Infrared spectroscopy combined with random forest to determine tylosin residues in powdered milk

• Random Forest and Boruta showed suitability for calibration purpose with FTIR data. • Absorption bands related to milk contamination were identified with Boruta algorithm. • FTIR and Random Forest allow analysis antibiotic residues directly in powdered milk. • The regression model showed good ability to predict tylosin concentration in milk. • The proposed methodology is non-destructive, fast, efficient and of low cost. The contamination of milk by antibiotic residues is a worldwide health and food safety problem. There is a need to develop new methods for the rapid determination of antibiotic residues in milk. A method has been developed for determining tylosin residues directly in powdered milk using Fourier Transformed Infrared spectroscopy (FTIR). Tylosin is a broad-spectrum macrolide antibiotic. The spectra obtained were submitted to chemometric analysis to obtain a prediction model for tylosin concentration in powdered milk. Using the Boruta algorithm, the absorption bands related to the milk contamination by the antibiotic were identified. Random forest was shown to be adequate for the prediction of tylosin residues in milk at low concentrations (≤ 100 μg L -1 ) and the prediction model generated showed high correlation and determination coefficients (greater than 0.95). The proposed methodology proved to be efficient for the investigation of antibiotic residues in powdered milk.