ABSTRACT
Brachycephalic obstructive airway syndrome (BOAS) in dogs challenges veterinary surgeons both with a complex clinical picture as well as wide-ranging ways to diagnose the disease, often not easily implemented nor standardised in clinical practice. The assessment of a combination of exercise testing, the occurrence of breathing noises, recovery time, and respiratory effort proved to be an appropriate method to identify Pugs with BOAS. The purpose of this study was to apply an established standardised, submaximal, treadmill-based fitness test for Pugs to other brachycephalic dog breeds. A total of 79 participants, belonging to 6 different brachycephalic breeds, trotted 15 min with an individual comfort speed of 3-7 km/h on a treadmill. Additionally, functional BOAS grading based on respiratory clinical signs before and after exercise was applied. The test was passed if the dogs presented with a BOAS grade of 0 or 1 and their vital parameters recovered to baseline within 15 min after exercise. A total of 68% showed a BOAS grade of 0 or 1 and passed the fitness test. Of the failed participants, 65% failed due to BOAS affectedness, 9% were categorised as not affected by BOAS and failed due to not passing the fitness test only, and 26% showed both failure criteria. The fitness test can be a useful method to identify BOAS-affected dogs in other brachycephalic breeds and to diagnose BOAS in dogs that only show clinical signs under exercise.
ABSTRACT
The early and accurate diagnosis of brachycephalic obstructive airway syndrome (BOAS) in dogs is pivotal for effective treatment and enhanced canine well-being. Owners often do underestimate the severity of BOAS in their dogs. In addition, traditional diagnostic methods, which include pharyngolaryngeal auscultation, are often compromised by subjectivity, are time-intensive and depend on the veterinary surgeon's experience. Hence, new fast, reliable assessment methods for BOAS are required. The aim of the current study was to use machine learning techniques to bridge this scientific gap. In this study, machine learning models were employed to objectively analyze 366 audio samples from 69 Pugs and 79 other brachycephalic breeds, recorded with an electronic stethoscope during a 15-min standardized exercise test. In classifying the BOAS test results as to whether the dog is affected or not, our models achieved a peak accuracy of 0.85, using subsets from the Pugs dataset. For predictions of the BOAS results from recordings at rest in Pugs and various brachycephalic breeds, accuracies of 0.68 and 0.65 were observed, respectively. Notably, the detection of laryngeal sounds achieved an F1 score of 0.80. These results highlight the potential of machine learning models to significantly streamline the examination process, offering a more objective assessment than traditional methods. This research indicates a turning point towards a data-driven, objective, and efficient approach in canine health assessment, fostering standardized and objective BOAS diagnostics.
