Automatic simulation of electrochemical sensors by machine learning for drugs quantification

Multiple drug concentrations concurrent detection and quantification based on electrochemical sensors are of great importance for therapeutic drug monitoring (TDM) and the development of personalized therapy. Cyclic voltammogram (CV) results obtained by electrochemical sensors can be used to offer quantitative information about drug concentrations. Several approaches have been proposed for single-concentration quantification based on CV results and Machine Learning (ML) models with lower training difficulty. However, insufficient measured dataset hinders the application of diverse large-scale ML algorithms in this field. A new method for automatic parameter estimation by ML of measured CV samples is here illustrated with the aim to generate a large simulated dataset for generalized drug concentration quantification model training in this paper. We present an ML-based approach that combines k-means clustering, polynomial regression, and Gaussian Mixture Model (GMM), which automates parameter estimation and simulation using peak detection, baseline subtraction, and peak Gaussian fitting with a small number of measurements. Large simulation datasets constructed on the basis of the estimation results open the possibility of training ML models for more generalized drug concentration quantification. The simulated dataset is processed to assess the efficiency of the proposed method. The Mean Average Percentage Error (MAPE) was 0.32% for etoposide (ETO) and 4.78% for methotrexate (MTX).