Functional Imaging Derived ADHD Biotypes Based on Deep Clustering May Guide Personalized Medication Therapy

• Type of Material: Article
• Authors: Aichen Feng, University of Chinese Academy of Sciences; Yuan Feng, Peking University; Dongme Zhi, Beijing Normal University; Rongtao Jiang, Yale University; Zening Fu, Emory University; Ming Xu, University of Chinese Academy of Sciences; Min Zhao, University of Chinese Academy of Sciences; Shan Yu, University of Chinese Academy of Sciences; Michael Stevens, Yale University; Li Sun, Peking University; Vince D. Calhoun, Emory University; Jing Sui, Beijing Normal University
• Language: English
• Date: 2023-09-14
• Publisher: NIH
• Publication Version: Preprint (Prior to Peer Review)
• Copyright Statement: 2023 Research Square
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): https://doi.org/10.21203/rs.3.rs-3272441/v1
• Title of Journal or Parent Work: Research Square
• Start Page: 3272441
• Grant/Funding Information: This work was supported by the scientific and technological innovation 2030 - the major project of the Brain Science and Brain-Inspired Intelligence Technology (2021ZD0200500), National key research and development program (2021YFE0202500), the National Natural Science Foundation of China (82022035, 61773380), China Postdoctoral Science Foundation (2022M710434), the National Institute of Health grants (R01MH117107, R01MH118695) and the National Science Foundation (2112455).
• Keywords: biological subtype detection; deep clustering; graph convolutional network (GCN); ABCD; Attention deficit hyperactivity disorder (ADHD)
• Research Categories: Psychology, Cognitive; Psychology, Developmental; Biology, Neuroscience

Abstract

Attention deficit hyperactivity disorder (ADHD) is one prevalent neurodevelopmental disorder with childhood onset, however, there is no clear correspondence established between clinical ADHD subtypes and primary medications. Identifying objective and reliable neuroimaging markers for categorizing ADHD biotypes may lead to more individualized, biotype-guided treatment. Here we proposed graph convolutional network plus deep clustering for ADHD biotype detection using functional network connectivity (FNC), resulting in two biotypes based on 1069 ADHD patients selected from Adolescent Brain and Cognitive Development (ABCD) study, which were well replicated on independent ADHD adolescents undergoing longitudinal medication treatment (n=130). Interestingly, in addition to differences in cognitive performance and hyperactivity/impulsivity symptoms, biotype 1 treated with methylphenidate demonstrated significantly better recovery than biotype 2 treated with atomoxetine (p<0.05, FDR corrected). This imaging-driven, biotype-guided approach holds promise for facilitating personalized treatment of ADHD, exploring possible boundaries through innovative deep learning algorithms aimed at improving medication treatment effectiveness.