The development of an electrochemical sensor for antibiotics in milk based on machine learning algorithms

TL;DR

This study develops an electrochemical sensor combined with machine learning to detect antibiotic residues in milk, achieving high accuracy and potential for on-site dairy farm monitoring.

Contribution

It introduces a novel multielectrode sensor integrated with machine learning for rapid, accurate antibiotic detection in milk, combining electrochemical analysis with molecular modeling.

Findings

High accuracy in antibiotic recognition in milk

Gradient boosting algorithm outperformed other models

Sensor design enables potential on-site dairy monitoring

Abstract

Present study is dedicated to the problem of electrochemical analysis of multicomponent mixtures such as milk. A combination of cyclic voltammetry facilities and machine learning technique made it possible to create a pattern recognition system for antibiotic residues in skimmed milk. A multielectrode sensor including copper, nickel and carbon fiber was fabricated for the collection of electrochemical data. Chemical aspects of processes occurring at the electrode surface were discussed and simulated with the help of molecular docking and density functional theory modelling. It was assumed that the antibiotic fingerprint reveals as potential drift of electrodes owing to redox degradation of antibiotic molecules followed by pH change or complexation with ions present in milk. Gradient boosting algorithm showed the best efficiency towards training the machine learning model. High accuracy was achieved for recognition of antibiotics in milk. The elaborated method may be incorporated into existing milking systems at dairy farms for monitoring the residue concentrations of antibiotics.