Foundation-Model-Boosted Multimodal Learning for fMRI-based Neuropathic Pain Drug Response Prediction

2025-02-28

AI Summary

Clinical fMRI data for predicting pharmacological response in neuropathic pain is severely limited. Method: We propose a dual-modality learning framework enhanced by an fMRI foundation model, jointly modeling resting-state fMRI time series and functional connectivity features. It enables knowledge synergy between pain-specific small-scale clinical data and large-scale non-pain fMRI datasets via cross-task knowledge transfer and cross-dataset representation alignment. Contribution/Results: To our knowledge, this is the first work to adapt an fMRI foundation model to drug response prediction, supporting both fine-tuning and interpretable analysis (e.g., gradient-weighted class activation mapping). Evaluated on our institutional cohort and OpenNeuro datasets, our method significantly outperforms unimodal baselines—achieving a 12.6% absolute improvement in prediction accuracy—and demonstrates enhanced cross-site generalizability. This establishes a novel paradigm for precision patient stratification and clinical trial optimization in neuropathic pain.

Technology Category

• Machine Learning: Multimodal Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Neuropathic pain, affecting up to 10% of adults, remains difficult to treat due to limited therapeutic efficacy and tolerability. Although resting-state functional MRI (rs-fMRI) is a promising non-invasive measurement of brain biomarkers to predict drug response in therapeutic development, the complexity of fMRI demands machine learning models with substantial capacity. However, extreme data scarcity in neuropathic pain research limits the application of high-capacity models. To address the challenge of data scarcity, we propose FMM$_{TC}$, a Foundation-Model-boosted Multimodal learning framework for fMRI-based neuropathic pain drug response prediction, which leverages both internal multimodal information in pain-specific data and external knowledge from large pain-agnostic data. Specifically, to maximize the value of limited pain-specific data, FMM$_{TC}$ integrates complementary information from two rs-fMRI modalities: Time series and functional Connectivity. FMM$_{TC}$ is further boosted by an fMRI foundation model with its external knowledge from extensive pain-agnostic fMRI datasets enriching limited pain-specific information. Evaluations with an in-house dataset and a public dataset from OpenNeuro demonstrate FMM$_{TC}$'s superior representation ability, generalizability, and cross-dataset adaptability over existing unimodal fMRI models that only consider one of the rs-fMRI modalities. The ablation study validates the effectiveness of multimodal learning and foundation-model-powered external knowledge transfer in FMM$_{TC}$. An integrated gradient-based interpretation study explains how FMM$_{TC}$'s cross-dataset dynamic behaviors enhance its adaptability. In conclusion, FMM$_{TC}$ boosts clinical trials in neuropathic pain therapeutic development by accurately predicting drug responses to improve the participant stratification efficiency.

Problem

• Predicts drug response for neuropathic pain using fMRI.
• Addresses data scarcity in neuropathic pain research.
• Enhances clinical trial efficiency through accurate predictions.

Innovation

• Leverages multimodal fMRI data for pain prediction
• Integrates external knowledge from large datasets
• Enhances drug response prediction accuracy