Abstract
Cushing’s syndrome is an endocrine disease in dogs that negatively impacts upon the quality-of-life of affected animals. Cushing’s syndrome can be a challenging diagnosis to confirm, therefore new methods to aid diagnosis are warranted. Four machine-learning algorithms were applied to predict a future diagnosis of Cushing's syndrome, using structured clinical data from the VetCompass programme in the UK. Dogs suspected of having Cushing's syndrome were included in the analysis and classified based on their final reported diagnosis within their clinical records. Demographic and clinical features available at the point of first suspicion by the attending veterinarian were included within the models. The machine-learning methods were able to classify the recorded Cushing’s syndrome diagnoses, with good predictive performance. The LASSO penalised regression model indicated the best overall performance when applied to the test set with an AUROC = 0.85 (95% CI 0.80–0.89), sensitivity = 0.71, specificity = 0.82, PPV = 0.75 and NPV = 0.78. The findings of our study indicate that machine-learning methods could predict the future diagnosis of a practicing veterinarian. New approaches using these methods could support clinical decision-making and contribute to improved diagnosis of Cushing’s syndrome in dogs.
Highlights
Cushing’s syndrome is an endocrine disease in dogs that negatively impacts upon the quality-oflife of affected animals
The support vector machine (SVM) models demonstrated a drop in performance when applied to the test set: Linear SVM area under the receiver operating characteristic (AUROC) = 0.73; radial basis function (RBF) SVM AUROC = 0.72 (Table 3)
This study demonstrates the ability of machine-learning methods to correctly classify the recorded veterinarian diagnosis of Cushing’s syndrome in dogs from the point of first suspicion, using electronic patient records of dogs under primary veterinary care in the UK
Summary
Cushing’s syndrome is an endocrine disease in dogs that negatively impacts upon the quality-oflife of affected animals. The findings of our study indicate that machine-learning methods could predict the future diagnosis of a practicing veterinarian New approaches using these methods could support clinical decision-making and contribute to improved diagnosis of Cushing’s syndrome in dogs. Affected dogs typically show various combinations of polyuria, polydipsia, polyphagia, a potbellied appearance, muscle weakness, bilateral alopecia, panting and lethargy[1,2,3,4] These clinical signs, along with potential consequential complications of the disease such as diabetes mellitus, pancreatitis and hypertension, highlight the importance of timely diagnosis and optimal control of Cushing’s syndrome for ongoing health and good quality-of-life[5, 6]. A machine-learning tool to predict dogs with Cushing’s syndrome could aid veterinarians within the practice setting and could facilitate timely commencement of treatment for affected dogs
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
