Identifying Neuropsychiatric Disorder Subtypes and Subtype-dependent Variation in Diagnostic Deep Learning Classifier Performance
Ellis, C. A.; Miller, R. L.; Calhoun, V. D.
Show abstract
Clinicians and developers of deep learning-based neuroimaging clinical decision support systems (CDSS) need to know whether those systems will perform well for specific individuals. However, relatively few methods provide this capability. Identifying neuropsychiatric disorder subtypes for which CDSS may have varying performance could offer a solution. Dynamic functional network connectivity (dFNC) is often used to study disorders and develop neuroimaging classifiers. Unfortunately, few studies have identified neurological disorder subtypes using dFNC. In this study, we present a novel approach with which we identify 4 states of dFNC activity and 4 schizophrenia subtypes based on their time spent in each state. We also show how the performance of an explainable diagnostic deep learning classifier is subtype-dependent. We lastly examine how the dFNC features used by the classifier vary across subtypes. Our study provides a novel approach for subtyping disorders that (1) has implications for future scientific studies and (2) could lead to more reliable CDSS.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- 4D Dynamic Spatial Brain Networks At Rest Linked To Cognition Show Atypical Variability And Coupling In Schizophrenia 96%
- A Multimodal Vision Transformer for InterpretableFusion of Functional and Structural NeuroimagingData 96%
- A method for estimating dynamic functional network connectivity gradients (dFNG) from ICA captures smooth inter-network modulation. 95%
Similar papers in this journal
- Classification of Functional Movement Disorders with Resting State fMRI 93%
- BrainNET: Inference of brain network topology using Machine Learning 93%
- A novel method for tri-clustering dynamic functional network connectivity (dFNC) identifies significant schizophrenia effects across multiple states in distinct subgroups of individuals 93%
Similar papers in this journal
- A Confounder Controlled Machine Learning Approach: Group Analysis and Classification of Schizophrenia and Alzheimer's Disease using Resting-State Functional Network Connectivity 95%
- Providing context: Extracting non-linear and dynamic temporal motifs from brain activity 95%
- Multiclass Classification of Autism Spectrum Disorder, Attention Deficit Hyperactivity Disorder, and Typically Developed Individuals Using fMRI Functional Connectivity Analysis 93%
Similar papers in this journal
- Stable Biomarker Identification For Predicting Schizophrenia in the Human Connectome 93%
- Characterising grey-white matter relationships in recent-onset psychosis and its association with cognitive function 93%
- Functional connectivity dynamics reflect disability and multi-domain clinical impairment in patients with relapsing-remitting multiple sclerosis 92%
Similar papers in this journal
- Unraveling Integration-Segregation Imbalances in Schizophrenia Through Topological High-Order Functional Connectivity 95%
- Towards Multi-Brain Decoding in Autism: A Self-Supervised Learning Approach 93%
- Building Models of Functional Interactions Among Brain Domains that Encode Varying Information Complexity: A Schizophrenia Case Study 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.