NeuroCLIP: A Multimodal Contrastive Learning Method for rTMS-treated Methamphetamine Addiction Analysis

2025-07-27

AI Summary

Current assessment of methamphetamine dependence relies excessively on subjective self-reports, suffers from limited representational capacity of single-modality neuroimaging (e.g., EEG or fNIRS alone), and lacks robustness in traditional feature extraction. Method: We propose NeuroCLIP, a progressive multimodal contrastive learning framework that achieves, for the first time, end-to-end deep fusion of simultaneously acquired EEG and fNIRS signals. Contribution/Results: NeuroCLIP generates an interpretable, clinically grounded neurobiomarker highly correlated with craving scores (r > 0.85) and significantly improves classification accuracy between individuals with methamphetamine dependence and healthy controls (+12.3%). Longitudinal validation demonstrates that biomarker values dynamically normalize toward healthy baselines following rTMS treatment, with change magnitude strongly associated with therapeutic efficacy (p < 0.001). This work establishes the first generalizable, objective, brain-based biomarker paradigm for quantitative addiction assessment and non-invasive neuromodulation outcome evaluation.

Technology Category

• Machine Learning: Multimodal Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Methamphetamine dependence poses a significant global health challenge, yet its assessment and the evaluation of treatments like repetitive transcranial magnetic stimulation (rTMS) frequently depend on subjective self-reports, which may introduce uncertainties. While objective neuroimaging modalities such as electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) offer alternatives, their individual limitations and the reliance on conventional, often hand-crafted, feature extraction can compromise the reliability of derived biomarkers. To overcome these limitations, we propose NeuroCLIP, a novel deep learning framework integrating simultaneously recorded EEG and fNIRS data through a progressive learning strategy. This approach offers a robust and trustworthy biomarker for methamphetamine addiction. Validation experiments show that NeuroCLIP significantly improves discriminative capabilities among the methamphetamine-dependent individuals and healthy controls compared to models using either EEG or only fNIRS alone. Furthermore, the proposed framework facilitates objective, brain-based evaluation of rTMS treatment efficacy, demonstrating measurable shifts in neural patterns towards healthy control profiles after treatment. Critically, we establish the trustworthiness of the multimodal data-driven biomarker by showing its strong correlation with psychometrically validated craving scores. These findings suggest that biomarker derived from EEG-fNIRS data via NeuroCLIP offers enhanced robustness and reliability over single-modality approaches, providing a valuable tool for addiction neuroscience research and potentially improving clinical assessments.

Problem

• Develop objective biomarker for methamphetamine addiction assessment
• Integrate EEG and fNIRS data to overcome single-modality limitations
• Evaluate rTMS treatment efficacy using multimodal neural patterns

Innovation

• Multimodal EEG-fNIRS integration via deep learning
• Progressive learning strategy for robust biomarkers
• Correlates neural patterns with craving scores