Canine hypoadrenocorticism is a life-threatening condition. It mimics many disease processes, including kidney, hepatic, and GI disease. Prognosis is excellent with appropriate treatment. This study used machine learning methods to aid in the diagnosis of canine hypoadrenocorticism. CBC and serum chemistry profile results were collected from 908 control dogs and 133 dogs with confirmed hypoadrenocorticism; these data were used as inputs for the machine algorithms in the study. This model showed a sensitivity of 96.3% and specificity of 97.2%. Although prospective studies are needed to validate this method, it has similar diagnostic performance to resting cortisol values, regardless of glucocorticoid or mineralocorticoid deficiency status, and uses an easy-to-use graphical interface.