publicly available website (eg, ISPE—the International Society for Pharmacoepidemiology).

Ethical approval is not required due to use of previously published data. Planned dissemination includes peer-reviewed publication, presentation and short summaries.

People with disabilities are underrepresented in clinical trials, which impacts generalisability and ethical integrity of results. Despite international mandates to diversify participants, there is a lack of guidance on how to make trials disability-inclusive. This scoping review identifies and synthesises guidance, practices and recommendations supporting the inclusion of people with disabilities in clinical trials.

We conducted a scoping review following the Arksey and O'Malley framework and reported according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses for scoping reviews.

Medline (OVID) and Public Affairs Information System Index (October 2024) searches identified peer-reviewed articles. Grey literature was identified through targeted advanced Google searches and website reviews (February–March 2025). Google Scholar was searched to identify recently published documents between March and April 2025.

Documents with guidance or policies related to inclusion of people with disabilities in clinical trials published in English from 2019 to 2025 were included.

Two independent reviewers screened titles, abstracts and full texts and extracted data, with adjudication by a third reviewer.

A total of 69 documents met inclusion criteria. Thematic synthesis identified eight recommendation domains: (1) inclusive and universal trial design, (2) accessible recruitment, (3) inclusive data collection, (4) equitable data analysis, (5) accessible reporting and dissemination, (6) ethical oversight and institutional review board inclusion, (7) supported and accessible consent processes and (8) the inclusion of people with disabilities as researchers and stakeholders. Themes cutting across all domains included guidance emphasising universal design, anti-ableist frameworks, supported decision-making, flexible protocols and engagement with disability communities.

Disability-inclusive clinical trials are essential to ensure the validity of clinical trial results, uphold ethical responsibilities and advance health equity. While emerging frameworks offer direction on how to include people with disabilities in trials, current implementation remains inconsistent and largely voluntary. Clear, enforceable standards are needed to support governments, ethics boards, institutions and funders in making clinical trials more disability-inclusive.

Using network analysis, which takes a holistic approach to health systems, we aimed to identify which psychosocial burden dimensions are the most central and, thus, critical to prioritising to improve the overall health of people with type 1 diabetes (PwT1D).

A cross-sectional network analysis.

We used data from participants attending 44 diabetes centres in France, who were enrolled in the SFDT1 cohort study between June 2020 and February 2024.

We included 1430 PwT1D (52% women, median age (IQR) 41 (31–52.8) years) who had completed questionnaires on diabetes burden.

The items from questionnaires on diabetes distress, fear of hypoglycaemia, quality of life, treatment burden and the impact of diabetes on education and work.

The network was highly stable (correlation stability coefficient=0.75). We observed nine domains within the network; ‘Loneliness, Worrying & Burnout’ was the most influential. We further grouped the domains into three distinct syndromes labelled ‘Diabetes Distress’, ‘Treatment Burden’ and ‘Impact of Diabetes on Life’. These syndromes reflect the most relevant pillars of the psychosocial burden in PwT1D.

We observed that ‘Loneliness, Worrying & Burnout’ is the most influential psychosocial burden network domain to prioritise for type 1 diabetes care. This new network-based approach opens the path to defining personalised interventions targeting the most critical burden parameters to expect the most significant overall beneficial impact on PwT1D’s health.

NCT04657783.

Yoga has been shown to improve pain and function compared with no exercise in people with chronic low back pain (LBP), but treatment effects are small. Given that yoga is a mind–body intervention that addresses physical as well as psychological factors, it may be more effective for patients with chronic LBP who are at high risk of poor prognosis. The study aims to investigate the efficacy of a 12-week yoga programme combined with education in reducing pain and disability for individuals with chronic LBP at high risk of poor prognosis at short (12 weeks) and intermediate (24 weeks) terms, compared with a control group receiving education only.

A randomised controlled trial will include 110 adults with chronic non-specific LBP reporting an average pain intensity of 3 points or more on a 0–10 scale over the past week and classified as high risk of poor prognosis (ie, scoring 50 points or above) on the Orebro Musculoskeletal Pain Questionnaire short-form. Participants in the control group will receive an educational booklet and attend three face-to-face lectures over a 3-month period. In the intervention group, in addition to the booklet and lectures, participants will attend group yoga sessions twice a week for 12 weeks, totalling 24 yoga sessions. The primary outcome is disability assessed at 12 weeks, measured using the Roland-Morris Disability Questionnaire.

The study was approved by the Human Research Ethics Committee of Universidade Federal de Minas Gerais (Protocol number CAAE: 57028022.0.0000.5149). Findings will be disseminated to trial participants, clinicians and the broader public and scientific community.

NCT05953155.

Prospective cohort study

In this pilot study, we recruited patients from a secondary pain clinic in Boston, Massachusetts.

