Prediction and Causality of functional MRI and synthetic signal using a Zero-Shot Time-Series Foundation Model

2025-09-15

AI Summary

This study evaluates the performance of time-series foundation models for zero-shot fMRI time-series forecasting and causal discovery, benchmarked against conventional methods. Methodologically, we propose a zero-shot forecasting framework that requires no fine-tuning and integrates a Granger-like causal estimation module; validation is conducted on synthetically generated fMRI-like time series—constructed via coupled logistic maps and Ornstein–Uhlenbeck processes—to ensure ground-truth causal structure. Results demonstrate that the foundation model achieves significantly lower mean absolute percentage error (MAPE) in zero-shot fMRI prediction (0.27 vs. baseline 0.55), outperforms classical Granger causality analysis in causal detection accuracy, and exhibits strong generalization across subjects and cognitive tasks. The core contribution is the first systematic empirical validation of foundation models’ feasibility and superiority for zero-shot forecasting and causal inference on neural time series—establishing a novel paradigm for brain functional modeling and unsupervised brain network characterization.

Technology Category

• Machine Learning: Causal Learning
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems
• Computer Vision: Other Foundations of Computer Vision

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Time-series forecasting and causal discovery are central in neuroscience, as predicting brain activity and identifying causal relationships between neural populations and circuits can shed light on the mechanisms underlying cognition and disease. With the rise of foundation models, an open question is how they compare to traditional methods for brain signal forecasting and causality analysis, and whether they can be applied in a zero-shot setting. In this work, we evaluate a foundation model against classical methods for inferring directional interactions from spontaneous brain activity measured with functional magnetic resonance imaging (fMRI) in humans. Traditional approaches often rely on Wiener-Granger causality. We tested the forecasting ability of the foundation model in both zero-shot and fine-tuned settings, and assessed causality by comparing Granger-like estimates from the model with standard Granger causality. We validated the approach using synthetic time series generated from ground-truth causal models, including logistic map coupling and Ornstein-Uhlenbeck processes. The foundation model achieved competitive zero-shot forecasting fMRI time series (mean absolute percentage error of 0.55 in controls and 0.27 in patients). Although standard Granger causality did not show clear quantitative differences between models, the foundation model provided a more precise detection of causal interactions. Overall, these findings suggest that foundation models offer versatility, strong zero-shot performance, and potential utility for forecasting and causal discovery in time-series data.

Problem

• Evaluating foundation models for fMRI time-series forecasting
• Comparing zero-shot and fine-tuned causality analysis methods
• Assessing directional interaction detection in neural activity

Innovation

• Zero-shot time-series foundation model
• Competitive fMRI forecasting accuracy
• Precise causal interaction detection