A new era of precision diagnosis and treatment for lung cancer: artificial intelligence-driven multimodal data integration and clinical applications.
Authors
Affiliations (4)
Affiliations (4)
- Department of Radiotherapy and Oncology, Affiliated Kunshan Hospital of Jiangsu University, Kunshan, China. [email protected].
- Department of Oncology, Jingjiang People's Hospital Affiliated with Yangzhou University, Jingjiang, China.
- Department of Radiotherapy and Oncology, Affiliated Kunshan Hospital of Jiangsu University, Kunshan, China.
- Department of Radiotherapy and Oncology, Affiliated Kunshan Hospital of Jiangsu University, Kunshan, China. [email protected].
Abstract
Certain characteristics, such as high heterogeneity, a complex tumor microenvironment, metastatic potential, and drug resistance, render Lung cancer (LC) a formidable challenge for clinical management. With rapid advancements in high-throughput sequencing, medical imaging, and digital pathology technologies, significant amounts of high-dimensional and heterogeneous multimodal data are now being generated. Traditional methods cannot comprehensively elucidate the intrinsic patterns within these multi-omics data, thereby limiting a comprehensive understanding of the biological characteristics of LC. Artificial intelligence (AI) technologies provide powerful computational frameworks for integrating such multi-scale and heterogeneous data. Through cross-modal data integration, AI enables the construction of a panoramic disease atlas ranging from microscopic molecular variations to macroscopic imaging phenotypes. This narrative review aims to systematically discuss the prospects of AI-driven multimodal data fusion in LC research and clinical applications. Our review highlights the potential clinical applications of integrating AI with multi-omics technologies in areas such as early screening, prognostic risk assessment, precision treatment, drug sensitivity analysis, and guiding personalized surgical plans. Against the backdrop of continuous advancements in AI research, we further discuss the main obstacles in translating AI-based multi-omics from research to clinical practice and propose strategic and actionable approaches to promote rapid development in this field.