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.

The objective of this study was to test whether an airtime reward increased tuberculosis (TB) Check screening uptake. This served as a feasibility study for the planned Phase 2, which aimed to test behavioural messaging to boost take-up of TB testing among users who were advised to get tested by TB Check.

The study was a randomised controlled trial with a parallel design.

This study assessed mHealth support to boost TB testing in high-burden Cape Town clinics.

Patients aged 18 or above with a valid mobile phone number that had been added within the last 5 years were invited by the Western Cape Department of Health and Wellness through unsolicited text messages to screen for TB using TB Check.

Patients in the intervention group (n=1250) were additionally offered R15 airtime for completing the screening and participating in the research study. Patients were allocated to the intervention or control group through parallel randomisation with equal group size.

The primary outcome was the number of TB Check screenings completed within 1 week of the SMS invitation being sent.

Messages were successfully delivered to 616 patients in the control group and 633 patients in the intervention group. Uptake of the invitation by the intended recipients was very low. Eight users in the control group and 20 users in the intervention group initiated a self-screening (1.3% vs 3.2% of delivered messages; 95% CI of difference (0.2 to 3.5)), but only three users in the control group and seven users in the intervention group successfully completed a self-screening (0.49% vs 1.11% of delivered messages; 95% CI of difference (–0.4 to 1.6)). Low delivery of text message invitations (50.0%) and low completion of users who started the screening (35.7%) posed additional challenges. No adverse events were recorded.

The addition of a small airtime participation reward to unsolicited text message invitations did not appear to be an effective tool to reach targeted individuals in this context. The results of Phase 1 reported here suggested that Phase 2 would not be feasible, so we did not proceed with the planned Phase 2. However, uptake of incentivised self-screening was unexpectedly high among users who were not originally invited (presumably known contacts of the original invitees). Within 5 days of the invitations being sent, 1962 unique self-screenings had taken place using the incentive code; only 7 of these users were originally invited. The lessons learnt from this study can help to inform future efforts to promote TB self-screening, mHealth initiatives and attempts to engage with patients via text message. 

The study was pre-registered with the South African National Clinical Trials Registry (Phase 1 trial no DOH-27-112023-9045, Phase 2 trial no DOH-27-112023-4944) and the Pan African Clinical Trials Registry (Phase 1 trial no PACTR202311529334858).

This study aimed to determine the prevalence and factors associated with pre-diabetes and undiagnosed type 2 diabetes (UDD) in Cambodia.

This analysis used data from the WHO World Health Survey Plus, which was collected using a cross-sectional design with a GIS-based, three-stage sampling approach. Multiple logistic regression was used to identify key associated factors, based on a significance level of p

Data were collected from all 25 provinces in Cambodia between 12 March 2023 and 31 May 2023.

4427 individuals aged 18 years or older, residing in the selected household for at least 6 months in the past year.

Pre-diabetes (Haemoglobin A1c (HbA1c) 5.7%–6.4%) and UDD (HbA1c≥6.5%), without prior knowledge of having type 2 diabetes (T2D).

The weighted prevalences of pre-diabetes and UDD were 26.4% (95% CI 24.0% to 29.0%) and 9.3% (95% CI 7.9% to 11.0%). Pre-diabetes prevalence was higher in urban areas compared with rural areas (adjusted OR, aOR=1.2, 95% CI 1.0 to 1.4), males (aOR=1.7, 95% CI 1.3 to 2.3), individuals aged 40–49 (aOR=1.8, 95% CI 1.4 to 2.4), individuals aged 50+ years group (aOR=2.9, 95% CI 2.3 to 3.6) compared with the 18–39 years group, overweight individuals (aOR=1.7, 95% CI 1.4 to 2.0), obese (aOR=2.1, 95% CI 1.5 to 3.0) and those with elevated total triglycerides (aOR=1.3, 95% CI 1.1 to 1.5). Similar risk factors were identified for UDD, with the addition of hypertension (aOR=1.6, 95% CI 1.3 to 2.0) and high waist circumference (aOR=2.0, 95% CI 1.5 to 2.7).

The high prevalence of pre-diabetes and UDD in Cambodia is a pressing public health concern. Urgent and intensive interventions are needed to effectively prevent and manage T2D, particularly among urban residents, older persons and individuals with metabolic risk factors.

