RESUMO
BACKGROUND: Contamination of milk by antibiotic residues represents risks to the health of consumers; therefore they should be monitored. The objective of this study was to propose a methodology for the determination of tylosin residues directly in fluid milk based on mid-infrared spectroscopy associated with chemometrics, using attenuated total reflection Fourier transform infrared (ATR-FTIR) spectroscopy associated with multilayer perceptron network (MLP) and partial least squares (PLS). RESULTS: MLP was shown to be adequate for the discrimination of milk samples contaminated with tylosin below or equal to or above the maximum residue limit (MRL), with an accuracy greater than 99%, using FTIR spectra data. PLS was shown to be appropriate for the prediction of the very low concentrations (0-100 µg L-1 ) of tylosin residues in milk using FTIR spectra data. PLS models with high correlation coefficients (R > 0.99) were generated. CONCLUSION: FTIR with chemometrics proved to be a non-destructive, efficient and low-cost method for the investigation and quantification of tylosin residues directly in fluid milk. © 2020 Society of Chemical Industry.