Use of physical examination, electrocardiography, radiography, and biomarkers to predict echocardiographic stage B2 myxomatous mitral valve disease in preclinical Cavalier King Charles Spaniels

Wesselowski, S.; Gordon, S.G.; Fries, R.; Saunders, A.B.; Sykes, K.T.; Vitt, J.; Boutet, B.; Häggström, J.; Kadotani, S.; Stack, J.; Barnett, B.G.

doi:10.1016/j.jvc.2023.10.001

Cited by 2 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A VLAS cutoff > 2.5 best identified MVD dogs with cardiac enlargement, which is in agreement with previously published results [6,7,14,30]. However, other authors have reported lower cutoffs, >2.2 [23], >2.3 [30][31][32][33], and >2.4 [8,15,18]. Considering the M-VLAS, a cutoff > 3.6 showed the optimal clinical utility, a result in line with the literature [15].…”

Section: Discussionsupporting

confidence: 91%

Radiographic Left Atrial Size Measurement of Dogs in Different Mitral Valve Disease Stages with Four Different Methods

Marbella Fernández,

Montoya-Alonso

2023

Animals

View full text Add to dashboard Cite

The left atrial size increases (LAS) in patients with mitral valve disease (MVD) as the disease progresses. The vertebral left atrial size (VLAS), the modified-vertebral left atrial size (M-VLAS), and the radiographic left atrial dimension (RLAD) are methods reported to assess LAS on dogs’ radiographs. All these methods transform the LAS into vertebral units. The thoracic inlet (TI) has been used as a reliable reference point to measure the cardiac silhouette of dogs with MVD in different stages. The objective of this study was to assess the clinical utility of measuring a dog LAS on right thoracic X-rays using the TI as a reference and determine whether it could differentiate dogs in different MVD stages. LAS was divided by the TI to obtain the thoracic inlet left atrial score (TILAS). This was a retrospective observational study including 135 apparently healthy dogs performed to assess their LAS with four different methods: VLAS, M-VLAS, RLAD, and TILAS. Thirty-six dogs from the general population were selected and compared to 100 dogs in different MVD stages. The TILAS was significantly different between the control dogs and MVD dogs, increasing with the disease stage: control dogs 0.51 ± 0.08, B1 0.57 ± 0.14, B2 0.75 ± 0.13, and C 0.84 ± 0.18. VLAS, M-VLAS, and RLAD also increased as the disease progressed, as shown in previous studies. The TILAS accuracy to distinguish MVD dogs with cardiac enlargement was comparable to VLAS, M-VLAS, and RLAD (AUC 0.91 vs. 0.93, 0.90, and 0.94 respectively). A TILAS > 0.8 can identify dogs with cardiac enlargement secondary to MVD.

show abstract

Section: Discussionsupporting

confidence: 91%

Radiographic Left Atrial Size Measurement of Dogs in Different Mitral Valve Disease Stages with Four Different Methods

Marbella Fernández,

Montoya-Alonso

2023

Animals

View full text Add to dashboard Cite

show abstract

A machine‐learning algorithm to grade heart murmurs and stage preclinical myxomatous mitral valve disease in dogs

McDonald,

Novo Matos,

Silva

et al. 2024

Veterinary Internal Medicne

View full text Add to dashboard Cite

BackgroundThe presence and intensity of heart murmurs are sensitive indicators of several cardiac diseases in dogs, particularly myxomatous mitral valve disease (MMVD), but accurate interpretation requires substantial clinical expertise.ObjectivesAssess if a machine‐learning algorithm can be trained to accurately detect and grade heart murmurs in dogs and detect cardiac disease in electronic stethoscope recordings.AnimalsDogs (n = 756) with and without cardiac disease attending referral centers in the United Kingdom.MethodsAll dogs received full physical and echocardiographic examinations by a cardiologist to grade any murmurs and identify cardiac disease. A recurrent neural network algorithm, originally trained for heart murmur detection in humans, was fine‐tuned on a subset of the dog data to predict the cardiologist's murmur grade from the audio recordings.ResultsThe algorithm detected murmurs of any grade with a sensitivity of 87.9% (95% confidence interval [CI], 83.8%‐92.1%) and a specificity of 81.7% (95% CI, 72.8%‐89.0%). The predicted grade exactly matched the cardiologist's grade in 57.0% of recordings (95% CI, 52.8%‐61.0%). The algorithm's prediction of loud or thrilling murmurs effectively differentiated between stage B1 and B2 preclinical MMVD (area under the curve [AUC], 0.861; 95% CI, 0.791‐0.922), with a sensitivity of 81.4% (95% CI, 68.3%‐93.3%) and a specificity of 73.9% (95% CI, 61.5%‐84.9%).Conclusion and Clinical ImportanceA machine‐learning algorithm trained on humans can be successfully adapted to grade heart murmurs in dogs caused by common cardiac diseases, and assist in differentiating preclinical MMVD. The model is a promising tool to enable accurate, low‐cost screening in primary care.

show abstract

Use of physical examination, electrocardiography, radiography, and biomarkers to predict echocardiographic stage B2 myxomatous mitral valve disease in preclinical Cavalier King Charles Spaniels

Cited by 2 publications

References 34 publications

Radiographic Left Atrial Size Measurement of Dogs in Different Mitral Valve Disease Stages with Four Different Methods

Radiographic Left Atrial Size Measurement of Dogs in Different Mitral Valve Disease Stages with Four Different Methods

A machine‐learning algorithm to grade heart murmurs and stage preclinical myxomatous mitral valve disease in dogs

Contact Info

Product

Resources

About