Lung cancer remains the leading cause of cancer-related mortality worldwide, underscoring the urgent need for accurate, efficient, and interpretable early detection methods. Existing benchmark large language models (LLMs) like ClinicalBERT and BioBERT, despite their advancements in biomedical text analysis, face critical limitations including high computational costs, limited interpretability, and reliance on extensive annotated datasets hindering their clinical integration. To address these challenges, we propose the Hybrid Attention Quantum Long Short-Term Memory-Attention (A-QLSTM-A) model, a novel quantum-classical framework that combines quantum variational circuits with LSTM networks and dual attention mechanisms. This design enhances feature extraction, improves interpretability, and offers a more efficient architectural pathway. Evaluated on MIMIC-III discharge summaries and MIMIC-IV chest radiography reports, A-QLSTM-A achieved 98.32% and 83.67% accuracy, respectively, surpassing existing models. This study establishes a new benchmark for scalable, interpretable AI in precision medicine, offering a promising tool for early lung cancer detection and clinical decision support.
Kesiku et al. (Wed,) studied this question.