Rhonda Marriott

Aboriginal pregnant women and new mothers face an increased risk of mental health issues, often stemming from historical trauma, including violence and discrimination. These challenges could contribute to complex trauma and adverse perinatal outcomes, highlighting the need for culturally sensitive care. However, non-Aboriginal clinicians often face barriers due to limited cultural knowledge, exacerbated by other factors such as time constraints for training and reliance on one-time training. Large Language Models (LLMs)-based chatbots offer the potential to support self-directed learning and enhance clinicians' self-efficacy through interactive question and answer. However, LLMs also pose challenges, including hallucinatory responses, outdated knowledge, fictitious information, unverifiable references, and difficulty handling domain-specific queries. In this study, we aim to mitigate these challenges by developing a specialized chatbot for improving Aboriginal perinatal mental health question-answering. The chatbot integrates Retrieval-Augmented Generation (RAG) with a semantic search engine, enabling it to retrieve verified external knowledge and provide more accurate, contextually relevant responses without frequent retraining. We evaluate its performance against a baseline GPT-3.5-turbo model and compare LLMs integrated with different RAG techniques to assess improvements in accuracy and reliability. Clinical Relevance- This study shows the potential of the specialized RAG LLM-based chatbot to improve domain-specific, clinically relevant, and on-demand question-answering support for clinicians. By providing accurate, verified information through interactive responses, it may help bridge knowledge gaps, support self-directed learning, and complement existing training.

In Australia, infants have the highest rate of child protection involvement. Many jurisdictions in Australia and internationally have introduced policies for prenatal planning and support, however little is known about outcomes of infants reported prenatally. This study is the first to use cross-jurisdictional, individual-record data to examine child protection pathways associated with prenatal and infant reports. Australian Institute of Health and Welfare data covering 2012-2018 was used. Cox regression analyses examined factors associated with removal into out-of-home care and reunification. Removals were significantly more likely for children with prenatal reports (HR = 2.29, 95% CI: 2.17-2.41). Earlier-in-pregnancy reports were not associated with reduced removals. There was significant variation across jurisdictions in removals and reunifications. Aboriginal children were significantly more likely to have prenatal reports and removals and less likely to be reunified. Examining the effectiveness and potential improvement of prenatal interventions and support could increase children's opportunity to safely remain at home.

Background
During pregnancy, childbirth and postnatally, women are at their most vulnerable, requiring health and social care systems able to meet their needs. In the context of perinatal care, assessing Aboriginal women’s mental health requires consideration of their whole-of-life to establish their overall social and emotional wellbeing. This requires mechanisms which respect women’s cultural positioning and needs. In the Australian health care system, Aboriginal women’s mental health is routinely viewed through mainstream screening and assessment tools, such as the Edinburgh Postnatal Depression Scale which does not address cultural strengths or the protective nature of being connected to culture. In the face of significant structural inequities, including in perinatal care, Aboriginal women are frequently marginalized which contributes to their disengagement from services. Despite this, women’s resilience remains evident and understanding why may hold the key to better perinatal care planning. As such, the aim of this study was to explore Aboriginal women’s resilience, self-efficacy and empowerment during their perinatal experiences, assessing factors contributing to their cultural strengths when addressing perinatal mental health concerns.

Methods
Situated in a larger pilot implementation project, this qualitative study used an Aboriginal Participatory Action Research method and was undertaken on Whadjuk Country, Boorloo (Perth Western Australia). Aboriginal women (n = 8) were invited to participate in yarns with the study’s lead Aboriginal researcher. Data was inductively and deductively analyzed, with findings interpreted through a decolonizing framework which prioritized strengths and cultural ways of being.

Results
Six themes were identified from analysis of the qualitative data: (1) strengthening identity-reconnecting to Culture; (2) connection to kinship/family sub-theme, strong partner support; (3) connection to country; (4) connection to culture; (5) resilience and self-efficacy; and (6) women’s experiences using the Baby Coming You Ready program’s digital platform. Themes 1–5 clearly demonstrated women’s strengths and resilience which were reported as a direct result of their culture and cultural connections; while theme 6 reported their positive experiences of using a strengths-based and culturally developed perinatal assessment platform.

Conclusion
The results of this study confirm the positive benefits and value of co-designing tools for use in clinical settings which incorporate the cultural determinants of health and holistic perspectives of social and emotional wellbeing when screening Aboriginal women’s perinatal mental health.

