Barcelona Institute for Global Health (ISGlobal), C/ del Dr. Aiguader, 88, Barcelona 08003, Catalonia, Spain; Universitat Pompeu Fabra (UPF), Spain.
Barcelona Institute for Global Health (ISGlobal), C/ del Dr. Aiguader, 88, Barcelona 08003, Catalonia, Spain.
Artif Intell Med. 2024 Nov;157:102991. doi: 10.1016/j.artmed.2024.102991. Epub 2024 Sep 29.
BACKGROUND & OBJECTIVES: Mental health disorders pose an increasing public health challenge worsened by the COVID-19 pandemic. The pandemic highlighted gaps in preparedness, emphasizing the need for early identification of at-risk groups and targeted interventions. This study aims to develop a risk assessment tool for anxiety, depression, and self-perceived stress using machine learning (ML) and explainable AI to identify key risk factors and stratify the population into meaningful risk profiles.
We utilized a cohort of 9291 individuals from Northern Spain, with extensive post-COVID-19 mental health surveys. ML classification algorithms predicted depression, anxiety, and self-reported stress in three classes: healthy, mild, and severe outcomes. A novel combination of SHAP (SHapley Additive exPlanations) and UMAP (Uniform Manifold Approximation and Projection) was employed to interpret model predictions and facilitate the identification of high-risk phenotypic clusters.
The mean macro-averaged one-vs-one AUROC was 0.77 (± 0.01) for depression, 0.72 (± 0.01) for anxiety, and 0.73 (± 0.02) for self-perceived stress. Key risk factors included poor self-reported health, chronic mental health conditions, and poor social support. High-risk profiles, such as women with reduced sleep hours, were identified for self-perceived stress. Binary classification of healthy vs. at-risk classes yielded F1-Scores over 0.70.
Combining SHAP with UMAP for risk profile stratification offers valuable insights for developing effective interventions and shaping public health policies. This data-driven approach to mental health preparedness, when validated in real-world scenarios, can significantly address the mental health impact of public health crises like COVID-19.
精神健康障碍对公共健康构成日益严峻的挑战，而 COVID-19 大流行则使这一问题雪上加霜。大流行凸显了准备工作中的差距，强调了需要及早识别高危人群并采取针对性干预措施。本研究旨在利用机器学习（ML）和可解释 AI 开发一种焦虑、抑郁和自我感知压力的风险评估工具，以识别关键风险因素，并将人群分层为有意义的风险特征。
我们利用来自西班牙北部的 9291 名个体的队列，进行了广泛的 COVID-19 后精神健康调查。ML 分类算法预测了抑郁、焦虑和自我报告的压力的三个类别：健康、轻度和重度结局。采用 SHAP（Shapley Additive exPlanations）和 UMAP（Uniform Manifold Approximation and Projection）的新颖组合来解释模型预测结果，并有助于识别高风险表型聚类。
抑郁的平均宏观平均一对一 AUROC 为 0.77（±0.01），焦虑为 0.72（±0.01），自我感知压力为 0.73（±0.02）。关键风险因素包括自我报告的健康状况不佳、慢性心理健康状况和社会支持不足。对于自我感知压力，确定了高风险特征，例如睡眠时间减少的女性。健康与高危人群分类的 F1-Score 超过 0.70。
将 SHAP 与 UMAP 结合用于风险特征分层，为制定有效的干预措施和制定公共卫生政策提供了有价值的见解。这种基于数据的精神健康准备方法，如果在现实场景中得到验证，可以显著解决 COVID-19 等公共卫生危机对精神健康的影响。
