A Deep Learning-Derived Transdiagnostic Signature Indexing Hypoarousal and Impulse Control: Implications for Treatment Prediction in Psychiatric Disorders

Hannah Meijs; Jurjen J Luykx; Nikita van der Vinne; Rien Breteler; Evian Gordon; Alexander T Sack; Hanneke van Dijk; Martijn Arns

doi:10.1016/j.bpsc.2024.07.027

A Deep Learning-Derived Transdiagnostic Signature Indexing Hypoarousal and Impulse Control: Implications for Treatment Prediction in Psychiatric Disorders

Biol Psychiatry Cogn Neurosci Neuroimaging. 2024 Aug 13:S2451-9022(24)00237-4. doi: 10.1016/j.bpsc.2024.07.027. Online ahead of print.

Authors

Hannah Meijs¹, Jurjen J Luykx², Nikita van der Vinne³, Rien Breteler⁴, Evian Gordon⁵, Alexander T Sack⁶, Hanneke van Dijk⁷, Martijn Arns⁸

Affiliations

¹ Research Institute Brainclinics, Brainclinics Foundation, Nijmegen, the Netherlands; Department of Cognitive Neuroscience, Faculty of Psychology and Neuroscience, Maastricht University, Maastricht, the Netherlands. Electronic address: hannah@brainclinics.com.
² Research Institute Brainclinics, Brainclinics Foundation, Nijmegen, the Netherlands; Department of Cognitive Neuroscience, Faculty of Psychology and Neuroscience, Maastricht University, Maastricht, the Netherlands.
³ Synaeda Research, Drachten, the Netherlands.
⁴ Department of Clinical Psychology, Faculty of Social Sciences, Radboud University, Nijmegen, the Netherlands.
⁵ Brain Resource Ltd., San Francisco, California.
⁶ Department of Cognitive Neuroscience, Faculty of Psychology and Neuroscience, Maastricht University, Maastricht, the Netherlands.
⁷ Department of Cognitive Neuroscience, Faculty of Psychology and Neuroscience, Maastricht University, Maastricht, the Netherlands; Synaeda Research, Drachten, the Netherlands.
⁸ Research Institute Brainclinics, Brainclinics Foundation, Nijmegen, the Netherlands; Department of Cognitive Neuroscience, Faculty of Psychology and Neuroscience, Maastricht University, Maastricht, the Netherlands; Stanford Brain Stimulation Laboratory, Stanford University, Palo Alto, California.

PMID: 39142534
DOI: 10.1016/j.bpsc.2024.07.027

Abstract

Background: Psychiatric disorders are traditionally classified within diagnostic categories, but this approach has limitations. The Research Domain Criteria (RDoC) constitute a research classification system for psychiatric disorders based on dimensions within domains that cut across these psychiatric diagnoses. The overall aim of RDoC is to better understand mental illness in terms of dysfunction in fundamental neurobiological and behavioral systems, leading to better diagnosis, prevention, and treatment.

Methods: A unique electroencephalographic feature, referred to as spindling excessive beta, has been studied in relation to impulse control and sleep as part of the arousal/regulatory system RDoC domain. Here, we studied electroencephalographic frontal beta activity as a potential transdiagnostic biomarker capable of diagnosing and predicting impulse control and sleep problems.

Results: We showed in the first dataset (n = 3279) that the probability of having spindling excessive beta, classified by a deep learning algorithm, was associated with poor sleep maintenance and low daytime impulse control. Furthermore, in 2 additional, independent datasets (iSPOT-A [International Study to Predict Optimized Treatment in ADHD], n = 336; iSPOT-D [International Study to Predict Optimized Treatment in Depression], n = 1008), we revealed that conventional frontocentral beta power and/or spindling excessive beta probability, referred to as Brainmarker-III, is associated with a diagnosis of attention-deficit/hyperactivity disorder, with remission to methylphenidate in children with attention-deficit/hyperactivity disorder in a sex-specific manner, and with remission to antidepressant medication in adults with major depressive disorder in a drug-specific manner.

Conclusion: Our results demonstrate the value of the RDoC approach in psychiatry research for the discovery of biomarkers with diagnostic and treatment prediction capacities.

Keywords: ADHD; AI; EEG; MDD; RDoC; SEB.