Can we diagnose mental disorders in children - A large-scale assessment of machine learning on structural neuroimaging of 6916 children in the adolescent brain cognitive development study

Aug 6, 2026

Prediction of mental disorders using neuroimaging is a fast-growing research direction with encouraging early findings in adults, yet evidence in children remains scarce and uncertain regarding transferability. Using 6916 children aged 9–10 from the multicenter Adolescent Brain Cognitive Development study, 136 structural MRI regional volume and thickness features were used to train machine-learning models to predict 10 psychiatric disorders. Cross-validation with permutation testing evaluated whether models captured true disorder-related patterns. Only ADHD and bipolar disorder showed statistically significant detection with advanced non-linear, dependency-aware, and confounder-resistant models.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Introduction

Motivation and background

Prior neuroimaging and machine-learning evidence

DOI: 10. 1002/jcv2.12184 ORIGINAL ARTICLE Can we diagnose mental disorders in children? A large‐scale assessment of machine learning on structural neuroimaging of 6916 children in the adolescent brain cognitive development study Richard Gaus1 | Sebastian Pölsterl 1 | Ellen Greimel2 | Gerd Schulte‐Körne2 | Christian Wachinger1,3 1The Lab for Artificial Intelligence in Medical Imaging (AI‐Med), Department of Child and Adolescent Psychiatry, Ludwig‐Maximilians‐ Universität, Munich, Germany 2Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, University Hospital, Ludwig‐ Maximilians‐Universität, Munich, Germany 3Department of Radiology, Technical University of Munich, School of Medicine, Munich, Germany Correspondence Christian Wachinger, The Lab for Artificial Intelligence in Medical Imaging (AI‐Med), LMU Klinikum, Ludwig-Maximilians-Universität, Nußbaumstr. 5a, 80336 Munich, Germany and Technical University of Munich, Department of Radiology, Ismaninger Straße 22, 81675 Munich, Germany. Email: christian.wachinger@med. uni[muenchen.de](muenchen.de) Funding information Bundesministerium für Bildung und Forschung, Grant/Award Number: 031L0200A; Bavarian State Ministry of Science and the Arts Abstract Background: Prediction of mental disorders based on neuroimaging is an emerging area of research with promising first results in adults. However, research on the unique demographic of children is underrepresented and it is doubtful whether findings obtained on adults can be transferred to children. Methods: Using data from 6916 children aged 9–10 in the multicenter Adolescent Brain Cognitive Development study, we extracted 136 regional volume and thickness measures from structural magnetic resonance images to rigorously evaluate the capabilities of machine learning to predict 10 different psychiatric disorders: major depressive disorder, bipolar disorder (BD), psychotic symptoms, attention deficit hyperactivity disorder (ADHD), oppositional defiant disorder, conduct disorder, post‐ traumatic stress disorder, obsessive‐compulsive disorder, generalized anxiety disorder, and social anxiety disorder. For each disorder, we performed cross‐validation and assessed whether models discovered a true pattern in the data via permutation testing. Results: Two of 10 disorders can be detected with statistical significance when using advanced models that (i) allow for non‐linear relationships between neuroanatomy and disorder, (ii) model interdependencies between disorders, and (iii) avoid confounding due to sociodemographic factors: ADHD (AUROC = 0. 567, p = 0.002) and BD (AUROC = 0. 551, p = 0.002). In contrast, traditional models perform consistently worse and predict only ADHD with statistical significance (AUROC = 0. 529, p = 0.002). Conclusion: While the modest absolute classification performance does not warrant application in the clinic, our results provide empirical evidence that embracing and explicitly accounting for the complexities of mental disorders via advanced machine learning models can discover patterns that would remain hidden with traditional models. | Richard Gaus and Sebastian Pölsterl are contributed equally to this work. | | --- | | This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
© 2023 The Authors. JCPP Advances published by John Wiley & Sons Ltd on behalf of Association for Child and Adolescent Mental Health. | JCPP Advances. 2023;3:e12184. [https://doi.org/10.1002/jcv2.12184](https://doi.org/10.1002/jcv2.12184) wi[leyonlinelibrary.com/journal/jcv2](leyonlinelibrary.com/journal/jcv2) 1 of 12 2 of 12 GAUS ET AL. KEYWORDS ABCD study, confounding, machine learning, mental disorders, neuroimaging INTRODUCTION A growing body of research focuses on using machine learning methods to identify vi

FAQs

这项研究使用了哪些数据与年龄范围？

研究使用了Adolescent Brain Cognitive Development（ABCD）研究中的6916名儿童数据，年龄为9–10岁。基于结构磁共振影像提取区域体积与皮层厚度等指标。

模型预测了哪些精神障碍？

模型面向10种精神障碍进行预测，包括重度抑郁障碍、双相障碍、精神病性症状、注意缺陷/多动障碍（ADHD）、对立违抗障碍、品行障碍、创伤后应激障碍、强迫症、广泛性焦虑障碍和社交焦虑障碍。

研究的主要发现是什么，哪些障碍达到统计显著？

在使用更高级的建模策略后，10种障碍中有两种达到统计显著：ADHD与双相障碍。相较之下，传统模型整体表现更差，只对ADHD给出了统计显著预测结果。

Aug 6, 2026

Upload by Emma Wilson