Application of a short-wave pocket-sized near-infrared spectrophotometer to predict milk quality traits

Portable handheld devices based on near-infrared (NIR) technology have improved and are gaining popularity, even if their implementation in milk has been barely evaluated. Thus, the aim of the present study was to assess the feasibility of using short-wave pocket-sized NIR devices to predict milk quality. A total of 331 individual milk samples from different cow breeds and herds were collected in 2 consecutive days for chemical determination and spectral collection by using 2 pocket-sized NIR spectrophotometers working in the range of 740 to 1,070 nm. The reference data were matched with the corresponding spectrum and modified partial least squares regression models were developed. A 5-fold cross-validation was applied to evaluate individual device performance and an external validation with 25% of the dataset as the validation set was applied for the final models. Results revealed that both devices' absorbance was highly correlated but greater for instrument A than B. Thus, the final models were built by averaging the spectra from both devices for each sample. The fat content prediction model was adequate for quality control with a coefficient of determination (R ² _ExV) and a residual predictive deviation (RPD _ExV) in external validation of 0.93 and 3.73, respectively. Protein and casein content as well as fat-to-protein ratio prediction models might be used for a rough screening (R ² _ExV >0.70; RPD _ExV >1.73). However, poor prediction models were obtained for all the other traits with an R ² _ExV between 0.43 (urea) and 0.03 (SCC), and a RPD _ExV between 1.18 (urea) and 0.22 (SCC). In conclusion, short-wave portable handheld NIR devices accurately predicted milk fat content, and protein, casein, and fat-to-protein ratio might be applied for rough screening. It seems that there is not enough information in this NIR region to develop adequate prediction models for lactose, SCC, urea, and freezing point.