RESUMO
Case summary: A 2-year-old spayed female domestic longhair cat was presented for evaluation of chronic ocular discharge and occasional vomiting. While physical examination findings were consistent with an upper respiratory infection (URI), serum chemistry results revealed increased liver enzyme activities. Histopathologic examination of a liver biopsy identified substantial centrilobular accumulation of copper in hepatocytes - strongly suggestive of primary copper hepatopathy (PCH). Retrospective cytologic examination of a liver aspirate also identified copper aggregates in hepatocytes. After transitioning to a low-copper diet, 1 year of chelation therapy with D-penicillamine achieved normalization of liver enzyme activities and resolution of persistent ocular signs. Subsequently, a long-term regimen of zinc gluconate has been successfully managing the cat's PCH for almost 3 years. Sanger sequencing of the cat's ATP7B gene, which encodes a copper-transporting protein, revealed a novel, 'likely pathogenic', single nucleotide variation (c.3670t/a [p.Trp1224Arg]), for which the cat is heterozygous. Relevance and novel information: Recommendations are described for the long-term clinical management of feline PCH - a previously attainable but unreported outcome - with considerations for mitigating the speculated oxidation-exacerbated ocular risks of concurrent URI. This report is the first to include identification of copper aggregates in a liver aspirate from a cat - evidence that liver aspirates from cats could be routinely examined for copper as is standard practice for those from dogs. The cat is also the first reported with PCH and a 'likely pathogenic' heterozygous ATP7B genotype, which suggests that normal ATP7B alleles could be recessive to or incompletely/co- dominant with deleterious ATP7B alleles in cats, as has been reported in other species.
RESUMO
This retrospective analytical observational cohort study aimed to model and predict the classification of feline intestinal diseases from segmentations of a transverse section from small intestine ultrasound (US) image, complete blood count (CBC), and serum biochemical profile data using a variety of machine-learning approaches. In 149 cats from three institutions, images were obtained from cats with biopsy-confirmed small cell epitheliotropic lymphoma (lymphoma), inflammatory bowel disease (IBD), no pathology ("healthy"), and other conditions (warrant a biopsy for further diagnosis). CBC, blood serum chemistry, small intestinal ultrasound, and small intestinal biopsy were obtained within a 2-week interval. CBC and serum biomarkers and radiomic features were combined for modeling. Four classification schemes were investigated: (1) normal versus abnormal; (2) warranting or not warranting a biopsy; (3) lymphoma, IBD, healthy, or other conditions; and (4) lymphoma, IBD, or other conditions. Two feature selection methods were used to identify the top 3, 5, 10, and 20 features, and six machine learning models were trained. The average (95% CI) performance of models for all combinations of features, numbers of features, and types of classifiers was 0.886 (0.871-0.912) for Model 1 (normal vs. abnormal), 0.751 (0.735-0.818) for Model 2 (biopsy vs. no biopsy), 0.504 (0.450-0.556) for Model 3 (lymphoma, IBD, healthy, or other), and 0.531 (0.426-0.589), for Model 4 (lymphoma, IBD, or other). Our findings suggest model accuracies above 0.85 can be achieved in Model 1 and 2, and that including CBC and biochemistry data with US radiomics data did not significantly improve accuracy in our models.
