A Hybrid Spatial Statistical Learning Framework for Individualized Probability Estimation: Application to Multisite Autism Neuroimaging
Abstract
Autism spectrum disorder is a heterogeneous neurodevelopmental condition whose functional brain organization varies across individuals and imaging centers. Resting-state functional connectivity provides an opportunity to study this variation, but analysis is complicated by high dimensionality, strong dependence among connections, and substantial site heterogeneity. We introduce a Hybrid Spatial Statistical Learning Framework for individualized probability estimation in multisite autism neuroimaging. The framework combines edge-level connectivity, graph-based network organization, and participant characteristics as complementary representations of a common probability target. Fine-scale connectivity retains discriminatory information, while broader representations stabilize probability estimates under site shift. All preprocessing and model development are performed within complete site-held-out validation to assess transportability to unseen acquisition environments. Simulations show that the hybrid preserves the discrimination of the strongest edge model while improving probability accuracy as between-site heterogeneity increases. In 860 participants from 20 ABIDE sites, the hybrid retained ROC AUC while reducing Brier score and log loss. These results show that multiscale integration can improve the reliability and transportability of individualized probabilities from complex, spatially dependent biomedical data.
Related
- Statistical Inference for Probability Barycenters and Kolmogorov Moments
- Statistical Methods for Estimating Probability of Detection in Structural Health Monitoring
- Sharp High-Probability Statistical Rates for Heavy-Tailed Nonsmooth Convex Optimization
- Robust estimation in generalized linear models based on the normal quantiles of the probability integral transformation
- Uniform retractions onto a probability measure algebra and an application to topological groups
BibTeX
@misc{fuentes2026hybrid,
title = {{A Hybrid Spatial Statistical Learning Framework for Individualized Probability Estimation: Application to Multisite Autism Neuroimaging}},
author = {Montserrat Fuentes and Veronica B. Patterson},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.27882},
eprint = {2609.27882},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.27882},
}
RIS
TY - UNPB
TI - A Hybrid Spatial Statistical Learning Framework for Individualized Probability Estimation: Application to Multisite Autism Neuroimaging
AU - Montserrat Fuentes
AU - Veronica B. Patterson
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.27882
UR - https://arxiv.org/abs/2609.27882
AB - Autism spectrum disorder is a heterogeneous neurodevelopmental condition whose functional brain organization varies across individuals and imaging centers. Resting-state functional connectivity provides an opportunity to study this variation, but analysis is complicated by high dimensionality, strong dependence among connections, and substantial site heterogeneity. We introduce a Hybrid Spatial Statistical Learning Framework for individualized probability estimation in multisite autism neuroimaging. The framework combines edge-level connectivity, graph-based network organization, and participant characteristics as complementary representations of a common probability target. Fine-scale connectivity retains discriminatory information, while broader representations stabilize probability estimates under site shift. All preprocessing and model development are performed within complete site-held-out validation to assess transportability to unseen acquisition environments. Simulations show that the hybrid preserves the discrimination of the strongest edge model while improving probability accuracy as between-site heterogeneity increases. In 860 participants from 20 ABIDE sites, the hybrid retained ROC AUC while reducing Brier score and log loss. These results show that multiscale integration can improve the reliability and transportability of individualized probabilities from complex, spatially dependent biomedical data.
ER -