Information regimes in population-graph neuroimaging: cohort context and implementation-dependent evaluation sensitivity
Preprint
Abstract
Population-graph models aggregate a query subject with an unlabeled cohort, so their reported performance can depend on the evaluation regime rather than on predictive information alone. Evaluation context has two separable axes: cohort visibility during training and the context available at inference . We study the training-time axis on an ABIDE-I cohort of 871 subjects (20 acquisition sites), comparing two population-graph implementations: a learned/adaptive graph (EV-GCN) and a static weighted graph (Parisot-GCN). Within each implementation the cohort, connectivity features, outer splits and training and selection rules are held fixed, and only the information available to the graph varies. The primary estimand is the implementation-by-training-context interaction, the difference between the P0-to-P1 AUC changes of the two implementations (ΔΔAUC). Across the two preselected outer splits (1024 and 2024), whose training and selection rules were fixed before the run, the direction is consistent and positive, with observed inter-action range 0.06285–0.11967; the earlier audited split 666 shows the same direction and is reported as historical support, because its execution identity cannot be established to the same standard. Uncertainty is assessed within each split by paired subject and site-cluster bootstrap resampling; the intervals are conditional on the fixed partitions and the trained checkpoints. Splits are replication units: they are not pooled and no cross-split average is reported. These findings tie reported performance to the evaluation information regime in the two implementations compared, and motivate explicit reporting of cohort visibility.Keywords
Funding Information
- Natural Science Foundation of Chongqing, China (CSTB2025NSCQ-LZX0057)
- Natural Science Foundation of Chongqing, China (CSTB2025NSCQ-LZX0073)
- Innovation and Development Joint Fund of Chongqing Natural Science Foundation (CSTB2024NSCQ-LZX0138)
- National Social Science Fund of China (23CTJ010)
- Chongqing Normal University (21XLB020)
This publication has 22 references indexed in Scilit:
- Data leakage in feature selection invalidates reported classification accuracy for autism diagnosis from fMRIeClinicalMedicine, 2026
- A fully inductive inference protocol for population GNNs in single-subject brain disorder diagnosisComputers in Biology and Medicine, 2026
- SFPGCL: Specificity-preserving federated population graph contrastive learning for multi-site ASD identification using rs-fMRI dataComputerized Medical Imaging and Graphics, 2025
- Self-supervised graph contrastive learning with diffusion augmentation for functional MRI analysis and brain disorder detectionMedical Image Analysis, 2024
- Knowledge-driven multi-graph convolutional network for brain network analysis and potential biomarker discoveryMedical Image Analysis, 2024
- BrainDAS: Structure-aware domain adaptation network for multi-site brain network analysisMedical Image Analysis, 2024
- Confounding Effects on the Performance of Machine Learning Analysis of Static Functional Connectivity Computed from rs-fMRI Multi-site DataNeuroinformatics, 2023
- Disease prediction with edge-variational graph convolutional networksMedical Image Analysis, 2022
- Disease prediction using graph convolutional networks: Application to Autism Spectrum Disorder and Alzheimer’s diseaseMedical Image Analysis, 2018
- A whole brain fMRI atlas generated via spatially constrained spectral clusteringHuman Brain Mapping, 2011