Converging Multidimensional Sensor and Machine Learning Toward High-Throughput and Biorecognition Element-Free Multidetermination of Extracellular Vesicle Biomarkers

Extracellular vesicles (EVs) are a frontier class of circulating biomarkers for the diagnosis and prognosis of different diseases. These lipid structures afford various biomarkers such as the concentrations of the EVs (C_V) themselves and carried proteins (C_P). However, simple, high-throughput, and accurate determination of these targets remains a key challenge. Herein, we address the simultaneous monitoring of C_V and C_P from a single impedance spectrum without using recognizing elements by combining a multidimensional sensor and machine learning models. This multidetermination is essential for diagnostic accuracy because of the heterogeneous composition of EVs and their molecular cargoes both within the tumor itself and among patients. Pencil HB cores acting as electric double-layer capacitors were integrated into a scalable microfluidic device, whereas supervised models provided accurate predictions, even from a small number of training samples. User-friendly measurements were performed with sample-to-answer data processing on a smartphone. This new platform further showed the highest throughput when compared with the techniques described in the literature to quantify EVs biomarkers. Our results shed light on a method with the ability to determine multiple EVs biomarkers in a simple and fast way, providing a promising platform to translate biofluid-based diagnostics into clinical workflows.