JMIR Publications

ABSTRACT

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, which is centred on a digitised, 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 over-rely 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:

This study aims to explore different machine learning techniques powered by eXplainable Artificial Intelligence (XAI) for developing culturally informed, strengths-based predictive modelling 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:

The study utilized de-identified data from 293 Aboriginal mothers who participated in the BCYR program between September 2021 and June 2023 at six healthcare 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), K-Nearest Neighbour (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 (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were applied.

Results:

The EBM performed the best in predictions, achieving an accuracy of 0.849, an F1 score of 0.771, and an AUC of 0.821. The RF model followed with an accuracy of 0.829, an F1 score of 0.736, and an AUC of 0.795. Explanations from EBM, as well as SHAP or LIME applied to RF, revealed consistent patterns of key protective and risk factors and their impact on prediction outcomes in both global model behaviour and individual 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 factors interact and influence outcomes. These models may help health professionals make more informed decisions in Aboriginal perinatal mental health screenings.