Machine-learning based prediction of Cushing’s syndrome in dogs attending UK primary-care veterinary practice

Schofield, I., Brodbelt, D. C., Kennedy, N., Niessen, S. J. M., Church, D. B., Geddes, R. F., & O’Neill, D. G. (2021). Machine-learning based prediction of Cushing’s syndrome in dogs attending UK primary-care veterinary practice. Scientific Reports, 11, Article 9035. https://www.nature.com/articles/s41598-021-88440-z

This study applied four machine-learning algorithms to predict Cushing’s syndrome in dogs using clinical data from the UK VetCompass programme. Dogs were classified based on their final diagnosis, with demographic and clinical features at the point of suspicion included in the models. The LASSO penalised regression model showed the best predictive performance with an AUROC of 0.85, sensitivity of 0.71, and specificity of 0.82. These findings suggest that machine-learning could assist veterinarians in diagnosing Cushing’s syndrome and improve decision-making.