Tobacco use is the most significant modifiable risk factor for adverse health outcomes, and early research indicates there are also significant harms associated with vaping. National targets aim to reduce smoking and vaping during pregnancy for Aboriginal and Torres Strait Islander people. While most Aboriginal and Torres Strait Islander people want to quit, cessation is frequently attempted without support, increasing the chance of relapse. Group-based smoking cessation programmes increase quit success by 50%–130% in the general population; however, they have never been evaluated in Aboriginal and/or Torres Strait Islander communities.

The Gulibaa study is an Indigenous-led and community-embedded project that will co-design, implement and evaluate a group-based model of care to support Aboriginal and Torres Strait Islander women to be smoke- and vape-free. Staff of Health Services in New South Wales, Australia, will receive training to deliver a face-to-face group-based smoking and vaping cessation intervention. Aboriginal and/or Torres Strait Islander people who identify as a woman or non-binary, are pregnant or of reproductive age (16 to 49 years), currently smoke or vape at least once per day and are willing to attend the programme are eligible to participate. Up to 500 participants will be recruited. A mixed method evaluation approach will be implemented guided by the RE-AIM framework. Outcomes will include intervention reach, intervention effectiveness (determined primarily by self-reported 7-day point prevalence abstinence at 6 months follow-up), acceptability and feasibility of the intervention, programme fidelity and maintenance and cost effectiveness.

Embedding culturally safe support to quit during pregnancy can result in improved outcomes for both mother and child and immediately improve intergenerational health and well-being. Ethics approval has been provided by the Aboriginal Health and Medical Research Council and the University of Newcastle. Study findings will be disseminated to Aboriginal and Torres Strait Islander communities in ways that are meaningful to them, as well as through Aboriginal health services, key national bodies, relevant state and federal government departments.

ACTRN12625001050448.

The expenses associated with cancer treatment are increasing at a rapid pace. The financial strain of providing care is experienced worldwide, but is particularly pronounced in low and middle-income countries (LMICs). This has resulted in a growing acknowledgement of the importance of value-based cancer care. Choosing Wisely Africa (CWA) is an initiative aimed at reducing the excessive use and expenses associated with cancer treatment. In this study, we assessed adherence to CWA recommendations for the treatment of breast cancer in three high-volume cancer centres in Sub-Saharan Africa (SSA).

A cross-sectional study across Rwanda, Ghana and Tanzania was conducted, involving a review of medical records to assess adherence to five measurable CWA practices in breast cancer care. The study used inferential statistics, such as ² tests, to compare adherence among these countries.

This study was conducted in three cancer centres (Ocean Road Cancer Institute, Rwanda Military Hospital and Korle Bu Teaching Hospital) in three countries (Tanzania, Rwanda and Ghana, respectively).

A total of 542 patients were recruited. Eligible patients were those with a breast cancer diagnosis and complete data as pertaining to five CWA recommendations.

A total of 542 participants with a mean age of 51 years were included. Participants were well distributed across Ghana (37%), Rwanda (34%) and Tanzania (29%). Female patients represented 97% of the study cohort. Half (51%) of the participants had some form of insurance. The study observed high adherence to cancer staging (94%) before treatment and histological confirmation (91%) before breast lump removal across all sites. Hypofractionation was used in 0% of cases in Rwanda, 42% in Ghana and 70% in Tanzania.

This study provides critical insights into the implementation of CWA recommendations in breast cancer care in SSA. It highlights the disparities in adherence to CWA recommendations across different centres, showing the need for policy-driven changes and healthcare infrastructure improvement to standardise cancer care practices in LMICs.

Structural MRI of the brain is routinely performed on patients referred to memory clinics; however, resulting radiology reports, including volumetric assessments, are conventionally stored as unstructured free text. We sought to use natural language processing (NLP) to extract text relating to intracranial volumetric assessment from brain MRI text reports to enhance routine data availability for research purposes.

Electronic records from a large mental healthcare provider serving a geographic catchment of 1.3 million residents in four boroughs of south London, UK.

A corpus of 4007 de-identified brain MRI reports from patients referred to memory assessment services. An NLP algorithm was developed, using a span categorisation approach, to extract six binary (presence/absence) categories from the text reports: (i) global volume loss, (ii) hippocampal/medial temporal lobe volume loss and (iii) other lobar/regional volume loss. Distributions of these categories were evaluated.

The overall F1 score for the six categories was 0.89 (precision 0.92, recall 0.86), with the following precision/recall for each category: presence of global volume loss 0.95/0.95, absence of global volume loss 0.94/0.77, presence of regional volume loss 0.80/0.58, absence of regional volume loss 0.91/0.93, presence of hippocampal volume loss 0.90/0.88, and absence of hippocampal volume loss 0.94/0.92.

These results support the feasibility and accuracy of using NLP techniques to extract volumetric assessments from radiology reports, and the potential for automated generation of novel meta-data from dementia assessments in electronic health records.