In this pilot study, we recruited patients from a secondary pain clinic within the Spaulding Rehabilitation network in Boston, Massachusetts, USA. We enrolled 37 patients who initially came in for a clinical visit with the principal investigator of the study. Of the 37 patients, 14 patients who continued to enrol/join after December 2024 received the ‘DigitalPulse’ to drive engagement.

To present a roadmap for our efforts to contextualise engagement in our digital health technology study and showcase our attempts to incorporate an engagement approach inspired by the Method for Program Adaptation through Community Engagement. Building on this, we further incorporated continued feedback and revision beyond the prototype of the user-centred feedback form (‘DigitalPulse’) to include expanded stakeholders such as clinicians and research assistants.

From these patients, we observed that our approach produced highly variable changes in engagement with slight increases at the group level.

From our observations, we have found that it is important to incorporate iterative refinements and expanded stakeholder involvement in designing patient-centred digital health tools to improve engagement. Overall, we report a process to address engagement and emphasise the need for continuous personalisation in digital health interventions.

Healthcare professionals are increasingly burdened by clerical tasks, contributing to reduced job satisfaction, heightened burnout and potential risk for patient safety. Despite ongoing efforts to promote patient-centred care, direct interaction time with patients remains limited, affecting both professional fulfillment and the quality of patient experience. In response, hospitals have begun implementing structured programmes to enhance protected patient time, though their effectiveness remains uncertain. The Geneva University Hospitals (HUG) developed the ‘More Time at Patients’ Side’ (MTP) programme, integrating Lean management and Design Thinking principles to optimise clinical interactions. This study aims to evaluate an MTP booster intervention, designed to reinforce selected programme elements, using a cluster-randomised controlled trial focusing on patient pain management and healthcare professional job satisfaction.

The MTP Booster will be implemented in selected units at HUG across internal medicine, surgery, rehabilitation, palliative care and paediatrics units. Originally launched in 2017, the MTP programme introduced structured medical rounds, delegated clerical tasks and communication tools such as patient whiteboards. The booster intervention follows a stepped-wedge cluster-randomised design, with immediate reactivation in intervention units and delayed implementation in control units. The intervention consists of two key components: (A) a collaborative selection of MTP elements to reinforce, based on their feasibility and perceived usefulness and (B) structured integration of audit and feedback into daily routines, including on-site observations and staff training. The primary outcome is the quality of pain management, measured by the timely administration of analgesia. Secondary outcomes include pain documentation, patient satisfaction, healthcare professional work satisfaction, burnout levels, turnover risk and absenteeism. Other MTP-related audits are suspended during the study to preserve methodological integrity, and concurrent institutional initiatives will be documented as potential confounders.

The trial has a declaration of no objection by Swissethics (2024-00169). All final results will be reported in accordance with the Consolidated Standards of Reporting Trials extended for cluster-randomised trials. We intend to publish the results of this trial in an international peer-reviewed journal, irrespective of the results.

The trial is currently in the pre-results stage and is registered at ClinicalTrials.gov, ID: NCT06491797, 9 July 2024.

To understand how reductions in resource allocation affect food safety services in England.

This longitudinal ecological study analysed secondary observational data.

England, data at the local authority level.

Ecological study, without human participants.

The primary outcome measures were the number of staff, represented by the number of full-time equivalents per capita, number of interventions per establishment, and proportion of hygiene-compliant establishments.

A £1 decrease in food safety expenditure per capita was associated with a 2% (–3.3 to –0.7) decrease in staffing levels and a 1.6% (–3.2 to –0.1) decrease in the number of interventions achieved per establishment. A one-unit reduction in staff was associated with a 42.2% (–80.5 to –11.9) decrease in the number of interventions achieved. No evidence of an association was found between expenditure or staff levels and the proportion of compliant establishments.

Spending reductions negatively affected the capacity of food safety teams to provide key services. Reductions in food safety expenditure significantly affected food hygiene staff levels and service provision. This finding raises concerns about the capacity of food safety teams to operate and the potential for increased public risk of gastrointestinal infections.

To assess human papillomavirus (HPV) vaccine awareness and uptake among caregivers in rural Indigenous communities in Guatemala and to identify sociodemographic predictors of vaccine unawareness and non-uptake.

This cross-sectional survey was conducted across 12 rural Indigenous communities in Guatemala’s Central Highlands. Using a community-engaged research approach, trained multilingual health workers administered surveys in Spanish, Kaqchikel or K’iche’. Eligible participants were adults who served as primary caregivers to children. The survey assessed HPV vaccine awareness, vaccine attitudes and uptake among those with daughters aged 8 or older. Logistic regression was used to examine predictors of vaccine unawareness and bivariate analysis explored differences in vaccine uptake.

Among 602 participants (92.5% identified as Indigenous), 95% expressed willingness to vaccinate a child against cervical cancer, yet only 56% had heard of the HPV vaccine. Of the 175 participants with eligible daughters, only 33.7% reported vaccination. Indigenous identity, older age and illiteracy were significantly associated with HPV vaccine unawareness. Speaking an Indigenous language at home was associated with greater awareness. Departmental differences were significant: participants from Sololá were more likely to be unaware of the vaccine, while those from Sacatepéquez had higher awareness and uptake. Community partners noted that access to information, geographic connectivity and social desirability may influence both awareness and response accuracy.

