In sub-Saharan African countries, the population-based assisted vaginal birth (AVB) rate is approximately 1% as compared with 16% in Western Europe. Consequently, women experiencing prolonged labour often face limited access to prompt intervention, leading to maternal and perinatal complications or unnecessary caesarean sections (CS). The OdonAssist device has been developed to be safe, user-friendly and more acceptable than currently used AVB devices. We propose to conduct a study in Ethiopia to evaluate if the implementation of this innovation is feasible and may contribute to improving the access to AVB while reducing unnecessary CSs.

We designed a single-centre feasibility study at Saint Luke Catholic Hospital (Wolisso, Ethiopia), a secondary facility where AVB is routinely performed by midwives and health officers under gynaecologist supervision, reflecting the local health system. Following a quasi-experimental design, we will include three groups of 20 women: an intervention group (OdonAssist), a vacuum extraction cohort and a control group of second-stage CS (performed without a prior trial of instrumental birth). The primary objective is to assess the clinical and methodological feasibility of the OdonAssist by collecting preliminary data on safety, acceptability and quantifying potential efficacy relative to the current standard of care. An exploratory economic evaluation of direct healthcare costs will be performed.

Approved by the Oromia Regional Health Bureau. The study results will be published in peer-reviewed journals to inform future impact evaluations of the OdonAssist device in global maternal and perinatal health.

NCT06918509.

Some cancers are diagnosed late, making them harder to treat. People with an undiagnosed cancer may use over-the-counter medications to manage non-specific cancer-related symptoms that often mimic other more common, easily treatable conditions. Results from the original Cancer Loyalty Card Study (CLOCS) suggest there may be an increase in purchases of pain and indigestion medication 8–9 months before an ovarian cancer diagnosis. We aim to validate the CLOCS findings by exploring whether a significant change in medication purchases could be an indication for early signs of the following cancer types: oesophageal, stomach (gastric), colorectal (bowel), pancreatic, liver, bladder, endometrial, uterine sarcoma, ovarian and vulval, using data collected through store loyalty cards.

Using a retrospective case-control design, we aim to recruit 1450 participants with one of the cancers of interest (cases) and 1450 participants without cancer (controls) in the UK who (or whose household members) hold a loyalty card with at least one participating high street retailer. We will use pre-existing loyalty card data to compare past purchase patterns of cases with those of controls. To assess cancer risk in participants and their purchasing patterns, we will collect information on demographic characteristics, health risk factors, lifestyle habits and behaviours, family history of cancer and any symptoms experienced prior to diagnosis (cases) and in the last year prior to study recruitment (controls). In addition, cases will be asked about their cancer diagnosis.

CLOCS-2 was reviewed and approved by the East Midlands-Leicester South Research Ethics Committee (23/EM/0224). Study outcomes will be disseminated through peer-reviewed publications, conferences, presentations to the research communities as well as patients and the public, the study website and other social media outlets.

NCT06447064, CPMS58679; pre-results.

Intraoperative complications contribute significantly to morbidity and mortality, and reducing their risk is a primary objective for all operating room’s healthcare professionals. Many of these complications are predictable and could be anticipated by the surgeon or anaesthesiologist. Various clinical scores were developed to assess cardiovascular risk, acute kidney injury or acute respiratory failure preoperatively. However, these scores require time for calculation and are not designed to be adjusted in real time during surgery, based on physiological signals and new intraoperative events. Besides, some events remain unpredictable because they are multifactorial.

In recent decades, Artificial Intelligence (AI)-based algorithms have been tested for the real-time prediction of intraoperative complications. These algorithms have the potential to continuously analyse patient data and provide early warnings, enabling professionals to intervene more effectively.

The aim of this review is to address the question: ‘What is the performance of AI models in predicting intraoperative complications during surgery using baseline and real-time data?’.

The review will follow the Transparent Reporting of multivariable prediction models for Individual Prognosis or Diagnosis: Checklist for Systematic Reviews and Meta-Analyses and BMJ guidelines. MEDLINE, Embase, CENTRAL (Cochrane), IEEE Xplore and Google Scholar databases will be explored for peer-reviewed papers up to 25 March 2025. First, two reviewers will independently screen titles, abstracts and full texts based on the inclusion and exclusion criteria. A third reviewer will resolve any disagreements. Eligibility criteria include AI models that predict or forecast intraoperative complications or immediate postoperative complications (up to the stay in the Post-Anaesthesia Care Unit) involving any patient undergoing surgery or interventional procedures with general or locoregional anaesthesia. The primary target is the algorithm’s performance, depending on the choice of the authors. Key items from the CHARMS 2014 checklist will be extracted using a standardised form. Risk of bias assessment will be performed using the PROBAST+AI tool. If possible, meta-analysis will be conducted by implementing a random effects meta-analysis model.

Ethical approval is not required. The results will be published in a peer-reviewed journal and presented at national and international conferences.

PROSPERO registration number: CRD420250599920. Any future amendments will be updated in the PROSPERO record.