Artificial intelligence is beginning to create value for selected small animal veterinary applications while remaining immature for others.

Artificial intelligence is a powerful technology with great potential to support veterinarians across many aspects of their multifaceted job. However, realizing this potential requires AI solutions that truly address specific pain points. Here we review 4 use cases in which AI has been applied to small animal veterinary medicine: image analysis, early disease detection, administration support, and disease surveillance.

An early prediction model for canine chronic kidney disease based on routine clinical laboratory tests.

The aim of this study was to derive a model to predict the risk of dogs developing chronic kidney disease (CKD) using data from electronic health records (EHR) collected during routine veterinary practice. Data from 57,402 dogs were included in the study. Two thirds of the EHRs were used to build the model, which included feature selection and identification of the optimal neural network type and architecture.

Development and initial validation of a dog quality of life instrument.

The increasing attention for the dog-owner relationship combined with advances in nutrition and veterinary care have made wellbeing a focal point for dog owners, veterinarians, and dog product and service providers. While canine wellbeing can be quantified by survey-based quality of life instruments like those used in human healthcare, there are currently few instruments available that can do this reliably and at scale. Here we report the development and initial validation of a canine quality of life instrument specifically designed to quantify wellbeing in the general dog population.

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

Background: Advanced machine learning methods combined with large sets of health screening data provide opportunities for diagnostic value in human and veterinary medicine.

Hypothesis/objectives: To derive a model to predict the risk of cats developing chronic kidney disease (CKD) using data from electronic health records (EHRs) collected during routine veterinary practice.

Animals: A total of 106 251 cats that attended Banfield Pet Hospitals between January 1, 1995, and December 31, 2017.

Moving Beyond Managing Realized Genomic Relationship in Long-Term Genomic Selection.

Long-term genomic selection (GS) requires strategies that balance genetic gain with population diversity, to sustain progress for traits under selection, and to keep diversity for future breeding. In a simulation model for a recurrent selection scheme, we provide the first head-to-head comparison of two such existing strategies: genomic optimal contributions selection (GOCS), which limits realized genomic relationship among selection candidates, and weighted genomic selection (WGS), which upscales rare allele effects in GS. Compared to GS, both methods provide the same higher long-term genetic gain and a similar lower inbreeding rate, despite some inherent limitations.

Heuristic exploitation of genetic structure in marker-assisted gene pyramiding problems.

Background: Over the last decade genetic marker-based plant breeding strategies have gained increasing attention because genotyping technologies are no longer limiting. Now the challenge is to optimally use genetic markers in practical breeding schemes. For simple traits such as some disease resistances it is possible to target a fixed multi-locus allele configuration at a small number of causal or linked loci.

Diagnosis-independent Alzheimer disease biomarker signature in cognitively normal elderly people.

Objective: To identify biomarker patterns typical for Alzheimer disease (AD) in an independent, unsupervised way, without using information on the clinical diagnosis.

Design: Mixture modeling approach.

Setting: Alzheimer's Disease Neuroimaging Initiative database.

The effect of weight loss on lameness in obese dogs with osteoarthritis.

This paper describes the effect of weight loss on lameness in obese dogs with osteoarthritis (OA). Fourteen obese client-owned dogs with clinical and radiographic signs of OA participated in an open prospective clinical trial. After a screening visit and a visit for collection of baseline data, the dogs were fed a restricted-calorie diet over a study period of 16 weeks that incorporated six follow-up visits.

Amino-truncated beta-amyloid42 peptides in cerebrospinal fluid and prediction of progression of mild cognitive impairment.

Background: Early identification of patients with mild cognitive impairment (MCI) progressing to Alzheimer disease (MCI-AD) by use of biomarkers in cerebrospinal fluid (CSF) is an essential step toward improving clinical diagnosis and drug development. We evaluated whether different beta-amyloid(42) (Abeta42) peptides can add further information to the combined use of tau and Abeta1-42 for predicting risk of progression of MCI to AD.

Methods: We used xMAP technology to simultaneously quantify different Abeta42 peptides modified at the amino terminus, tau, and phosphorylated tau (P-tau181P) in CSF.

Attention and information processing in survivors of childhood acute lymphoblastic leukemia treated with chemotherapy only.

Background: Omitting radiotherapy for central nervous system (CNS) prophylaxis has improved the overall quality of life for long-term survivors of childhood acute lymphoblastic leukemia (ALL). However, recent reports suggest minor cognitive impairment in survivors who received chemotherapy only.

Procedure: This study focused on attentional functioning and speed of information processing in 23 children previously treated for ALL according to EORTC 58881 and EORTC 58951 protocol.

Simultaneous measurement of beta-amyloid(1-42), total tau, and phosphorylated tau (Thr181) in cerebrospinal fluid by the xMAP technology.

Background: To simultaneously study several biomarkers for Alzheimer disease (AD), we used the xMAP technology to develop and evaluate a multiparametric bead-based assay for quantification of beta-amyloid((1-42)) [Abeta((1-42))], total tau (T-TAU), and hyperphosphorylated tau [P-TAU((181P))] in cerebrospinal fluid (CSF).

Methods: We compared the new multianalyte assay format with established ELISA techniques for the same proteins. We then performed a clinical study using CSF samples from patients with AD or mild cognitive impairment with progression to AD, healthy controls, and patients with other neurologic disorders.

Neurotoxicity marker profiles in the CSF are not age-dependent but show variation in children treated for acute lymphoblastic leukemia.

Background: In children treated for hematological malignancies, a transient elevation of the neurodegenerative marker Tau was found in the cerebrospinal fluid (CSF). In the first part of this study, CSF-Tau, CSF-Phospho-Tau, and CSF-Neuromodulin (CSF-NM) were measured in a heterogeneous group of patients presenting in the pediatric oncology department. In the second part, the neurodegenerative markers were analyzed in a group of children with non-B-cell acute lymphoblastic leukemia (nB-ALL) treated according to EORTC protocols 58881 and 58951.

Abscisic acid determines basal susceptibility of tomato to Botrytis cinerea and suppresses salicylic acid-dependent signaling mechanisms.

Abscisic acid (ABA) is one of the plant hormones involved in the interaction between plants and pathogens. In this work, we show that tomato (Lycopersicon esculentum Mill. cv Moneymaker) mutants with reduced ABA levels (sitiens plants) are much more resistant to the necrotrophic fungus Botrytis cinerea than wild-type (WT) plants.