Despite strong willingness to vaccinate, significant knowledge gaps persist among Indigenous caregivers. Tailored, community-informed education strategies—delivered through trusted channels and adapted linguistically and culturally—are urgently needed to increase awareness and uptake of the HPV vaccine in underserved Guatemalan communities.

Shortages in the nursing workforce impact on the quality of patient care and pose a complex challenge for governments and healthcare organisations across the globe. There are estimated to be approximately 29 million nurses worldwide as of 2020, with a shortage of approximately 7 million against required levels. Despite growth in the workforce over the coming years, the nursing shortage is still projected to be 4.5M by 2030.1

One approach to addressing...

Women who develop gestational diabetes mellitus (GDM) have a 60% lifetime risk of developing type 2 diabetes mellitus (T2D), which is already elevated within the first decade following childbirth. Despite the impact of lifestyle interventions to reduce long-term T2D risk in women with previous GDM, successful implementation of lifestyle interventions remains a barrier. Metformin is recommended for adults at increased risk of developing T2D; however, there is limited evidence of tolerability in the early postpartum period. Glucagon-like peptide 1 receptor agonists (GLP-1 RA) are effective at improving glycaemic status and body weight. However, GLP-1 RA have not been evaluated in the postpartum population. Finally, physical activity monitors may support behaviour changes related to physical activity to reduce long-term risk of T2D but are yet to be studied following GDM.

This will be a multicentre, randomised, open-label interventional pilot study. Using a 2x2 factorial design, we will examine the feasibility and acceptability of a pharmacotherapy intervention and a physical activity intervention in women with previous GDM at increased risk of developing T2D. Participants will be recruited from tertiary referral hospitals in Australia and will be randomised to receive either metformin alone or in combination with a GLP-1 RA and subsequently randomised to either a physical activity intervention involving activity monitor use, or usual care for 6 months, followed by a 6-month follow-up period. Primary feasibility outcomes include the acceptability and safety of the metformin and GLP-1 RA as measured through pill and injection counts, acceptability questionnaire and adverse events.

This trial is registered with the Australian and New Zealand Clinical Trials Registry (Registration Number: ACTRN12624001253594). This trial has received ethics approval from the South Eastern Sydney Local Health District Human Research Ethics Committee (Approval Number: 2024/ETH00042, protocol version v1.1, 28/02/2025).

Australian and New Zealand Clinical Trials Registry, Registration Number: ACTRN12624001253594.

The global rise in the population aged over 65 has led to a corresponding increase in cognitive impairment diagnoses, with dementia as a predominant condition characterised by diverse aetiopathogenetic profiles. Behavioural and psychological symptoms of dementia (BPSD) encompass a range of psychiatric, behavioural and cognitive symptoms associated with cognitive impairment. BPSD significantly affects patients, caregivers and healthcare providers, often necessitating interventions like sedatives or physical restraints that may worsen patient outcomes. Emerging evidence underscores the need for innovative, non-pharmacological interventions to manage BPSD effectively.

The current study intends to investigate the feasibility and acceptability of customised, immersive virtual reality environments (iVRe) to reduce responsive behaviours among individuals with dementia. Building on prior findings demonstrating virtual reality (VR) potential in reducing anxiety and fostering positive emotional states, this pilot study assesses the feasibility, safety and user engagement of customised iVRe interventions.

A longitudinal, mixed-methods design will be employed, enrolling 20 elderly participants with varying levels of cognitive impairment from the APSP ‘Margherita Grazioli’ long-term care facility in Trento. Participants undergo three VR exposure sessions featuring tailored environments adjusted in real-time for visual and auditory preferences. Data collection integrates standardised self-report questionnaires, observational tools and clinical records. Measures include the Functional Assessment Staging Tool, Neuropsychiatric Inventory and Cohen-Mansfield Agitation Inventory, as well as tools assessing pain, anxiety and emotional states before, during and after VR sessions.

The study protocol has been approved by the Comitato Etico Territoriale della Provincia Autonoma di Trento per le Sperimentazioni Cliniche, Azienda Provinciale per i Servizi Sanitari—Trento, Italy (Rep. Int. 12090, 15 May 2025). All participants or their legal representatives will provide written informed consent prior to enrolment. Deidentified data will be securely stored on institutional servers at the Fondazione Bruno Kessler and the APSP ‘Margherita Grazioli’, curated in compliance with the General Data Protection Regulation, and retained for 3 years after study completion. Any data shared externally will be provided in fully anonymised form, and only for scientific purposes, subject to prior ethical and legal approval. Study findings will be disseminated through peer-reviewed publications, conference presentations and executive summaries shared with participating institutions and stakeholders.

NCT06693193.