Leveraging artificial intelligence in the prediction, diagnosis and treatment of depression and anxiety among perinatal women in low- and middle-income countries: a systematic review
Bibliographic record
Abstract
AIM: The adoption of artificial intelligence (AI) tools is gaining traction in maternal mental health (MMH) research. Despite its growing usage, little is known about its prospects and challenges in low- and middle-income countries (LMICs). This study aims to systematically review articles on the role of AI in addressing MMH in LMICs. METHODS: This systematic review adopts a patient and public involvement approach to investigate the role of AI in predicting, diagnosing or treating perinatal depression and anxiety (PDA) among perinatal women in LMICs. Seven databases were searched for studies that reported on AI tools/methods for PDA published between January 2010 and July 2024. Eligible studies were identified and extracted based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines using Covidence, and the data were synthesised using thematic analysis. RESULTS: Out of 2203 studies, 19 studies across eight countries were deemed eligible for extraction and synthesis. The review revealed that the supervised machine learning method was the most common AI approach and was used to improve the early detection of depression and anxiety among perinatal women. Additionally, postpartum depression was the most frequently investigated MMH condition in this study. Further, the review revealed only three conversational agents (CAs)/chatbots used to deliver psychological treatment. CONCLUSIONS: The findings underscore the potential of AI-based methods in identifying risk factors and delivering psychological treatment for PDA. Future research should investigate the underlying mechanisms of the effectiveness of AI-based chatbots/CAs and assess the long-term effects for diagnosed mothers, to aid the improvement of MMH in LMICs. PROSPERO REGISTRATION NUMBER: CRD42024549455.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".