BrachySound: machine learning based assessment of respiratory sounds in dogs.

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.

Breed-specific values for vertebral heart score (VHS), vertebral left atrial size (VLAS), and radiographic left atrial dimension (RLAD) in pugs without cardiac disease, and their relationship to Brachycephalic Obstructive Airway Syndrome (BOAS).

This prospective study aims to establish reference ranges for vertebral heart score (VHS), vertebral left atrial size (VLAS), and radiographic left atrial dimension (RLAD) in pugs. The impact of clinical severity of Brachycephalic Obstructive Airway Syndrome (BOAS), gender, body condition score, and body weight on VHS, VLAS, and RLAD were investigated. Intra- and interobserver correlation was determined. Correlation of radiographic scores to echocardiographic left atrial dimension was inspected. Additionally, for VLAS and RLAD, correlation to VHS was examined. Additionally, an assessment of thoracic and vertebral malformations was performed. Forty-seven privately owned pugs underwent physical examination, echocardiography, and thoracic radiography to determine cardiac health. Thirty-two pugs were eligible for establishing reference ranges for VHS in right lateral radiographs, which was 11.25 ± 0.62 (95% range, 10.1-12.8). Reference ranges for VHS in left lateral, and for VLAS and RLAD in right lateral radiograph were determined in 30 pugs. The VHS in left lateral radiograph was 11.01 ± 0.70 (95% range, 9.4-12.6), VLAS was 1.96 ± 0.38 (95% range, 1.1-2.8), and RLAD was 1.59 ± 0.34 (95% range, 0.7-2.4). Clinical severity of BOAS did not show any impact on radiographic measurements. For VLAS, a significant correlation to VHS was detected by all observers. No other variables had a consistent influence on the radiographic scores given by all observers. Interobserver agreement was almost perfect for VHS (0.89 on right lateral and 0.91 on left lateral image), moderate for VLAS (0.49), and fair for RLAD (0.22). More than one third of the entire study population (18 of 47 pugs) showed at least one thoracic cavity or spine abnormality, often leading to considerable changes in vertebral body shape and size.

Reference ranges for standard-echocardiography in pugs and impact of clinical severity of Brachycephalic Obstructive Airway Syndrome (BOAS) on echocardiographic parameters.

BACKGROUND: Echocardiographic measurements may be influenced by breed-specific characteristics. Therefore, this study aims to establish reference values for standard echocardiographic measurements in pugs by investigating the influence of age, sex, heart rate, body weight and Brachycephalic Obstructive Airway Syndrome (BOAS). Sixty-two privately owned pugs underwent physical examination, blood sample collection, non-invasive blood pressure measurements and echocardiography. Influences of independent variables on echocardiographic measurements were examined using a multiple linear regression analysis model. For the entire study population, 95% prediction intervals were generated. Further, reference ranges for subcategories of clinical severities of BOAS were provided. Selected echocardiographic measurements of pugs were compared to reference values of previous studies generated from various breeds. RESULTS: In the study, a total of fifty-one privately owned pugs aged between two and 10 years were included for establishing reference ranges. Mainly body weight, but also age, sex and heart rate had influence on several echocardiographic parameters. The clinical grading of BOAS was conducted in 42 pugs. Except for pulmonic peak velocity (Pvel), which declined with increasing severity of BOAS, clinical symptoms of upper airway disease did not have significant impact on echocardiographic measurement results. Significant deviations, however, of left ventricular (LV) internal dimension (LVID), interventricular septum (IVS), LV posterior wall (LVPW), and tricuspid annular plane systolic motion excursion (TAPSE) compared to interbreed reference values were observed. CONCLUSIONS: Breed-specific reference ranges for echocardiographic values with special regard to BOAS are provided to enable a more accurate assessment of cardiac health in pugs.

Evaluation of a Treadmill-Based Submaximal Fitness Test in Pugs, and Collecting Breed-Specific Information on Brachycephalic Obstructive Airway Syndrome.

Despite efforts of veterinarians and breeders, brachycephalic obstructive airway syndrome (BOAS) is still a common problem in pugs, underlining the need for objective tests to identify and prevent breeding with affected dogs. In the current study, a submaximal, treadmill-based fitness test was evaluated as a tool to identify signs of airway obstruction not recognisable under rest conditions. In addition to this, different body conformation and measurements were assessed regarding their association with BOAS. A total of 62 pugs and 10 mesocephalic dogs trotted with an individual comfort speed on a treadmill for 15 min. Before and during the examination, dogs were examined for signs of respiratory distress, and a functional BOAS grading was applied. The influence of body conformation on BOAS grading was tested in a univariable and multivariable logistic regression model. During exercise, more respiratory noises were observed, and existing respiratory noises became more apparent in comparison to when at rest. In the multivariable logistic regression model, no factor had a statistically significant influence on BOAS classification. Submaximal fitness testing helped to identify signs of respiratory distress not apparent under resting conditions, and could be a valuable addition for identifying dogs with BOAS. Performing testing on a treadmill facilitates continuous observation of the patients, and enables standardisation of the test regarding the test environment, as well as provides an uninterrupted, steady workload.

Evaluation of blood pressure and NT-proBNP in pugs with and without clinical signs of Brachycephalic Obstructive Airway Syndrome.

Brachycephalic Obstructive Airway Syndrome (BOAS) is a pathologic condition of the upper airways, frequently occurring in dogs of brachycephalic breeds including pugs. It has been suspected that BOAS may be associated with cardiovascular changes and an increased risk for hypertension. The cardiac biomarker NT-proBNP can help to differentiate cardiac from non-cardiac respiratory distress. A possible influence of BOAS on NT-proBNP values has not been investigated, however. The aim of the current study was to examine blood pressure and NT-proBNP levels in pugs with and without clinical signs of BOAS and compare them to values of mesocephalic dogs. For this purpose, NT-proBNP values of 42 pugs and six mesocephalic dogs and blood pressure measurements of 34 pugs and four mesocephalic dogs were explored in the present study. Pugs were examined for clinical signs of BOAS at rest and after a submaximal fitness test, and a functional BOAS grading was applied. Blood pressure (BP) was measured at the beginning and end of the study day and NT-proBNP values were obtained before and after exercise. Measured values of pugs with different degrees of clinical impairment due to BOAS were compared among each other as well as to the CG. In terms of systolic, mean, diastolic BP, and NT-pro BNP, there were no relevant differences between pugs and the CG and no obvious connection between the severity of BOAS symptoms and measured values. BP values of all groups were lower at the second measurement at the end of the study day. NT-proBNP measurements were higher after exercise. BP and NT-proBNP values in all groups were in agreement with commonly used reference ranges. In conclusion, the study adds evidence, that BP and NT-proBNP values did not differ between mesocephalic dogs and pugs with different levels of severity of BOAS but between the measurement times. Thus, in the present study, excitement and exercise seemed to have a greater influence on BP and NT-proBNP values than presence of BOAS symptoms or breed. Discovered values show that the commonly used reference ranges for BP and NT-proBNP are applicable in pugs. This indicates that NT-proBNP can be used to differentiate between cardiac and non-cardiac respiratory distress even in pugs with clinical symptoms of BOAS.