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

SIMPLE SUMMARY: Monitoring health status and disease outbreak among food animal herds is vitally important to global food safety. Affected animals will experience production losses, and in uncurable cases, operations will need to be modified or animals culled. Producers and veterinary personnel have consistent interest in new diagnostic tools to provide rapid, accurate, and simple testing strategies which do not undermine financial viability of the operation. This manuscript describes a new approach for diagnosis of mastitis in dairy animals. The new method involves first analyzing raw milk from animals by matrix-assisted laser desorption/ionization mass spectrometry and collecting mass spectra. Then, peaks from the mass spectra are imported into a machine learning model, and this software application discovers non-obvious patterns present in the data which coincide with the mastitis condition. Finally, a separate set of milk samples is analyzed (scoring set) to evaluate the diagnostic accuracy of the new model. Results suggest that certain machine learning models offer value to the producer for diagnosis of subclinical mastitis in dairy cows. More generally, the manuscript outlines use of the machine learning approach for diagnoses of animal disease, and we prophesize that this strategy may be applicable to a wide array of animal health concerns. ABSTRACT: Novel strategies for diagnostic screening of animal and herd health are crucial to contain disease outbreaks, maintain animal health, and maximize production efficiency. Mastitis is an inflammation of the mammary gland in dairy cows, often resulting from infection from a microorganism. Mastitis outbreaks result in loss of production, degradation of milk quality, and the need to isolate and treat affected animals. In this work, we evaluate MALDI-TOF mass spectrometry as a diagnostic for the culture-less screening of mastitis state from raw milk samples collected from regional dairies. Since sample preparation requires only minutes per sample using microvolumes of reagents and no cell culture, the technique is promising for rapid sample turnaround and low-cost diagnosis. Machine learning algorithms have been used to detect patterns embedded within MALDI-TOF spectra using a training set of 226 raw milk samples. A separate scoring set of 100 raw milk samples has been used to assess the specificity (spc) and sensitivity (sens) of the approach. Of machine learning models tested, the gradient-boosted tree model gave global optimal results, with the Youden index of J = 0.7, sens = 0.89, and spc = 0.81 achieved for the given set of conditions. Random forest models also performed well, achieving J > 0.63, with sens = 0.83 and spc = 0.81. Naïve Bayes, generalized linear, fast large-margin, and deep learning models failed to produce diagnostic results that were as favorable. We conclude that MALDI-TOF MS combined with machine learning is an alternative diagnostic tool for detection of high somatic cell count (SCC) and subclinical mastitis in dairy herds.