Multimodal LLM-Driven Intervention for Precision Risk Prediction in Lung Cancer Surgery

Abstract

This abstract presents a multimodal deep learning framework that integrates clinical variables, imaging-derived radiomic features, and large language model insights to predict postoperative complications in lung cancer surgery. The model generates editable, clinician-friendly risk summaries so that surgical experts can refine risk predictions in real time.

Publication
Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; Clinical Cancer Research 31(13 Suppl), Abstract A054, 2025