Transformer-Enhanced Joint Information Extraction Framework for Bladder Cancer Medical Dialogue Analysis

Bladder cancer diagnosis and treatment monitoring through medical dialogues present unique information extraction requirements that traditional single-task approaches struggle to address effectively. Extracting ac curate clinical information from patient-physician conversations about bladder cancer involves recognizing subtle symptom descriptions, understanding treatment responses, and capturing disease progression indicators that may be scattered across extended dialogue sequences. Bladder cancer transformer for joint information extraction (BCT-JIE) addresses these requirements through a collaborative transformer architecture that simultaneously performs entity recognition, intent classification, and clinical state assessment within bladder cancer medical dialogues. The framework employs a sliding window mechanism combined with bidirectional long short-term memory networks to capture historical dialogue context, while utilizing a symptom-aware module to identify bladder cancer specific clinical indicators. Global attention mechanisms enhance the model's ability to understand relationships between urological symptoms and their clinical manifestations across extended conversation sequences. Interactive guidance modules explicitly model the interdependencies between symptom extraction, treatment intent recognition, and disease progression assessment tasks, enabling more accurate information capture for bladder cancer management. Experimental validation on MedDialog and Multi MedQA datasets demonstrates superior performance compared to baseline approaches, with notable improvements in bladder cancer-specific entity extraction and clinical state classification accuracy, achieving 91.76% F1-score in symptom entity extraction and 83.42% accuracy in staging classification. Ablation studies with five-fold repetition con firm that both the sliding window mechanism and global attention module contribute reliably to extraction performance across all tasks.