Use of Multivariate Adaptive Regression Splines, Classification Trees and ROC Curve in Diagnosis of Subclinical Mastitis in Dairy Cattle

Subclinical mastitis is one of the most significant diseases that cause economic losses in dairy cattle farming. This research was conducted on 112 heads of Holstein Friesian dairy cattle to reveal the relationship between subclinical mastitis and milk composition and milk quality.In the study, CMT (California Mastitis Test) and CSCC (Classified Somatic Cell Count) used in the diagnosis of subclinical mastitis were used as a binary response variable i.e. healthy and unhealthy. Potential predictors included here were lactation number, days in milk (DIM), darkness-lightness ranges between 0=black and 100=white (L*), green-red ranges between - a*=-60 and a*=+60 (a*), blue-yellow ranges between -b*=-60 and b*=+60 (b*), redness-yellowness (Hue degrees), vividness-dullness (Chroma), milk fat, milk protein, lactose, milk freezing point, solid non-fat SNF, density, solids, pH, and electrical conductivity. Classification and Regression Tree (CART), Chi-Squared Automatic Interaction Detection (CHAID), Exhaustive Chi-Squared Automatic Interaction Detection (Ex-CHAID), Quick, Unbiased, Efficient, Statistical Tree (QUEST), and multivariate adaptive regression splines (MARS) were used as data mining algorithms that help to make an accurate decision about detecting influential factors increasing the risk of subclinical mastitis. In conclusion, better classification performances of CART and MARS data mining algorithms were determined compared with those of the remaining algorithms to correctly discriminate between healthy and unhealthy cows.