Prediction of Streptococcus uberis clinical mastitis treatment success in dairy herds by means of mass spectrometry and machine-learning

Abstract

Streptococcus uberis is one of the leading pathogens causing mastitis worldwide. Identification of S. uberis strains that fail to respond to treatment with antibiotics is essential for better decision making and treatment selection. We demonstrate that the combination of supervised machine learning and matrix-assisted laser desorption ionization/time of flight (MALDI-TOF) mass spectrometry can discriminate strains of S. uberis causing clinical mastitis that are likely to be responsive or unresponsive to treatment. Diagnostics prediction systems trained on 90 individuals from 26 different farms achieved up to 86.2% and 71.5% in terms of accuracy and Cohen’s kappa. The performance was further increased by adding metadata (parity, somatic cell count of previous lactation and count of positive mastitis cases) to encoded MALDI-TOF spectra, which increased accuracy and Cohen’s kappa to 92.2% and 84.1% respectively. A computational framework integrating protein–protein networks and structural protein information to the machine learning results unveiled the molecular determinants underlying the responsive and unresponsive phenotypes.

How to Control the Increased Bulk Milk Somatic Cell Count in Dairy Cows

“…Environmental streptococci such as S. uberis and S. dysgalactiae show poor response when treated during lactation, and after possible treatment, the probability of infection returning is high. Therefore, their subclinical cases are not considered suitable for treatment [50]. Subclinical mastitis caused by Staphylococcus aureus causes a relatively persistent infection in the udder and increases the number of somatic cells to a moderate extent, and due to poor response to treatment during the lactation period; treated only in young cows, when of shorter duration of infection and lower SCC, days in milk less than 100, in non-chronic and repetitive and high producing cows [51,52].…”

“…In cases caused by Mycoplasma bovis, the number of somatic cells increases drastically, but the total number of bacteria in the bulk milk tank does not change. Its subclinical cases are not treated, and an attempt is made to cull or segregate affected cows [50].…”

Matrix-assisted laser desorption ionization-time-of-flight mass spectrometry in veterinary medicine: Recent advances (2019–present)

“…Every M. bovis isolate was correctly identified as M. bovis by the MALDI-TOF software, and none of the field isolates were misidentified as one of the other mycoplasmas present in the library, nor were the other mycoplasmas misidentified as M. bovis. Maciel-Guerra et al [27] used MALDI-TOF as a diagnostic tool for the prediction of positive treatment outcome for S. uberis infections in dairy herds. As influenced by the earlier work of Ebrahimi et al [118], this fascinating work uses MALDI-TOF data coupled with machine learning to identify patterns in datasets to improve diagnosis.…”