Brain-based classification of youth with anxiety disorders: transdiagnostic examinations within the ENIGMA-Anxiety database using machine learning

Journal article

Neuroanatomical findings on youth anxiety disorders are notoriously difficult to replicate, small in effect size, and have limited clinical relevance. These concerns have prompted a paradigm shift towards highly powered (i.e., big data) individual-level inferences, which are data-driven, transdiagnostic, and neurobiologically informed. Hence, we uniquely built/validated supervised neuroanatomical machine learning (ML) models for individual-level inferences, using the largest up to date neuroimaging database on youth anxiety disorders: ENIGMA Anxiety Consortium (N=3,343; Age: 10-25 years; Global Sites: 32). Modest, yet robust, brain-based classifications were achieved for specific anxiety disorders (Panic Disorder), but also transdiagnostically for all anxiety disorders when patients were subgrouped according to their sex, medication status, and symptom severity (AUC’s 0.59-0.63). Classifications were driven by neuroanatomical features (cortical thickness/surface area, subcortical volumes) in fronto-striato-limbic and temporo-parietal regions. This benchmark study provides estimates on individual-level classification performances that can be realistically achieved with ML using neuroanatomical data, within a large, heterogenous, and multi-site sample of youth with anxiety disorders.

Authors: Bruin, WB; Zhutovsky, P; van Wingen, GA; Bas-Hoogendam, JM; Groenewold, NA

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer Nature
• Journal: Nature Mental Health
• Volume: 2
• Issue: 1
• Pages: 104-118
• Publication date: 2024-01-10
• Acceptance date: 2023-10-26
• DOI: 10.1038/s44220-023-00173-2
• EISSN: 2731-6076
• Language: English
• Keywords: classification; child/adolescent psychiatry; magnetic resonance imaging; machine learning; anxiety disorders; neurostructural