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.
@article{arxiv.2603.15100,
title = {Learning from Limited and Incomplete Data: A Multimodal Framework for Predicting Pathological Response in NSCLC},
author = {Alice Natalina Caragliano and Giulia Farina and Fatih Aksu and Camillo Maria Caruso and Claudia Tacconi and Carlo Greco and Lorenzo Nibid and Edy Ippolito and Michele Fiore and Giuseppe Perrone and Sara Ramella and Paolo Soda and Valerio Guarrasi},
journal= {arXiv preprint arXiv:2603.15100},
year = {2026}
}