Diagnostic Screening of Bovine Mastitis Using MALDI-TOF MS Direct-Spotting of Milk and Machine Learning

Thompson J., Everhart Nunn S.L., Sarkar S., Clayton B. (2023). Diagnostic Screening of Bovine Mastitis Using MALDI-TOF MS Direct-Spotting of Milk and Machine Learning. Vet. Sci., 10(2), 101. https://doi.org/10.3390/vetsci10020101

This study evaluates the use of MALDI-TOF mass spectrometry (MS) combined with machine learning (ML) for rapid, culture-less screening of bovine mastitis. Using a training set of 226 milk samples, machine learning algorithms detected patterns within MALDI-TOF spectra, while a scoring set of 100 samples assessed diagnostic accuracy. The gradient-boosted tree model performed best, achieving a Youden index of 0.7, with 89% sensitivity and 81% specificity. This approach demonstrates potential as a cost-effective, efficient tool for diagnosing subclinical mastitis in dairy cows.