用于饮食失调、抑郁症和酒精使用障碍诊断及风险预测的机器学习模型。
Machine learning models for diagnosis and risk prediction in eating disorders, depression, and alcohol use disorder.
作者信息
Zhang Zuo, Robinson Lauren, Whelan Robert, Jollans Lee, Wang Zijian, Nees Frauke, Chu Congying, Bobou Marina, Du Dongping, Cristea Ilinca, Banaschewski Tobias, Barker Gareth J, Bokde Arun L W, Grigis Antoine, Garavan Hugh, Heinz Andreas, Brühl Rüdiger, Martinot Jean-Luc, Martinot Marie-Laure Paillère, Artiges Eric, Orfanos Dimitri Papadopoulos, Poustka Luise, Hohmann Sarah, Millenet Sabina, Fröhner Juliane H, Smolka Michael N, Vaidya Nilakshi, Walter Henrik, Winterer Jeanne, Broulidakis M John, van Noort Betteke Maria, Stringaris Argyris, Penttilä Jani, Grimmer Yvonne, Insensee Corinna, Becker Andreas, Zhang Yuning, King Sinead, Sinclair Julia, Schumann Gunter, Schmidt Ulrike, Desrivières Sylvane
机构信息
Social, Genetic and Developmental Psychiatry Centre, Institute of Psychiatry, Psychology & Neuroscience, King's College London, De Crespigny Park, London SE5 8AF, UK; School of Psychology, Institute for Mental Health, University of Birmingham, Birmingham, UK.
Department of Psychological Medicine, Centre for Research in Eating and Weight Disorders, Institute of Psychiatry, Psychology & Neuroscience, King's College London, UK; South London and Maudsley NHS Foundation Trust, London, UK; Oxford Institute of Clinical Psychology Training and Research, Oxford University, Oxford, UK.
出版信息
J Affect Disord. 2025 Jun 15;379:889-899. doi: 10.1016/j.jad.2024.12.053. Epub 2024 Dec 17.
BACKGROUND
Early diagnosis and treatment of mental illnesses is hampered by the lack of reliable markers. This study used machine learning models to uncover diagnostic and risk prediction markers for eating disorders (EDs), major depressive disorder (MDD), and alcohol use disorder (AUD).
METHODS
Case-control samples (aged 18-25 years), including participants with Anorexia Nervosa (AN), Bulimia Nervosa (BN), MDD, AUD, and matched controls, were used for diagnostic classification. For risk prediction, we used a longitudinal population-based sample (IMAGEN study), assessing adolescents at ages 14, 16 and 19. Regularized logistic regression models incorporated broad data domains spanning psychopathology, personality, cognition, substance use, and environment.
RESULTS
The classification of EDs was highly accurate, even when excluding body mass index from the analysis. The area under the receiver operating characteristic curves (AUC-ROC [95 % CI]) reached 0.92 [0.86-0.97] for AN and 0.91 [0.85-0.96] for BN. The classification accuracies for MDD (0.91 [0.88-0.94]) and AUD (0.80 [0.74-0.85]) were also high. The models demonstrated high transdiagnostic potential, as those trained for EDs were also accurate in classifying AUD and MDD from healthy controls, and vice versa (AUC-ROCs, 0.75-0.93). Shared predictors, such as neuroticism, hopelessness, and symptoms of attention-deficit/hyperactivity disorder, were identified as reliable classifiers. In the longitudinal population sample, the models exhibited moderate performance in predicting the development of future ED symptoms (0.71 [0.67-0.75]), depressive symptoms (0.64 [0.60-0.68]), and harmful drinking (0.67 [0.64-0.70]).
CONCLUSIONS
Our findings demonstrate the potential of combining multi-domain data for precise diagnostic and risk prediction applications in psychiatry.
背景
精神疾病的早期诊断和治疗因缺乏可靠标志物而受到阻碍。本研究使用机器学习模型来发现饮食失调（EDs）、重度抑郁症（MDD）和酒精使用障碍（AUD）的诊断及风险预测标志物。
方法
病例对照样本（年龄18 - 25岁），包括神经性厌食症（AN）、神经性贪食症（BN）、MDD、AUD患者及匹配的对照组，用于诊断分类。对于风险预测，我们使用了基于人群的纵向样本（IMAGEN研究），在14岁、16岁和19岁时对青少年进行评估。正则化逻辑回归模型纳入了涵盖精神病理学、人格、认知、物质使用和环境等广泛的数据领域。
结果
即使在分析中排除体重指数，EDs的分类也高度准确。接受者操作特征曲线下面积（AUC - ROC [95% CI]）对于AN达到0.92 [0.86 - 0.97]，对于BN达到0.91 [0.85 - 0.96]。MDD（0.91 [0.88 - 0.94]）和AUD（0.80 [0.74 - 0.85]）的分类准确率也很高。这些模型显示出较高的跨诊断潜力，因为针对EDs训练的模型在从健康对照中分类AUD和MDD时也很准确，反之亦然（AUC - ROCs，0.75 - 0.93）。共同的预测因素，如神经质、绝望感和注意力缺陷/多动障碍症状，被确定为可靠的分类指标。在纵向人群样本中，模型在预测未来ED症状（0.71 [0.67 - 0.75]）、抑郁症状（0.64 [0.60 - 0.68]）和有害饮酒（0.67 [0.64 - 0.70]）的发展方面表现出中等性能。
结论
我们的研究结果证明了在精神病学中结合多领域数据用于精确诊断和风险预测应用的潜力。
Zotero 插件