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

BACKGROUND

The 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.

OBJECTIVES

Assess 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.

ANIMALS

Dogs (n = 756) with and without cardiac disease attending referral centers in the United Kingdom.

METHODS

All 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.

RESULTS

The 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 IMPORTANCE

A 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.

Evaluation of a new smartphone-based digital stethoscope featuring phonocardiography and electrocardiography in dogs and cats

This study assessed a new smartphone-based digital stethoscope (DS) featuring simultaneous phonocardiographic and one-lead electrocardiogram (ECG) recording in dogs and cats. The audio files and ECG traces obtained by the device were compared with conventional auscultation and standard ECG. A total of 99 dogs and nine cats were prospectively included. All cases underwent conventional auscultation using an acoustic stethoscope, standard six-lead ECG, standard echocardiography and recordings with the DS. All the audio recordings, phonocardiographic files and ECG traces were then blind reviewed by an expert operator. The agreement between methods was assessed using Cohen's kappa and the Bland-Altman test. Audio recordings were considered interpretable in 90% animals. Substantial agreement was found in the diagnosis of heart murmur (κ = 0.691) and gallop sound (k = 0.740). In nine animals with an echocardiographic diagnosis of heart disease, only the DS detected a heart murmur or gallop sound. ECG traces recorded with the new device were deemed interpretable in 88 % animals. Diagnosis of heart rhythm showed moderate agreement in the identification of atrial fibrillation (k = 0.596). The detection of ventricular premature complexes and bundle branch blocks revealed an almost perfect agreement (k = 1). Overall, the DS showed a good diagnostic accuracy in detecting heart murmurs, gallop sounds, ventricular premature complexes and bundle branch blocks. A clinically relevant overdiagnosis of atrial fibrillation was found but without evidence of false negatives. The DS could represent a useful screening tool for heart sound abnormalities and cardiac arrhythmias..

Evaluation of the Corrected QT Interval with Bazett’s Method in Cavalier King Charles Spaniel Dogs with Myxomatous Mitral Valve Disease

Myxomatous mitral valve disease (MMVD) is one of the most common heart diseases in dogs. The disease progresses faster in Cavalier King Charles Spaniel (CKCS) dogs and occurs at an earlier age. QT interval length reflects abnormalities in ventricular repolarization which may predispose to the formation of fatal arrhythmias such as torsades de pointes. A fast and accurate assessment is therefore essential. The study aimed to examine the changes in QT duration in MMVD cases of CKCS and to calculate the corrected QT durations with Bazett’s formula in various stages of the disease. The study included 20 CKCS dogs of both genders, various ages and weights, and different stages of MMVD (n=6 in B1 stage, n=6 in B2 stage, and n=8 in C stage), and 5 healthy CKCS which were included in the control group. Clinical, radiological, hematological, biochemical, echocardiographic, and electrocardiographic examinations were performed. The corrected QT interval duration in the MMVD group was longer than the control (p<0.05). However, there was no significant difference between B1, B2, and C. It was concluded that the corrected QT interval can give a significant distinction between healthy and MMVD CKCS dogs.

Use of proposed systolic and myocardial performance indices derived from simultaneous ECG and PCG recordings to assess cardiac function in healthy Beagles

Background and Aim:

Cardiac time intervals (CTIs) can provide important information on the electrical and mechanical properties of the heart. We hypothesized that cardiac function can be described using the combined power of electrocardiography (ECG) and phonocardiography (PCG) signals. This study aimed to (1) validate a novel custom device in measuring CTI parameters; (2) compare CTI parameters with a commercially available device and standard transthoracic echocardiography (STE); and (3) compare calculated systolic performance index (SPI) and myocardial performance index (MPI) with Tei index from the STE.

Materials and Methods:

This study determined CTIs based on simultaneous ECG and PCG recordings in 14 healthy Beagle dogs using the custom-built device. These CTI parameters were compared with a commercially available device (Eko DUO ECG + Digital Stethoscope; Eko DUO) and the STE. Agreement of CTI parameters between the custom device and the commercially available device or STE was evaluated. Calculated SPI and MPI based on Wigger’s diagram were proposed, compared with SPI and Tei index, and correlated with STE parameters.

Results:

We found that the ECG and PCG parameters measured from the custom-built device did not differ from the commercially available device and the STE. By combining ECG and PCG signals, we established CTI parameters in healthy dogs including indices for systolic function (SPI: QS1/S1S2) and global cardiac function {F1 ([QS1+S2]/S1S2), F2 ([RS1+S2]/S1S2), and F3 (RS1 + [QS2-QT]/S1S2)}. The SPI, F2, and F3 were comparable with echocardiographic parameters describing systolic (Pre-ejection period/left ventricular ejection time [LVET]) and Tei index ([MCOdur-LVET]/LVET), respectively. Only SPI and F3 were correlated significantly with MCOdur and heart rate, respectively.

Conclusion:

We have validated the use of the custom-built device to describe CTIs that are comparable to the commercially available device and STE in healthy Beagles. The proposed SPI and MPI derived from CTI parameters can be useful in clinical practice to describe the cardiac function, especially in areas where access to STE is constrained.

Digital phonocardiography of cardiac arrhythmias in dogs - Preliminary experiences

Electronic stethoscopes and digital phonocardiograms (DPCGs) can be applied when diagnosing cardiac murmurs, but their use for cardiac arrhythmias is not described in veterinary medicine. Data of 10 dogs are presented in this preliminary study, demonstrating the applicability of these techniques. Although the number of artefacts and the amount of baseline noise produced by the two digitising systems used did not differ, the Welch Allyn Meditron system or similar ones capable of simultaneous recording of electrocardiograms (ECGs) and DPCGs provide a better option for clinical research and education, whilst the 3M Littmann 3200 system might be more suitable for everyday clinical settings. A combined system with simultaneous phonocardiogram and ECG, especially with wireless transmission, might be a solution in the future.

