Midwifery knowledge of equitable and culturally safe maternity care for Aboriginal women.

BACKGROUND: The Birthing on Noongar Boodjar project (NHMRC Partnership Project #GNT1076873) investigated Australian Aboriginal women and midwives' views of culturally safe care during childbearing. This paper reports on midwifery knowledge of Aboriginal women's cultural needs, their perceptions of health systems issues, and their ability to provide equitable and culturally safe care. METHOD: A qualitative study framed by an Indigenous methodology and methods which supported inductive, multilayered analyses and consensus-driven interpretations for two clinical midwife data groups (n = 61) drawn from a larger project data set (n = 145) comprising Aboriginal women and midwives. FINDINGS: Midwives demonstrated limited knowledge of Aboriginal women's cultural childbearing requirements, reported inadequate access to cultural education, substituted references to women-centered care in the absence of culturally relevant knowledge and consistently expressed racialized assumptions. Factors identified by midwives as likely to influence the midwifery workforce enabling them to provide culturally safe care for Aboriginal women included more professional development focused on improving understandings of cultural birth practices and health system changes which create safer maternal health care environments for Aboriginal women. CONCLUSIONS: Individual, workforce, and health systems issues impact midwives' capability to meet Aboriginal women's cultural needs. An imperative exists for effective cultural education and improved professional accountability regarding Aboriginal women's perinatal requirements and significant changes in health systems to embed culturally safe woman-centered care models as a means of addressing racism in health care.

A deep multi-view imbalanced learning approach for identifying informative COVID-19 tweets from social media.

Social media platforms such as Twitter are home ground for rapid COVID-19-related information sharing over the Internet, thereby becoming the favorable data resource for many downstream applications. Due to the massive pile of COVID-19 tweets generated every day, it is significant that the machine-learning-supported downstream applications can effectively skip the uninformative tweets and only pick up the informative tweets for their further use. However, existing solutions do not specifically consider the negative effect caused by the imbalanced ratios between informative and uninformative tweets in training data. In particular, most of the existing solutions are dominated by single-view learning, neglecting the rich information from different views to facilitate learning. In this study, a novel deep imbalanced multi-view learning approach called D-SVM-2K is proposed to identify the informative COVID-19 tweets from social media. This approach is built upon the well-known multiview learning method SVM-2K to incorporate different views generated from different feature extraction techniques. To battle against the class imbalance problem and enhance its learning ability, D-SVM-2K stacks multiple SVM-2K base classifiers in a stacked deep structure where its base classifiers can learn from either the original training dataset or the shifted critical regions identified using the well-known k-nearest neighboring algorithm. D-SVM-2K also realises a global and local deep ensemble learning on the multiple views' data. Our empirical experiments on a real-world labeled tweet dataset demonstrate the effectiveness of D-SVM-2K in dealing with the real-world multi-view class imbalance issues.

Coupling Machine Learning Models with Innovative Technology-based Screening Tool for Identifying Psychological Distress among Aboriginal Perinatal Mothers.

Aboriginal perinatal mothers are at a significant risk of experiencing mental health problems, which can have profound negative impacts, despite their overall resilience. This work aimed to build prediction models for identifying high psychological distress among Aboriginal perinatal mothers by coupling machine learning models with an innovative and culturally-safe screening tool. The original dataset of 179 Aboriginal mothers with 337 variables was obtained from twelve perinatal health settings at Perth metropolitan and regional centers in Western Australia between July and September 2022, using a specifically designed web-based rubric for the perinatal mental health assessment. After data preprocessing and feature selection, 23 variables related to emotional manifestations, the problematic partner, worries about daily living, and the need for follow-up wraparound support were identified as significant predictors for the high risk of psychological distress measured by the Kessler 5 plus adaptation. The selected predictors were used to train prediction models, and most of the chosen machine learning models achieved satisfactory results, with Random Forest and Support Vector Machine yielding the highest AUC of over 0.95, accuracy over 0.86, and F1 score above 0.87. This study demonstrates the potential of using machine learning-based models in clinical decision-making to facilitate healthcare and social and emotional well-being for Aboriginal families.

The EPDS and Australian Indigenous women: A systematic review of the literature.

