Unlocking the power of quantum computing in biomedical NLP for lung cancer diagnosis
Abstract
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.
Read the paper
Related studies
- In silico toxicology protocols
- QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
- Quantum Informed Machine-Learning Potentials for Molecular Dynamics Simulations of CO2's Chemisorption and Diffusion in Mg-MOF-74
- In-silico strategies in nano-drug design: Bridging nanomaterials and pharmacological applications
- mRNA codon optimization with quantum computers
- The computational power of the human brain
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.