Discovering robust biomarkers of psychiatric disorders from resting-state functional MRI via graph neural networks: A systematic review

2024-05-01

AI Summary

Resting-state fMRI biomarkers for psychiatric disorders suffer from low reproducibility and poor cross-diagnostic generalizability. Method: We propose a unified “prediction–attribution–evaluation” framework, systematically reviewing 65 graph neural network (GNN) studies on classification of ADHD, ASD, MDD, and schizophrenia (SZ), and integrating explainability methods—including GNNExplainer and Integrated Gradients—for multi-disorder comparison and quantitative robustness assessment. Contribution/Results: We introduce, for the first time, objective robustness criteria for neuroimaging biomarkers—namely cross-dataset consistency and topological stability—and find that only a few brain regions (e.g., anterior cingulate cortex, precuneus) exhibit cross-study reproducibility; no biomarker demonstrates consistent robustness across diagnoses. This work establishes a methodological benchmark and a reproducibility-oriented evaluation paradigm for GNN-driven psychiatric neuroimaging biomarker research.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Graph neural networks (GNN) have emerged as a popular tool for modelling functional magnetic resonance imaging (fMRI) datasets. Many recent studies have reported significant improvements in disorder classification performance via more sophisticated GNN designs and highlighted salient features that could be potential biomarkers of the disorder. However, existing methods of evaluating their robustness are often limited to cross-referencing with existing literature, which is a subjective and inconsistent process. In this review, we provide an overview of how GNN and model explainability techniques (specifically, feature attributors) have been applied to fMRI datasets for disorder prediction tasks, with an emphasis on evaluating the robustness of potential biomarkers produced for psychiatric disorders. Then, 65 studies using GNNs that reported potential fMRI biomarkers for psychiatric disorders (attention-deficit hyperactivity disorder, autism spectrum disorder, major depressive disorder, schizophrenia) published before 9 October 2024 were identified from 2 online databases (Scopus, PubMed). We found that while most studies have performant models, salient features highlighted in these studies (as determined by feature attribution scores) vary greatly across studies on the same disorder. Reproducibility of biomarkers is only limited to a small subset at the level of regions and few transdiagnostic biomarkers were identified. To address these issues, we suggest establishing new standards that are based on objective evaluation metrics to determine the robustness of these potential biomarkers. We further highlight gaps in the existing literature and put together a prediction-attribution-evaluation framework that could set the foundations for future research on discovering robust biomarkers of psychiatric disorders via GNNs.

Problem

• Brain Disorders
• Functional MRI
• Graph Neural Networks

Innovation

• Improved Graph Neural Network
• Stable Biomarkers
• Mental Disorders Prediction