Automating classification of veterinary biosecurity recommendations using machine learning

ProAction® is a mandatory Canadian milk quality assurance program that requires dairy farmers to conduct a biosecurity risk assessment with a veterinarian. Based on this assessment, the veterinarian provides personalized recommendations to improve farm biosecurity, resulting in a large volume of text data. This study aimed to develop a machine learning model capable of automatically classifying these biosecurity recommendations into 12 predefined categories. As the recommendations were written in French or English, all texts were translated into French to ensure consistency in feature extraction and model training. The model was trained on 11,250 manually classified veterinary recommendations from 3,825 Québec dairy herds, collected between 2018 and 2021. Three algorithms were tested: Multinomial Naïve Bayes (MNB), Support Vector Machine (SVM), and Random Forest (RF). Performance was evaluated using precision, recall, and F1-score. The SVM achieved the highest performance while maintaining efficient processing time. The trained SVM model was selected to classify new recommendations collected between 2022 and 2024 from herds in Alberta, Ontario and Québec. To evaluate model’s performance on this new dataset, a random sample of 250 recommendations was manually classified. The agreement between human classification and model predictions resulted in a Cohen’s Kappa of 0.88, suggesting strong agreement. This study highlights the potential of machine learning to classify biosecurity recommendations and support timely, informed decision-making in dairy herd management. • Text classification models were useful to analyze free-text biosecurity data • Support Vector Machine achieved the highest performance in classifying recommendations • Trained model performed well on text originally written in French or translated • Automated text classification may support informed decision-making in dairy farms