MEXA-CTP: Mode Experts Cross-Attention for Clinical Trial Outcome Prediction

2025-01-12

AI Summary

To address the reliance on wet-lab data and manual prior knowledge, as well as insufficient fusion of multi-source heterogeneous information in clinical trial outcome prediction, this paper proposes a lightweight cross-modal attention model. Methodologically, it introduces a novel modular “modality expert” architecture that jointly encodes drug representations (via graph neural networks), disease descriptions, and eligibility criteria (via text encoders), integrates inter-modality cross-attention, and employs the Cauchy loss to explicitly model critical cross-modal interactions—thereby mitigating human encoding bias. On the TOP benchmark, the model achieves absolute improvements of 11.3% in F1, 12.2% in PR-AUC, and 2.5% in ROC-AUC over state-of-the-art methods including HINT. Its core contributions are: (1) an end-to-end multimodal fusion paradigm that requires neither wet-lab data nor handcrafted expert rules; and (2) an interpretable, low-bias mechanism for modeling cross-modal interactions.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Clinical trials are the gold standard for assessing the effectiveness and safety of drugs for treating diseases. Given the vast design space of drug molecules, elevated financial cost, and multi-year timeline of these trials, research on clinical trial outcome prediction has gained immense traction. Accurate predictions must leverage data of diverse modes such as drug molecules, target diseases, and eligibility criteria to infer successes and failures. Previous Deep Learning approaches for this task, such as HINT, often require wet lab data from synthesized molecules and/or rely on prior knowledge to encode interactions as part of the model architecture. To address these limitations, we propose a light-weight attention-based model, MEXA-CTP, to integrate readily-available multi-modal data and generate effective representations via specialized modules dubbed"mode experts", while avoiding human biases in model design. We optimize MEXA-CTP with the Cauchy loss to capture relevant interactions across modes. Our experiments on the Trial Outcome Prediction (TOP) benchmark demonstrate that MEXA-CTP improves upon existing approaches by, respectively, up to 11.3% in F1 score, 12.2% in PR-AUC, and 2.5% in ROC-AUC, compared to HINT. Ablation studies are provided to quantify the effectiveness of each component in our proposed method.

Problem

• Clinical Trial Prediction
• Multi-source Information Integration
• Drug Development Efficiency

Innovation

• Cross-attention Mechanism
• Cauchy Loss
• Clinical Trial Prediction