Predicting early risk of chronic kidney disease in cats using routine clinical laboratory tests and machine learning.

Bradley, R., Tagkopoulos, I., Kim, M., Kokkinos, Y., Panagiotakos, T., Kennedy, J., De Meyer, G., Watson, P., & Elliott, J. (2019). Predicting early risk of chronic kidney disease in cats using routine clinical laboratory tests and machine learning. Journal of Veterinary Internal Medicine, 33, 2644–2656. https://doi.org/10.1111/jvim.15623

This study aimed to develop a model for predicting the risk of chronic kidney disease (CKD) in cats using electronic health records (EHRs) from routine veterinary practice. Data from 106,251 cats over a 22-year period were used, with 67% employed for model development and 33% for validation. The final model, a recurrent neural network (RNN), utilized four features: creatinine, blood urea nitrogen, urine specific gravity, and age. The model achieved a sensitivity of 90.7% and a specificity of 98.9% near diagnosis, but sensitivity decreased with longer prediction windows. Machine learning models can enhance early detection of CKD, supporting veterinary decision-making.