Evaluation of supervised machine-learning algorithms to distinguish between inflammatory bowel disease and alimentary lymphoma in cats

Abstract

Inflammatory bowel disease (IBD) and alimentary lymphoma (ALA) are common gastrointestinal diseases in cats. The very similar clinical signs and histopathologic features of these diseases make the distinction between them diagnostically challenging. We tested the use of supervised machine-learning algorithms to differentiate between the 2 diseases using data generated from noninvasive diagnostic tests. Three prediction models were developed using 3 machine-learning algorithms: naive Bayes, decision trees, and artificial neural networks. The models were trained and tested on data from complete blood count (CBC) and serum chemistry (SC) results for the following 3 groups of client-owned cats: normal, inflammatory bowel disease (IBD), or alimentary lymphoma (ALA). Naive Bayes and artificial neural networks achieved higher classification accuracy (sensitivities of 70.8% and 69.2%, respectively) than the decision tree algorithm (63%, p < 0.0001). The areas under the receiver-operating characteristic curve for classifying cases into the 3 categories was 83% by naive Bayes, 79% by decision tree, and 82% by artificial neural networks. Prediction models using machine learning provided a method for distinguishing between ALA-IBD, ALA-normal, and IBD-normal. The naive Bayes and artificial neural networks classifiers used 10 and 4 of the CBC and SC variables, respectively, to outperform the C4.5 decision tree, which used 5 CBC and SC variables in classifying cats into the 3 classes. These models can provide another noninvasive diagnostic tool to assist clinicians with differentiating between IBD and ALA, and between diseased and nondiseased cats.

Evaluation of the VETSCAN IMAGYST: an in-clinic canine and feline fecal parasite detection system integrated with a deep learning algorithm

“…To the best of our knowledge, this is the first study demonstrating that a deep learning object detection algorithm successfully recognized and identified intestinal parasite eggs of dogs and cats on fecal flotation slides scanned by an automated microscope. The utilization of machine learning systems to support veterinarians with decision and diagnosis making processes has been evaluated previously [12][13][14][15][16][17]; however, it has been very limited in veterinary medicine compared to that in human medicine [18]. The algorithms evaluated in previous studies were mainly systems that assisted the medical decision-making processes based on results obtained from physical examinations and laboratory tests [12][13][14][15][16][17].…”

“…The utilization of machine learning systems to support veterinarians with decision and diagnosis making processes has been evaluated previously [12][13][14][15][16][17]; however, it has been very limited in veterinary medicine compared to that in human medicine [18]. The algorithms evaluated in previous studies were mainly systems that assisted the medical decision-making processes based on results obtained from physical examinations and laboratory tests [12][13][14][15][16][17]. Additionally, a computational shape recognition system integrated with fluorescent lebelling and smartphonebased image capturing has been assessed and applied for parasite fecal egg counting examinations [19,20].…”

Pilot study of the effect of gastrointestinal diets on fecal occult blood testing in cats

“…11 Identifying melena and or hematochezia in our feline patients is equally valid; the type of gastrointestinal diseases resulting in gastrointestinal bleeding, such as inflammatory bowel disease and neoplasia, may vary in severity, location and presentation, and may result in both melena and hematochezia. [22][23][24] Differences in FOB sensitivity based on the location of gastrointestinal bleeding may occur as a result of the presence of bacteria and digestive enzymes, which degrade hemoglobin. Administering incremental volumes of whole blood directly to stool samples, we were able to assess test sensitivity for varying levels of hematochezia.…”

Serum haptoglobin concentrations in feline inflammatory bowel disease and small-cell alimentary lymphoma: a potential biomarker for feline chronic enteropathies

“…These biomarkers include albumin, cobalamin, folate, total protein, lactate dehydrogenase, thymidine kinase type 1, serum amyloid A and fecal calprotectin, among others. 2,7,9–11 None has been able to replace the need for histopathologic evaluation of biopsied tissue.…”