Keller Jacob, Eglinsky Jenny, Garbade Maike, Pfeiffer Elisa, Plener Paul L, Rosner Rita, Sukale Thorsten, Sachser Cedric
Clinical Child and Adolescent Psychology, Institute of Psychology, University of Bamberg, Kapuzinerstraße 32, 96047, Bamberg, Germany.
Department of Child- and Adolescent Psychiatry, Psychosomatics and Psychotherapy, Ulm University, Ulm, Germany.
Eur Child Adolesc Psychiatry. 2025 Sep 12. doi: 10.1007/s00787-025-02828-0.
Suicidality is a major public health concern worldwide. Evidence on the prevalence and risk factors of suicidality amongst unaccompanied young refugees (UYRs), a population already at risk for mental health disorders, is scarce.
Given the complexity of individual risk factor constellations influencing suicidality, machine learning (ML) methods offer a statistical approach that can detect complex relations within the data. Four ML classifiers, (logistic regression (LR), random forest (RF), support vector machines (SVM), and extreme gradient boosting (XGB)) were trained on a dataset of n = 623 UYRs (M=16.77, SD = 1.34, range: 12-21), retrieved from the large-scale randomized controlled trial Better Care to predict suicidal ideation. Features used in the classifiers were age, gender, asylum status, having contact with the family, and whether parents are alive as well as clinically elevated post-traumatic stress symptoms (PTSS), depressive symptoms and past suicide attempts. The classifiers were then tested on the independent dataset of n = 94 UYRs (M=16.31, SD = 2.03, range: 5-21) retrieved from the screening tool porta project to examine their predictive performance.
The prevalence of past-week suicidal ideation in the combined sample of N = 717 was 18.13%. All classifiers yielded good predictive performance (accuracy 0.734-0.840, sensitivity 0.857, AUC 0.853-0.880). The most relevant features were past suicide attempts, PTSS and depressive symptoms as risk factors, and having a living mother as protective factor.
Suicidal ideation is prevalent amongst UYRs, and using ML approaches, the classifiers were able to classify roughly 85% of the cases with suicidal ideation in the past week correctly as suicidal. Building on the findings of this study, screening for suicidality could be further improved by implementing ML classifiers in the assessment to highlight potential at risk cases early, and suitable interventions be developed.
自杀行为是全球主要的公共卫生问题。在无人陪伴的年轻难民（UYRs）中，自杀行为的患病率和风险因素的证据很少，而这一群体本身就有心理健康障碍的风险。
鉴于影响自杀行为的个体风险因素组合的复杂性，机器学习（ML）方法提供了一种统计方法，可以检测数据中的复杂关系。在一个n = 623名无人陪伴年轻难民的数据集上训练了四种ML分类器（逻辑回归（LR）、随机森林（RF）、支持向量机（SVM）和极端梯度提升（XGB））（M = 16.77，SD = 1.34，范围：12 - 21岁），该数据集取自大规模随机对照试验“更好的护理”，用于预测自杀意念。分类器中使用的特征包括年龄、性别、庇护状况、与家人的联系、父母是否健在以及临床上创伤后应激症状（PTSS）、抑郁症状和过去的自杀未遂情况。然后，在从筛查工具porta项目中获取的n = 94名无人陪伴年轻难民的独立数据集上对分类器进行测试（M = 16.31，SD = 2.03，范围：5 - 21岁），以检验它们的预测性能。
在N = 717的合并样本中，过去一周自杀意念的患病率为18.13%。所有分类器都具有良好的预测性能（准确率0.734 - 0.840，灵敏度0.857，AUC 0.853 - 0.880）。最相关的特征是过去的自杀未遂、PTSS和抑郁症状作为风险因素，以及有健在的母亲作为保护因素。
自杀意念在无人陪伴年轻难民中很普遍，使用ML方法，分类器能够正确地将过去一周内约85%有自杀意念的病例分类为有自杀倾向。基于本研究的结果，通过在评估中实施ML分类器以早期突出潜在的风险病例，并制定合适的干预措施，可以进一步改善对自杀行为的筛查。
