Al-Juhani Abdulkreem, Desoky Rodan, Iskander Ziyad, Alotaibi Rimaz M, Alzain Nouf N, Aljohani Naif, Alrefaai Mamoun M, Alhasanat Raneen A, AlMehaimeed Manar A, Alharthi Abdulrahman S
Forensic Medicine, Forensic Medicine Center, Jeddah, SAU.
Medicine and Surgery, College of Medicine Alfaisal University, Riyadh, SAU.
Cureus. 2025 Aug 12;17(8):e89873. doi: 10.7759/cureus.89873. eCollection 2025 Aug.
The incidence of suicide, self-harm, and mental crises among teenagers is rising, presenting significant global public health issues. Conventional clinical risk evaluations have inadequate predictive accuracy, often overlooking high-risk adolescents. Machine learning models employing electronic health records provide an innovative method for predicting mental health crises through the integration of intricate clinical data patterns. Hence, this review aims to comprehensively examine and synthesize information about machine learning models created using electronic health record data for predicting suicide attempts, self-harm, or mental hospitalization in teenagers. Adhering to Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) principles, we executed an exhaustive search across six databases (2000-2025) for peer-reviewed research utilizing machine learning algorithms on electronic health record data to predict adolescent mental health crises. The inclusion criteria emphasized structured or unstructured electronic health record inputs, teenage cohorts (ages 10-20), and performance indicators like area under the curve (AUC), sensitivity, or specificity. The Prediction Model Risk of Bias Assessment Tool (PROBAST) was utilized to evaluate the risk of bias. Our search yielded five studies (2019-2024) that satisfied the inclusion criteria. All studies were retrospective cohorts conducted in high-income nations. Structured electronic health record data (e.g., diagnoses, prescriptions) were frequently utilized; two studies included natural language processing. Machine learning models demonstrated moderate to high discrimination (AUC 0.68-0.88), exhibiting optimal performance in short-term suicide prediction with hybrid data inputs. All investigations, however, exhibited a significant risk of bias in the analysis domain owing to insufficient external validation and absent calibration data. The positive predictive values consistently remained modest across all models. Overall, machine learning models demonstrate potential for enhancing adolescent suicide risk classification utilizing electronic health record data, surpassing numerous traditional instruments. Nonetheless, issues of generalizability, ethical constraints, and implementation obstacles remain. Thorough validation, calibration, and equity assessments are necessary prior to incorporation into clinical practice.
青少年自杀、自残和精神危机的发生率正在上升，这成为了重大的全球公共卫生问题。传统的临床风险评估预测准确性不足，常常会忽视高风险青少年。利用电子健康记录的机器学习模型，通过整合复杂的临床数据模式，为预测心理健康危机提供了一种创新方法。因此，本综述旨在全面审视和综合有关利用电子健康记录数据创建的机器学习模型的信息，这些模型用于预测青少年的自杀企图、自残行为或精神住院情况。我们遵循系统评价和Meta分析的首选报告项目（PRISMA）原则，在六个数据库（2000 - 2025年）中进行了详尽搜索，以查找利用机器学习算法对电子健康记录数据进行分析以预测青少年心理健康危机的同行评审研究。纳入标准强调结构化或非结构化的电子健康记录输入、青少年队列（10 - 20岁）以及诸如曲线下面积（AUC）、敏感性或特异性等性能指标。使用预测模型偏倚风险评估工具（PROBAST）来评估偏倚风险。我们的搜索产生了五项符合纳入标准的研究（2019 - 2024年）。所有研究均为在高收入国家进行的回顾性队列研究。经常使用结构化电子健康记录数据（如诊断、处方）；两项研究纳入了自然语言处理。机器学习模型显示出中等至高的区分度（AUC为0.68 - 0.88），在使用混合数据输入进行短期自杀预测方面表现最佳。然而，由于外部验证不足和缺乏校准数据，所有调查在分析领域均表现出显著的偏倚风险。所有模型的阳性预测值一直都较低。总体而言，机器学习模型显示出利用电子健康记录数据增强青少年自杀风险分类的潜力，优于许多传统工具。尽管如此，仍存在可推广性、伦理限制和实施障碍等问题。在纳入临床实践之前，需要进行全面的验证、校准和公平性评估。
