机器学习在研究移民和少数族裔心理健康方面的应用：一篇系统综述 (Machine Learning Applications in Studying Mental Health Among Immigrants and Racial and Ethnic Minorities: A Systematic Review)

Background: The use of machine learning (ML) in mental health (MH) research is increasing, especially as new, more complex data types become available to analyze. By systematically examining the published literature, this review aims to uncover potential gaps in the current use of ML to study MH in vulnerable populations of immigrants, refugees, migrants, and racial and ethnic minorities. Methods: In this systematic review, we queried Google Scholar for ML-related terms, MH-related terms, and a population of a focus search term strung together with Boolean operators. Backward reference searching was also conducted. Included peer-reviewed studies reported using a method or application of ML in an MH context and focused on the populations of interest. We did not have date cutoffs. Publications were excluded if they were narrative or did not exclusively focus on a minority population from the respective country. Data including study context, the focus of mental healthcare, sample, data type, type of ML algorithm used, and algorithm performance was extracted from each. Results: Our search strategies resulted in 67,410 listed articles from Google Scholar. Ultimately, 12 were included. All the articles were published within the last 6 years, and half of them studied populations within the US. Most reviewed studies used supervised learning to explain or predict MH outcomes. Some publications used up to 16 models to determine the best predictive power. Almost half of the included publications did not discuss their cross-validation method. Conclusions: The included studies provide proof-of-concept for the potential use of ML algorithms to address MH concerns in these special populations, few as they may be. Our systematic review finds that the clinical application of these models for classifying and predicting MH disorders is still under development.

翻译：背景：随着新的更复杂数据类型变得可供分析，机器学习（ML）在心理健康（MH）研究中的应用正在增加。通过对已发表文献的系统检查，本综述旨在揭示目前 ML 在研究易受伤者移民、难民、移民和少数族裔心理健康方面应用的潜在差距。方法：在本系统综述中，我们使用 Google Scholar 查询与 ML 相关的术语、与 MH 相关的术语以及焦点搜索术语的人群，并用布尔运算符将它们串起来。我们还进行了向后引用搜索。包含的同行评审研究报告在 MH 上使用了 ML 方法或应用，并集中在感兴趣的人群。我们没有日期截止日期。如果出版物是叙述性的或不仅专门关注少数民族人口，就会被排除在外。从每个出版物中提取包括研究背景、心理卫生关注重点、样本、数据类型、使用的 ML 算法类型和算法表现在内的数据。结果：我们的搜索策略在 Google Scholar 中产生了 67,410 篇文章。最终，包括12篇文章。所有文章都发表在过去6年内，并有一半研究的是美国境内的人口。大多数评价研究使用有监督的学习来解释或预测心理卫生结果。一些出版物使用了多达16个模型来确定最佳预测能力。将近一半的包括在内的出版物没有讨论它们的交叉验证方法。结论：这些研究提供了证明在这些特殊人群中使用 ML 算法应对心理健康问题的潜力。我们的系统综述发现，这些模型的临床应用用于分类和预测MH障碍仍在发展中。