LUNG-KGMM: Knowledge-Guided Multimodal Learning for Lung Cancer Incidence Prediction
Summary
The paper proposes LUNG-KGMM, a knowledge-guided multimodal framework for predicting lung cancer incidence by integrating EHR, radiology data, and clinical guidelines, demonstrating superior performance on the MIMIC dataset and real-world validation.
View Cached Full Text
Cached at: 08/18/26, 10:22 AM
# LUNG-KGMM: Knowledge-Guided Multimodal Learning for Lung Cancer Incidence Prediction Source: [https://arxiv.org/abs/2608.14657](https://arxiv.org/abs/2608.14657) [View PDF](https://arxiv.org/pdf/2608.14657) > Abstract:Early identification of lung cancer risk is critical for timely intervention, yet existing prediction models are limited by their reliance on single data modalities and their inability to leverage structured clinical knowledge\. We propose LUNG\-KGMM, a knowledge\-guided multimodal framework that integrates longitudinal electronic health records, radiology reports, chest radiograph representations, and guideline\-derived knowledge for 1\-to\-6\-year incident lung cancer prediction\. To address modality heterogeneity and potential data leakage, we develop a leakage\-sanitized report processing pipeline and a horizon\-masked cumulative training objective that handles incomplete follow\-up\. We further introduce a knowledge\-graph representation of clinical guidance that encodes report\-triggered finding\-attribute\-action relations as an auditable knowledge stream\. We build a multimodal development cohort from the publicly available MIMIC databases and construct a real\-world validation cohort from the Xiamen Medical Big Data Platform\. Extensive experiments on the MIMIC cohort demonstrate that LUNG\-KGMM achieves superior performance over state\-of\-the\-art methods, and validation on the Xiamen cohort further characterizes its cross\-cohort portability and the need for local adaptation\. The MIMIC development cohort is publicly accessible; the Xiamen cohort is governed by local data privacy regulations\. ## Submission history From: Zhong Cao \[[view email](https://arxiv.org/show-email/12308478/2608.14657)\] **\[v1\]**Fri, 31 Jul 2026 10:34:41 UTC \(4,821 KB\)
Similar Articles
Lung-R1: A Knowledge Graph-Guided LLM for Pulmonary Diagnostic Reasoning
The paper introduces LungKG, the first structured pulmonary knowledge graph, and Lung-R1, a LLM trained via KG-constrained reasoning and reinforcement learning for pulmonary diagnostic reasoning from EMRs. Lung-R1-14B achieves state-of-the-art performance on EMR diagnosis.
Multi-Modal Machine Learning for Breast Cancer Recurrence Prediction
This paper examines the integration of multi-modal clinical data, including treatment records, pathology reports, and clinician notes, using rule-based extraction and machine learning to improve breast cancer recurrence prediction compared to single-modal approaches.
Patients-like-me: A Variational LM--GNN Framework for Explainable Clinical Prediction
This paper proposes Patients-like-me (PLM), a unified LM–GNN framework that integrates local patient semantics with global cohort structure for explainable clinical prediction. It introduces a Variational Expectation-Maximization algorithm and demonstrates state-of-the-art results on MIMIC-III and MIMIC-IV with reference-patient explanations.
Large Language Models as Unified Multimodal Learners for Clinical Prediction
The paper proposes converting multimodal patient data (text, labs, vitals) into a single natural language sequence and fine-tuning LLMs for clinical prediction, achieving comparable or better performance than specialized fusion architectures across three tasks.
Primary ICD Category Prediction using LLM-based Probing
This paper presents a method that uses frozen medical large language model (LLM) representations as a shared embedding space to predict primary ICD diagnosis categories from both structured and unstructured electronic health record data, achieving improved accuracy over baseline methods on MIMIC-IV and showing transferability to MIMIC-III.