LLM Augmented Intervenable Multimodal Adaptor for Post-operative Complication Prediction in Lung Cancer Surgery

2026-01-20

AI Summary

This study addresses the critical need for accurate prediction of postoperative complications in lung cancer surgery to improve patient outcomes and reduce healthcare costs. To this end, the authors propose an interpretable, multimodal deep learning framework that integrates preoperative structured clinical data with high-dimensional imaging features. Efficient feature alignment is achieved through a hyperspherical embedding space, while an expert-interactable intervention module enhances model interpretability by allowing clinicians to adjust predictions based on domain knowledge. Furthermore, a large language model–enhanced mechanism is incorporated to strengthen clinical semantic understanding. Evaluated on POC-L, a real-world dataset comprising 3,094 patients, the proposed method significantly outperforms conventional machine learning approaches and existing large language model variants, delivering high-performance, personalized, and clinically actionable risk prediction.

Technology Category

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

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Postoperative complications remain a critical concern in clinical practice, adversely affecting patient outcomes and contributing to rising healthcare costs. We present MIRACLE, a deep learning architecture for prediction of risk of postoperative complications in lung cancer surgery by integrating preoperative clinical and radiological data. MIRACLE employs a hyperspherical embedding space fusion of heterogeneous inputs, enabling the extraction of robust, discriminative features from both structured clinical records and high-dimensional radiological images. To enhance transparency of prediction and clinical utility, we incorporate an interventional deep learning module in MIRACLE, that not only refines predictions but also provides interpretable and actionable insights, allowing domain experts to interactively adjust recommendations based on clinical expertise. We validate our approach on POC-L, a real-world dataset comprising 3,094 lung cancer patients who underwent surgery at Roswell Park Comprehensive Cancer Center. Our results demonstrate that MIRACLE outperforms various traditional machine learning models and contemporary large language models (LLM) variants alone, for personalized and explainable postoperative risk management.

Problem

• postoperative complications
• lung cancer surgery
• risk prediction
• multimodal data
• clinical decision support

Innovation

• intervenable deep learning
• hyperspherical embedding
• multimodal fusion
• postoperative complication prediction
• LLM-augmented adaptor