We use multidimensional data from automated monitoring systems and milking systems to predict disorders of dairy cows by employing eight machine learning algorithms. The data included the season, days in milking, parity, age at the time of disorders, milk yield (kg/day), activity (unitless), six variables related to rumination time, and two variables related to the electrical conductivity of milk. We analyze 131 sick cows and 149 healthy cows with identical lactation days and parity; all data are collected on the same day, which corresponds to the diagnosis day for disordered cows. For disordered cows, each variable, except the ratio of rumination time from daytime to nighttime, displays a decreasing/increasing trend from d-7 or d-3 to d0 and/or d-1, with the d0, d-1, or d-2 values reaching the minimum or maximum. The test data sensitivity for three algorithms exceeded 80%, and the accuracies of the eight algorithms ranged from 65.08% to 84.21%. The area under the curve (AUC) of the three algorithms was >80%. Overall, Rpart best predicts the disorders with an accuracy, precision, and AUC of 81.58%, 92.86%, and 0.908, respectively. The machine learning algorithms may be an appropriate and powerful decision support and monitoring tool to detect herds with common health disorders.
The objective of this study was to analyze data on physical activity and rumination time monitored via collars at the farm coupled with milk yield recorded by the rotary milking system to predict cows based on several disorders using the binary Logistic regression conducted with R software. Data for metritis (n=60), mastitis (n=98), lameness (n=35), and digestive disorders (n=52) were collected from 1,618 healthy cows used to construct the prediction model. To verify the feasibility and adaptability of the proposed method, we analyzed data of cows in the same herd (herd 1) not used to construct the model, and cows in another herd (herd 2) with data recorded by the same type of automated system, and led to detection of 75.0%, 64.2%, 74.2%, and 76.9% animals in herd 1 correctly predicted to suffer from metritis, mastitis, lameness, and digestive disorders, respectively. For cows in herd 2, 66.6%, 58.8%, 80.7%, and 71.4% were correctly predicted for metritis, mastitis, lameness, and digestive disorders, respectively. Compared with traditional clinical diagnoses by farm personnel, the algorithm developed allowed for earlier prediction of cows with a disorder.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.