Validation of a Microfluidic Device Prototype for Cancer Detection and Identification: Circulating Tumor Cells Classification Based on Cell Trajectory Analysis Leveraging Cell-Based Modeling and Machine Learning.

Early detection is currently the most effective method to combat cancer, as it maximizes treatment options and improves potential survival rates. However, the cost of early detection presents a significant barrier, limiting access for underrepresented groups and discouraging industrial partners from investing in the research and development of screening devices. This study provides an in-silico conceptual validation for the development of an innovative hyperuniform microchip designed to identify circulating tumor cells (CTCs) without the need for biomarker labeling. We created a cell-based modeling framework to examine CTC dynamics in erythrocyte-laden plasma flow, producing an extensive dataset of CTC trajectories that reflect two distinct CTC phenotypes. Two machine learning architectures were utilized to analyze this dataset and classify the phenotypes. The results demonstrate the potential effectiveness of the hyperuniform micropost MD design and analysis approach in distinguishing between different CTC phenotypes based on cell trajectory, offering a promising and cost-effective method for early cancer detection.