Simultaneous Quantification of Multiple Drugs by Machine Learning on Electrochemical Sensors

Electrochemical devices and systems are significant for the development of therapeutic drug monitoring (TDM) and personalized therapy. However, electrochemical sensors are usually not that much selective. Therefore, innovative machine learning (ML) approaches are now required to improve the selectivity at system level based on cyclic voltammograms (CV) obtained from electrochemical sensors in order to assure the quantification of several different drugs simultaneously present into the blood of patients. Based on an Artificial Neural Network (ANN), this paper proposes a novel model TwoWayANN along with an adaptive weighted cross-entropy loss (AWCEL) to address drugs interaction effectively and decline the quantification error range. The simulated dataset of etoposide (ETO) and methotrexate (MTX), proposed here as model drugs, is demonstrated to validate the efficacy of our proposed method. Our TwoWayANN model achieves the accuracy at 100% and 99.35% for ETO and MTX respectively within the error range of ±5μM. Our results are important for the development of point-of-care systems for applications in personalized therapy.