Anaduaka Uchechi Shirley, Oladosu Ayomide Oluwaseyi, Katsande Samantha, Frempong Clinton Sekyere, Awuku-Amador Success
School of Public Health, University of Alberta, Edmonton, Alberta, Canada.
School of Graduate Studies, Lingnan University, Hong Kong, Hong Kong
BMJ Open. 2025 Apr 27;15(4):e091531. doi: 10.1136/bmjopen-2024-091531.
Perinatal depression and anxiety (PDA) is associated with a high risk of maternal mortality. Existing data shows that 95% of maternal mortality in low- and middle-income countries (LMICs) is due to resource constraints and negligence in addressing perinatal mental health (PMH). Research conducted in more developed countries has demonstrated the potential of artificial intelligence (AI) to assist in predicting, identifying, diagnosing and treating PDA. However, there is limited knowledge regarding the utilisation of AI in LMICs where PDA disproportionately affects women. Therefore, this study aims to investigate the role of AI in predicting, identifying, diagnosing and treating PDA among pregnant women and mothers in LMICs.
This systematic review will use a patient and public involvement (PPI) approach to systematically investigate the role of AI in predicting, identifying, diagnosing, and treating PDA among pregnant women and mothers in LMICs. The study will combine secondary evidence from academic databases and primary evidence from focus group discussions and a workshop and webinar to comprehensively analyse all relevant published and reported evidence on PDA and AI from the period between January 2010 and May 2024. To gather the necessary secondary data, reputable interdisciplinary databases in the field of maternal health and AI will be used, including ACM Digital Library, CINAHL, MEDLINE, PsycINFO, Scopus and Web of Science. The extracted data will be reported following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, ensuring transparency and comprehensiveness in reporting the findings. Finally, the extracted studies will be synthesised using the integrative data synthesis approach.
Given the PPI approach to be employed by this study which involves multi-stakeholders including mothers with lived experience, ethical approvals have been sought from the University of Ghana and University of Alberta. Additionally, during the review process, to ensure that the articles included in this study uphold ethical standards, only peer-reviewed articles from reputable journals/databases will be included in this review. The findings from this systematic review will be disseminated through workshops, webinars, conferences, academic publications, social media and all relevant platforms available to the researchers.
PROSPERO (10/06/24) CRD42024549455.
围产期抑郁和焦虑(PDA)与孕产妇死亡的高风险相关。现有数据表明,低收入和中等收入国家(LMICs)中95%的孕产妇死亡是由于资源限制以及在解决围产期心理健康(PMH)问题上的疏忽。在更发达国家进行的研究已经证明了人工智能(AI)在协助预测、识别、诊断和治疗PDA方面的潜力。然而,在PDA对女性影响尤为严重的LMICs中,关于AI应用的知识有限。因此,本研究旨在调查AI在LMICs中孕妇和母亲的PDA预测、识别、诊断和治疗中的作用。
本系统评价将采用患者和公众参与(PPI)方法,系统地调查AI在LMICs中孕妇和母亲的PDA预测、识别、诊断和治疗中的作用。该研究将结合来自学术数据库的二级证据以及来自焦点小组讨论、研讨会和网络研讨会的一级证据,以全面分析2010年1月至2024年5月期间所有关于PDA和AI的已发表和报告的相关证据。为了收集必要的二级数据,将使用孕产妇健康和AI领域的知名跨学科数据库,包括ACM数字图书馆、护理学与健康领域数据库(CINAHL)、医学期刊数据库(MEDLINE)、心理学文摘数据库(PsycINFO)、Scopus和科学引文索引(Web of Science)。提取的数据将按照系统评价和Meta分析的首选报告项目(PRISMA)框架进行报告,确保在报告结果时的透明度和全面性。最后,将使用综合数据综合方法对提取的研究进行综合。
鉴于本研究采用的PPI方法涉及包括有实际经验的母亲在内的多个利益相关者,已获得加纳大学和阿尔伯塔大学的伦理批准。此外,在审查过程中,为确保本研究纳入的文章符合伦理标准,本综述仅纳入来自知名期刊/数据库的同行评审文章。本系统评价的结果将通过研讨会、网络研讨会、会议、学术出版物、社交媒体以及研究人员可用的所有相关平台进行传播。
国际系统评价注册平台(PROSPERO)注册号:PROSPERO(2024年6月10日)CRD42024549455。