Poor indoor air quality and heat, individually and together, cause serious health impacts on children. Thus, there is a growing interest in creating school classroom environments that reduce health risks associated with these indoor environmental conditions. However, it is unclear if the existing evidence provides effective, practical and reliable interventions or strategies that can be implemented in classrooms. Additionally, the pertinence of these strategies for low-income communities needs to be elucidated. This scoping review will, therefore, document the findings of studies that have analysed interventions and strategies to improve school classroom conditions by reducing heat exposure and poor air quality to protect the health and well-being of children. This scoping review will consider: (1) interventions or adaptation strategies that have reduced heat exposure in classrooms; (2) interventions or adaptation strategies that have reduced air pollutant exposure in classrooms; (3) classroom building modifications that reduce exposure to heat and poor air quality and (4) improved health outcomes in children due to reduced heat and air pollutants. Studies that report reductions in heat or air pollutant exposure and show significant improvements in learner health outcomes will be prioritised for deeper analysis and considered particularly valuable for informing evidence-based recommendations.

We will explore original and review articles from both high-income and low-income settings that evaluate interventions and strategies for preventing or reducing heat exposure and poor air quality, to safeguard the health and well-being of children in classrooms. A comprehensive literature search will be conducted on Ovid MEDLINE, Ovid Global Health, PubMed, Scopus, ScienceDirect and Web of Science. Searches will be limited to literature published in the last 10 years (2015–2025). Results will be exported to EndNote for deduplication and to Abstrackr software for screening. Four reviewers will do abstract screening to ensure consistency. Data from included papers will be presented in tables with a narrative commentary.

No ethical approval is required for this study as primary data collection will not be conducted. A manuscript detailing the findings from this review will be published in a peer-reviewed journal.

Procedure-related pain should be minimised to prevent psychological trauma and the potential negative consequences on body physiology. Dressing changes in paediatric patients with burn injuries are frequently performed with analgesics alone where sedation is not indicated, especially in minor and superficial burns. It is hypothesised that distraction methods can be used in addition to pain alleviating medication to reduce the experience of pain in these patients.

With this research project, we aim to assess the effectiveness of a simple, inexpensive, non-electronic distraction method, a kaleidoscope, to reduce acute pain experienced in paediatric patients undergoing dressing changes in the outpatient clinic.

A randomised controlled trial will be performed at the Ngwelezana Tertiary Hospital, Empangeni, South Africa. Paediatric patients between the ages of 5 years and 12 years with minor and superficial partial thickness burn injuries who require dressing changes in the outpatient clinic, without sedation, will be randomised into two groups with a 1:1 allocation ratio. Fixed randomisation will be performed by a computer random number generator. The control group will receive standard practice of care which concerns a dressing change without any distraction methods, and the intervention group will receive distraction by use of a kaleidoscope as an additional method for potential pain alleviation. Patients in both groups will receive paracetamol or non-steroidal anti-inflammatory drugs when indicated according to hospital protocol. The primary outcome will be the change in pain score from pre-procedural to pain score during the dressing change and will be analysed with a linear regression analysis. Additionally, subanalyses will be performed to evaluate potentially modifying factors on the treatment effect. This will also be evaluated with a linear regression analysis and correlated with caregiver and healthcare worker observational pain scores. Participants and assessors are not blinded to group assignment due to the nature of the intervention. To achieve a power of 80% and a level of significance of 5% for detecting at least a 1-point difference in change in pain scores between the intervention and control group, a sample size of 50 patients in each group is required.

This study evaluates a non-invasive adjunct to reduce pain in children who undergo a painful procedure. Ethical approval has been granted from the University of Kwazulu-Natal’s biomedical research and ethics committee and the ethics and research committee of Ngwelezana Tertiary Hospital prior to recruitment (ref no. BREC/00005194/2023). Written informed consent will be acquired from all study participants’ caregivers. Study findings will be presented orally to staff at the paediatric burn unit of Ngwelezana Tertiary Hospital (study location). The research methodology and results will be presented at scientific conferences and will be submitted for publication in a peer-reviewed journal.

NCT06591195.