Learning from Limited and Incomplete Data: A Multimodal Framework for Predicting Pathological Response in NSCLC

2026-03-16

AI Summary

This study addresses the challenge of preoperative prediction of major pathological response (pR) to neoadjuvant therapy in non-small cell lung cancer, which is hindered by sparse and frequently missing clinical data. To overcome this limitation, the authors propose a multimodal deep learning framework that leverages foundation models to extract features from CT imaging and introduces a missingness-aware neural network to directly model incomplete clinical variables, thereby circumventing conventional imputation strategies. A learnable weighted fusion mechanism is employed to effectively integrate information from multiple sources. Evaluated in real-world clinical settings with limited sample sizes, the proposed method significantly outperforms unimodal baselines, demonstrating the efficacy and robustness of the missingness-aware architecture and multimodal fusion strategy.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

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

Abstract

Major pathological response (pR) following neoadjuvant therapy is a clinically meaningful endpoint in non-small cell lung cancer, strongly associated with improved survival. However, accurate preoperative prediction of pR remains challenging, particularly in real-world clinical settings characterized by limited data availability and incomplete clinical profiles. In this study, we propose a multimodal deep learning framework designed to address these constraints by integrating foundation model-based CT feature extraction with a missing-aware architecture for clinical variables. This approach enables robust learning from small cohorts while explicitly modeling missing clinical information, without relying on conventional imputation strategies. A weighted fusion mechanism is employed to leverage the complementary contributions of imaging and clinical modalities, yielding a multimodal model that consistently outperforms both unimodal imaging and clinical baselines. These findings underscore the added value of integrating heterogeneous data sources and highlight the potential of multimodal, missing-aware systems to support pR prediction under realistic clinical conditions.

Problem

• pathological response
• non-small cell lung cancer
• limited data
• incomplete clinical data
• preoperative prediction

Innovation

• multimodal learning
• missing-aware architecture
• foundation model
• pathological response prediction
• limited data