Background:
Perinatal depression and anxiety significantly impact maternal and infant health, potentially leading to severe outcomes like preterm birth and suicide. Aboriginal women, despite their resilience, face elevated risks due to the long-term effects of colonization and cultural disruption. The Baby Coming You Ready (BCYR) model of care, centered on a digitized, holistic, strengths-based assessment, was co-designed to address these challenges. The successful BCYR pilot demonstrated its ability to replace traditional risk-based screens. However, some health professionals still overrely on psychological risk scores, often overlooking the contextual circumstances of Aboriginal mothers, their cultural strengths, and mitigating protective factors. This highlights the need for new tools to improve clinical decision-making.

Objective:
We explored different explainable artificial intelligence (XAI)–powered machine learning techniques for developing culturally informed, strengths-based predictive modeling of perinatal psychological distress among Aboriginal mothers. The model identifies and evaluates influential protective and risk factors while offering transparent explanations for AI-driven decisions.

Methods:
We used deidentified data from 293 Aboriginal mothers who participated in the BCYR program between September 2021 and June 2023 at 6 health care services in Perth and regional Western Australia. The original dataset includes variables spanning cultural strengths, protective factors, life events, worries, relationships, childhood experiences, family and domestic violence, and substance use. After applying feature selection and expert input, 20 variables were chosen as predictors. The Kessler-5 scale was used as an indicator of perinatal psychological distress. Several machine learning models, including random forest (RF), CatBoost (CB), light gradient-boosting machine (LightGBM), extreme gradient boosting (XGBoost), k-nearest neighbor (KNN), support vector machine (SVM), and explainable boosting machine (EBM), were developed and compared for predictive performance. To make the black-box model interpretable, post hoc explanation techniques including Shapley additive explanations and local interpretable model-agnostic explanations were applied.

Results:
The EBM outperformed other models (accuracy=0.849, 95% CI 0.8170-0.8814; F1-score=0.771, 95% CI 0.7169-0.8245; area under the curve=0.821, 95% CI 0.7829-0.8593) followed by RF (accuracy=0.829, 95% CI 0.7960-0.8617; F1-score=0.736, 95% CI 0.6859-0.7851; area under the curve=0.795, 95% CI 0.7581-0.8318). Explanations from EBM, Shapley additive explanations, and local interpretable model-agnostic explanations identified consistent patterns of key influential factors, including questions related to “Feeling Lonely,” “Blaming Herself,” “Makes Family Proud,” “Life Not Worth Living,” and “Managing Day-to-Day.” At the individual level, where responses are highly personal, these XAI techniques provided case-specific insights through visual representations, distinguishing between protective and risk factors and illustrating their impact on predictions.

Conclusions:
This study shows the potential of XAI-driven models to predict psychological distress in Aboriginal mothers and provide clear, human-interpretable explanations of how important factors interact and influence outcomes. These models may help health professionals make more informed, non-biased decisions in Aboriginal perinatal mental health screenings.

In Western settings where solitary, continuous infant sleep throughout the night is emphasised, parents might perceive their infant's nightwaking as a problem and seek solutions. Interventions typically aim to reduce nighttime parent-infant interactions to facilitate independent infant sleep. There are concerns regarding the acceptability of these interventions to parents, and their applicability for families with diverse parenting practices, such as co-sleeping. The specific theories and strategies applied by evidence-based infant sleep interventions have not been systematically explored. This scoping review aimed to characterise infant sleep interventions for their theoretical underpinnings and behaviour change techniques (BCTs]. Where applicable, this review also aimed to explore associations between meaningful groupings of theory type and BCTs and outcomes including parent satisfaction and intervention adherence. Online databases were searched for Randomised Controlled and cluster Randomised Controlled Trials of non-pharmacological interventions delivered in non-acute primary care or community settings that targeted the prevention or treatment of sleep problems in infants (0–3 years). Twenty-eight of 34,898 retrieved articles were included, describing 34 unique interventions. Operant conditioning theory underpinned 50 % (13/26) of the theory-informed interventions. Interventions were found to be multicomponent and the application of BCTs was heterogeneous across interventions. Findings suggest a need for more diversity of theoretical underpinnings and a clear indication of BCTs included in interventions. Future research should identify theories that can be adapted to align with family cultural contexts and parenting practices, and BCTs that can be operationalised to facilitate acceptable and culturally sensitive approaches to infant sleep intervention.

