Artificial intelligence, omics, and biomarkers: Redefining lung cancer early detection

Lung cancer, the leading cause of death worldwide, claims millions of lives yearly, largely due to limited early interventions. Currently used lung cancer screening methods are still limited in their reach and accuracy due to invasiveness, radiation exposure, and low sensitivity, especially in early stages, necessitating the need for innovative technologies. This review examines emerging tools for the early detection of lung cancer, utilizing biomarkers in conjunction with omics approaches and AI technology, which could significantly impact its clinical landscape. Tumor cells release specific biological indicators called biomarkers, which can be cellular components, nucleic acid fragments, protein fragments, or metabolites, detected from bodily fluids through non-invasive methods. The integration of biomarkers with omics technologies (such as proteomics and genomics) or multi-omics provides a comprehensive insight into the molecular profiles of various cancer subtypes and stages. Artificial intelligence, including machine learning and deep learning tools, further increases the accuracy and precision of these techniques. However, challenges still persist in its clinical translation, including technical limitations, regulatory hurdles and ethical concerns. Overcoming these limitations requires standardised protocols, interdisciplinary collaborations, and strategies for equitable access to innovative technologies. Novel, cutting-edge technological interventions, such as advanced imaging techniques, sensor technology, nanotechnology, breathomics, and microbiome analysis, have the potential to enhance early lung cancer diagnosis, ultimately improving patient outcomes and reducing the global burden of this disease.