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. The remaining unseen EHRs were used to evaluate model performance. The final model was a recurrent neural network with 6 features (creatinine, blood urea nitrogen, urine specific gravity, urine protein, weight, age). Identifying CKD at the time of diagnosis, the model displayed a sensitivity of 91.4% and a specificity of 97.2%. When predicting future risk of CKD, model sensitivity was 68.8% at 1 year, and 44.8% 2 years before diagnosis. Positive predictive value (PPV) varied between 15 and 23% and was influenced by the age of the patient, while the negative predictive value remained above 99% under all tested conditions. While the modest PPV limits its use as a stand-alone diagnostic screening tool, high specificity and NPV make the model particularly effective at identifying patients that will not go on to develop CKD.

OBJECTIVE To evaluate patient and vaccine factors associated with adverse events (AEs) recorded within 3 days of vaccine administration in a large cohort of dogs. ANIMALS 4,654,187 dogs vaccinated in 16,087,455 office visits in a 5-year period at 1,119 hospitals of a corporate practice. METHODS Electronic medical records of dogs vaccinated between January 1, 2016, and December 31, 2020, were searched for diagnoses of possible AEs recorded within 3 days of administration of vaccines without concurrent injectable heartworm preventative. Patient risk factors (age, sex, breed, and weight) and number and type of vaccine were extracted from records. ORs (and 95% CIs) for risk factors were estimated via multivariable logistic regression mixed models with patient as a random effect. RESULTS AEs were recorded following 31,197 vaccination visits (0.19%, or 19.4/10,000 visits). Reported AE rates increased from 1 to 4 vaccines administered and among individual vaccines were greatest for rabies vaccine. AE rate was generally inversely related to body weight, with largest rates in dogs ≤ 5 kg. The largest AE rates were noted in French Bulldogs and Dachshunds (ORs > 4 compared to mixed-breed dogs). CLINICAL RELEVANCE Risk factor information can be used to update vaccination protocols and client communication. Breed differences may indicate genetics as the primary risk factor for adverse vaccine reactions following vaccinations.

OBJECTIVE To estimate the incidence of and identify patient risk factors for an acute adverse event in dogs after administration of a sustained-release injectable heartworm preventive product. ANIMALS Canine patients that received the injectable heartworm preventive product during routine preventive care visits. METHODS Retrospective analysis of electronic medical records of canine visits within a large network of primary care veterinary clinics in which the product was administered from January 1, 2016, through December 31, 2020. Visits during which vaccination(s) were also administered were excluded from analysis. Identification of acute adverse events was based on diagnostic entries and other clinical presentations suggestive of an adverse event within 3 days of product administration. Data were analyzed using mixed-effects logistic regression. RESULTS In the 5-year study period, 1,399,289 visits with 694,030 dogs led to an incidence estimate of approximately 14.3 events/10,000 doses. Regression analysis found younger dogs and 7 breeds (relative to mixed-breed dogs) to have statistically significant greater odds of an event. CLINICAL RELEVANCE Understanding of incidence and patient risk factors provides veterinary professionals and dog owners more information when deciding on heartworm preventive options for their dog when considering risk for adverse event in dogs of certain ages or breeds.