PROBLEM: The Edinburgh Postnatal Depression Scale (EPDS) is considered the gold standard in perinatal mental health screening and the Australian Clinical Practice Guidelines recommend universal use. However, screening rates are four times lower with Indigenous Australian women compared to non-Indigenous women. Difficulties have been reported using the EPDS in this context. BACKGROUND: Evidence demonstrates the link between perinatal mental health and maternal and child outcomes. Indigenous Australian maternal and child health and wellbeing outcomes remain unacceptably poor across all measured parameters and reported psychological distress and child removal rates are increasing. METHODS: A systematic literature review was conducted to assess the effectiveness, validity, reliability, and cultural safety of the EPDS in the Indigenous Australian context and identify the availability and suitability of any adaptations. FINDINGS: The EPDS has not been validated for use with Indigenous Australian women. DISCUSSION: The findings and limitations identified in this review are consistent with concerns in other countries about the cross-cultural use of the EPDS and its sensitivity in predicting risk for postnatal depression amongst Indigenous women. Where adaptations of the EPDS have been used there has been no psychometric and cultural validation beyond the remote communities in which they were developed. CONCLUSIONS: There is no evidence to demonstrate that the EPDS in its current form and application is suitable for screening with Indigenous Australian women. Urgent work is required to evaluate and/or develop culturally meaningful screening tools that are predictive of risk for social and emotional wellbeing and perinatal mental distress in this context.

Validity and Acceptability of Kimberley Mum's Mood Scale to Screen for Perinatal Anxiety and Depression in Remote Aboriginal Health Care Settings.

BACKGROUND: The Edinburgh Postnatal Depression Scale (EPDS) is widely recommended for perinatal anxiety and depression screening. However, many Aboriginal women find EPDS language complex and confusing, and providers find using it with Aboriginal women challenging. The two part Kimberley Mum's Mood Scale (KMMS) was developed to improve screening: Part 1 is a Kimberley version of EPDS; Part 2 is a psychosocial tool that enables contextualisation of Part 1 scores. We aimed to determine if KMMS is a valid and acceptable method of identifying Kimberley Aboriginal perinatal women at risk of anxiety or depressive disorders compared to a semi-structured clinical interview. METHODS: Across 15 sites in the Kimberley, Western Australia, 97 Aboriginal women aged 16 years and older who intended to continue with their pregnancy or had a baby within the previous 12 months were administered the KMMS by trained healthcare providers who provided an overall assessment of no, low, moderate or high risk; 91 participants were then independently assessed by a blinded clinical expert using Diagnostic and Statistical Manual of Mental Disorders, 4th Edition criteria. A qualitative approach was used to determine KMMS' acceptability. RESULTS: Part 1 had high internal consistency (Cronbach's alpha, 0.89), and overall KMMS risk equivalence for screening for anxiety or depressive disorders was moderate (sensitivity, 83%; specificity, 87%; positive predictive value, 68%). Participants found the process easy and useful, and healthcare providers found KMMS more useful than EPDS. Part 2 allowed healthcare providers to ask questions that gave participants an opportunity to express themselves, resulting in a deeper understanding between them. CONCLUSION: KMMS is an effective tool for identifying Kimberley Aboriginal perinatal women at risk of anxiety and depressive disorders. Adoption of KMMS with culturally safe training and support is likely to improve screening processes, and with further validation may have broader applicability across remote Australia.

Perinatal depression and screening among Aboriginal Australians in the Kimberley.

PROBLEM: Adhoc culturally questionable perinatal mental-health screening among Aboriginal women in the Kimberley. BACKGROUND: Mental-health issues, substance abuse and suicide attempts are high among young Aboriginal women in Australia. There is no evidence that the Edinburgh Postnatal Depression Scale (EPDS) is effective or culturally safe. Screening practices are complicated by limited understanding of the complex cultural interface between Western and Aboriginal beliefs and notions about health and mental-health. QUESTION: What is the current context of perinatal mental-health screening practices among Aboriginal women in the Kimberley and what might be considered a culturally safe approach? METHODS: A review of the literature and exploration of current screening practices preceded community participatory action research (CPAR) of perinatal mental-health screening. RESULTS: More than 100 Kimberley women and 72 health practitioners contributed to this joint strategic body of work. Recommendations for practice include one single culturally appropriate Kimberley version of the EPDS.