Access to high-quality, culturally responsive nutrition advice during pregnancy is necessary for optimal health outcomes for mothers and babies. Evidence indicates that age, education and access to trained healthcare practitioners have a positive correlation with healthy food intake and positive outcomes. There are limited studies that discuss the importance of providing culturally responsive nutrition advice to pregnant Indigenous women. Therefore, this paper investigates the sources from which Indigenous women access nutrition information, assesses its adequacy in meeting needs, and identifies the effective ways to deliver this information. This study took place in Queensland (QLD), New South Wales (NSW), and Western Australia (WA), which were chosen to represent diverse cultural communities. A total of 103 participants were recruited, including Indigenous women and healthcare practitioners. Focus groups were audio-recorded, transcribed and analysed. Participants indicated that pregnant women are highly interested in improving their nutrition knowledge during pregnancy and actively seek information from their healthcare practitioners and dietitians. Findings suggested dissatisfaction with the information received, as it failed to address their needs. Results of this paper call for an urgent increased presence of community dietitians in antenatal clinics dedicated to Indigenous pregnant women as an additional way to provide families with the information they need for healthy pregnancies.

Background:
Effective mental health primary prevention and early detection strategies targeting perinatal mental healthcare settings are vital. Poor maternal mental health places the developing foetus at risk of lasting cognitive, developmental, behavioural, physical, and mental health problems. Indigenous women endure unacceptably poor mental health compared to all other Australians and disproportionately poorer maternal and infant health outcomes. Mounting evidence demonstrates that screening practices with Indigenous women are neither effective nor acceptable. Improved understanding of their perinatal experiences is necessary for optimizing successful screening and early intervention. Achieving this depends on adopting culturally safe research methodologies.

Methodology:
Decolonizing translational research methodologies are described. Perspectives of Australian Indigenous peoples were centred on leadership in decision-making throughout the study. This included designing the research structure, actively participating throughout implementation, and devising solutions. Methods included community participatory action research, codesign, and yarning with data analysis applied through the cultural lenses of Indigenous investigators to inform culturally meaningful outcomes.

Discussion:
The Indigenous community leadership and control, maintained throughout this research, have been critical. Allowing time for extensive community collaboration, fostering mutual trust, establishing strong engagement with all stakeholders and genuine power sharing has been integral to successfully translating research outcomes into practice. The codesign process ensured that innovative strengths-based solutions addressed the identified screening barriers. This process resulted in culturally sound web-based perinatal mental health and well-being assessment with embedded potential for widespread cultural adaptability.

Background: In Australia Stillbirth disproportionately impacts Aboriginal and Torres Strait Islander families. Still Aware received funding from the Australian Government to co-design, co- disseminate and co-evaluate stillbirth awareness for prevention messages with and for Aboriginal and Torres Strait Islander women and families.

Methods: Still Aware has taken a “steady walking and talking [1]’ approach. Firstly by conducting as many ‘meet and greet’ activities as each community needed to develop mutual rapport and trust. Once community were ready a Yarning WINDS workshop was held through which knowledge and sharing understanding of how key messages might be able to be effectively communicated to Aboriginal and Torres Strait Islander women was surfaced. After the WINDS workshop Still Aware has continued to work with community members to fine tune the resources ready for production, co-dissemination and co-evaluation through culturally appropriate mechanisms.

Results: To date, a mural consisting of multiple 8x8 paintings depicting what ‘stillbirth awareness for prevention means to us’ by community members is being created. When the mural is finalised it will be installed in a public place. A brochure titled ‘Keep bubba safe and strong’ has also been co-designed. It has culturally appropriate images, language and evidence-based messaging about keeping mum and bubba safe and strong in pregnancy. Educational videos have also been developed and/or planned to supplement the information in the brochure.

Conclusions: In this presentation ways that a non-Indigenous Australian not-for-profit organisation can successfully work with Indigenous communities will be explored. Resources that have been developed will be presented. Ways midwives can utilise these resources into their practice will be proposed.

Aboriginal and Torres Strait Islander people have some of the highest rates of infant death in Australia, including Sudden Unexpected Death in Infancy (SUDI) and Sudden Infant Death Syndrome (SIDS). In 2018, data from the Australian Mothers and Babies report (Australian Institute of health and Welfare, 2020) reported that 1 in 18 or 5.7% of all babies born in Australia were Aboriginal and/or Torres Strait Islander. While the proportion of Aboriginal infant deaths occurring out-of-hospital is not reported, there has been an identified need to address the issues of community competence and awareness in cardiopulmonary resuscitation (CPR) and first aid in Western Australia, for many years (Celenza et al., 2002; Lynch et al., 2005)…

Perinatal mental health is vital for mothers, infants, and families. Aboriginal mothers, despite their strengths, face greater mental health disparities due to colonisation and trauma. Traditional screening methods lack cultural sensitivity. The Baby Coming You Ready (BCYR) program offers a culturally sensitive assessment with promising pilot results. To support health professionals, an AI solution using the Explainable Boosting Machine (EBM) is proposed, trained with Aboriginal lived experiences. This model identifies maternal protective and risk factors, offering interpretable predictions for holistic culturally sensitive care.