A Low-Cost and Sensitive Nanoengineered Electrochemical Biosensor for Early Pancreatic Cancer Prediction: Methodology and ML Models

Abstract In the United States, pancreatic cancer ranks in third place amongst all cancers, with a very low survival rate of 20%, which drops to 9% after five years. Alarmingly, it is anticipated that by 2030, it will become the second-leading cause of cancer-related fatalities in the US, surpassing lung cancer. Conventional diagnostic procedures for clinical testing are expensive, invasive, and include radiation-intensive biopsies. The manuscript presents a preliminary methodology/protocol for using an electrochemical biosensor to target CA 19-9, a critical biomarker for pancreatic tumors, to address the urgent need for affordable, non-invasive diagnostic methods. Leveraging the unique properties of graphene oxide, owing to its high surface area and excellent sensitivity and specificity, we developed a nanoengineered biosensor by surface functionalizing the gold electrode for early CA 19-9 detection using electrochemical analysis, resulting in improved accuracy. This developed sensor, integrated with machine learning algorithms, enhances diagnostic accuracy, specificity, and predictive capabilities by combining nanotechnology with advanced data analytics. Upon binding with the target protein, the gold, graphene oxide-coated, and graphene sensor sensors had a change in impedance (∆ Z ) values of 12,700, 37,000, and 34,000 Ω/cm 2 , respectively. Our results demonstrated that graphene-based electrochemical biosensors offer significant advantages over traditional carbon- or gold-based sensors, showing strong potential as reliable, user-friendly, and cost-effective tools for the early detection of pancreatic cancer. However, further studies are required to optimize the parameters and validate the sensor with patient samples more effectively. Graphical abstract