Lung cancer is the leading cause of cancer-related mortality worldwide, accounting for approximately 1.8 million deaths annually. A major challenge in reducing lung cancer mortality is the lack of reliable, rapid, and affordable screening tools capable of detecting the disease at an early stage. Unlike breast cancer, which benefits from routine screening programs, lung cancer is often diagnosed only after symptoms appear, resulting in delayed treatment and poor patient outcomes. Current diagnostic approaches, including imaging and biopsy, are costly, invasive, and unsuitable for routine population screening, while emerging biosensor technologies remain largely confined to research laboratories.

This project aims to develop a next-generation machine learning-assisted molecularly imprinted polymer (MIP)-based electrochemical sensor for the detection of lung cancer biomarkers, enabling rapid, sensitive, and highly selective detection for early diagnosis and prognosis.

To achieve high analytical performance, molecularly imprinted polymers will be synthesized as artificial recognition elements, offering excellent stability, selectivity, and cost-effectiveness compared with conventional antibodies. Machine learning algorithms will be employed to optimize MIP formulation and fabrication parameters, enabling the selection of the best-performing sensor designs while reducing experimental time and cost. The developed technology can subsequently be extended to a multiplex sensor capable of simultaneously detecting additional lung cancer biomarkers to improve diagnostic accuracy, cancer staging, and metastasis assessment. The proposed platform has the potential to provide a rapid, affordable, and clinically translatable point-of-care diagnostic tool, significantly improving early lung cancer detection and patient survival.