Evaluation of a machine learning tool to screen for hypoadrenocorticism in dogs presenting to a teaching hospital

Abstract

Background Dogs with hypoadrenocorticism (HA) have clinical signs and clinicopathologic abnormalities that can be mistaken as other diseases. In dogs with a differential diagnosis of HA, a machine learning model (MLM) has been validated to discriminate between HA and other diseases. This MLM has not been evaluated as a screening tool for a broader group of dogs. Hypothesis An MLM can accurately screen dogs for HA. Animals Dogs (n = 1025) examined at a veterinary hospital. Methods Dogs that presented to a tertiary referral hospital that had a CBC and serum chemistry panel were enrolled. A trained MLM was applied to clinicopathologic data and in dogs that were MLM positive for HA, diagnosis was confirmed by measurement of serum cortisol. Results Twelve dogs were MLM positive for HA and had further cortisol testing. Five had HA confirmed (true positive), 4 of which were treated for mineralocorticoid and glucocorticoid deficiency, and 1 was treated for glucocorticoid deficiency alone. Three MLM positive dogs had baseline cortisol ≤2 μg/dL but were euthanized or administered glucocorticoid treatment without confirming the diagnosis with an ACTH‐stimulation test (classified as “undetermined”), and in 4, HA was ruled out (false positives). The positive likelihood ratio of the MLM was 145 to 254. All dogs diagnosed with HA by attending clinicians tested positive by the MLM. Conclusions and Clinical Importance This MLM can robustly predict HA status when indiscriminately screening all dogs with blood work. In this group of dogs with a low prevalence of HA, the false positive rates were clinically acceptable.

Evaluation of the Blood Neutrophil-to-Lymphocyte Ratio (NLR) as a Diagnostic and Prognostic Biomarker in Dogs with Portosystemic Shunt

“…Thus, the diagnosis, treatment, and prognosis of PSSs continue to rely on the integration of the results of several diagnostical tests, including routine blood work, urinalysis, diagnostic imaging, further diagnostics to rule out other differentials, and potentially hepatic biopsy, to arrive at the final diagnosis and optimize treatment for individual patients. However, integrating the NLR into a diagnostic algorithm, similar to that recently described for the diagnosis of HOC [ 49 ], may allow for a prediction of the number of surgical interventions required if shunt attenuation using surgical ligation is selected, but further prospective studies are needed to confirm our results.…”

Veterinarian burnout demographics and organizational impacts: a narrative review

“…The doubling time for knowledge in 1950 was an estimated 50 years, but it accelerated to 7 years by 1980, to 3.5 years by 2010, and was projected to be 73 days by 2020 in a 2011 study (244). Veterinary education increasingly emphasizes self-directed learning skills (245) and to manage this information growth, the technology needs of veterinary education and practice may ultimately increase in the form of computerized clinical decision support software [such as Elsevier's ClinicalKey R for physicians (246)] and artificial intelligence systems (247)(248)(249). Given the exponential expansion of scientific knowledge in modern medical practice, at some point, the profession may need to re-evaluate the fundamental structures and expectations of veterinary education and/or potentially consider future limitations or specifications on different types of veterinary licensure.…”