The Longitudinal Outcome Of Canine (K9) myxomatous mitral valve disease (LOOK-Mitral registry): Baseline characteristics

INTRODUCTION

The Longitudinal Outcome Of Canine (K9) myxomatous mitral valve disease (MMVD) registry (LOOK-Mitral registry) was established to describe the natural history and predictors of outcome in dogs affected by MMVD. This study was intended to describe the baseline characteristics of dogs in the LOOK-mitral registry.

ANIMALS

Dogs with echocardiographic evidence of MMVD were prospectively enrolled by thirteen referral centers.

RESULTS

A total of 6102 dogs with MMVD were included. The median age was 10 years (1-19 years), and mixed breed was the most common breed (n = 1,360, 22%). Concomitant diseases were reported in 2459 dogs with chronic respiratory diseases occurring most frequently (14%), followed by the presence of azotemia (6%) and orthopedic diseases (5%). Regarding disease severity, 65% of dogs were in ACVIM Stage-B1, 15% in Stage-B2, and 20% in Stage-C. Dogs in Stage-B1 were younger (p<0.001) than dogs in other stages. Murmur intensity, heart rate during physical examination, and radiographic vertebral heart score were positively associated with the stage. Dogs in Stage-C were more likely to have tachypnea (p<0.001), dyspnea (p<0.001), cough (p<0.001), syncopal episodes (p<0.001), and tachyarrhythmias (p<0.001) compared to dogs in Stage-B1 and B2. Echocardiographic indices of left atrial and ventricular size were positively correlated with the ACVIM stage. Interestingly, 4% of dogs that weighed <20 kg had an increased normalized end-systolic left ventricle internal diameter (>1.26).

CONCLUSIONS

This study contributes to a better understanding of the clinical characteristics of dogs affected by MMVD and provides new findings that may be of clinical relevance.

Prevalence and diagnostic characteristics of non-clinical mitral regurgitation murmurs in North American Whippets

OBJECTIVES

To assess the prevalence of functional ejection murmurs and murmurs of mitral regurgitation (MR) due to myxomatous mitral valve disease in healthy whippets; to assess the diagnostic value of auscultation to detect MR; and investigate the relationship between age and presence of echocardiographically documented MR (MR_echo).

ANIMALS

A total of 200 healthy client-owned Whippets, recruited at national shows between 2005 and 2009 were involved in this study.

METHODS

Cross-sectional study. Dogs were examined by auscultation by one examiner and Doppler echocardiography by another, and results were compared. Prevalence of types of murmurs and MR_echo were calculated and correlated to age. Accuracy of auscultation to predict MR_echo was calculated.

RESULTS

Left-sided systolic heart murmurs were detected in 185/200 (93%) of dogs. Left apical systolic murmurs (L_apex) were detected in 57/200 (29%) and left basilar systolic murmurs (L_base) in 128/200 of the dogs (64%). MR_echo was present in 76/200 (38%) dogs. Prevalence MR_echo was correlated with age (r = 0.96, p=0.0028). Mitral regurgitation detected by echocardiography was present in 12/78 (15%) of the dogs ≤ 2 years of age and in 59% of the dogs at 7-8 years old. Detection of L_apex predicted MR_echo with sensitivity 65%, specificity 94%, positive predictive value 86%, and negative predictive value 81%; and accuracy improved when only dogs with more intense L_apex (grade ≥ 3/6) were considered.

CONCLUSIONS

Systolic murmurs are common in North American Whippets and this breed exhibits a high prevalence of MR_echo, which may be documented at a relatively early age. Whippets with non-clinical MR_echo may not be identifiable by auscultation alone; echocardiographic examination may be required to exclude a diagnosis of MR. Louder heart murmurs allow more accurate localization in this population.

Prevalence of mitral valve regurgitation in 79 asymptomatic Norfolk terriers

OBJECTIVES

To determine the prevalence of mitral valve regurgitation (MR) in asymptomatic Swedish Norfolk terriers.

ANIMALS

Seventy-nine privately owned Norfolk terriers.

MATERIALS AND METHODS

A prospective observational study was conducted where dogs were recruited via the Swedish Norfolk terrier club. All dogs were examined using the same protocol including physical examination and Doppler echocardiography.

RESULTS

Fifteen dogs (19%) had a murmur at the time of the examination. A total of 35 dogs (44%) had MR, including 23 dogs (29%) with both MR and tricuspid valve regurgitation and 12 dogs (15%) with MR only, identified on Doppler echocardiography. In addition, 7 dogs (9%) had tricuspid valve regurgitation only. The prevalence of MR increased with increasing age (p < 0.0001).

CONCLUSIONS

Mitral valve regurgitation is common in asymptomatic Norfolk terriers with and without murmurs and the prevalence increases with age. The impact of MR in this breed on survival remains to be elucidated by a longitudinal study.

Clinical severity score system in dogs with degenerative mitral valve disease

BACKGROUND

Several risk factors already have been determined for dogs with degenerative mitral valve disease (DMVD). Risk factors often have been considered in isolation and have not always taken into account additional information provided by the history and physical examination (PE).

HYPOTHESIS/OBJECTIVES

Data obtained from history and PE of dogs with DMVD provide prognostic information and can be used for risk stratification.

ANIMALS

Client-owned dogs (n = 244) with DMVD recruited from first opinion practice.

METHODS

Prospective longitudinal follow-up of dogs with DMVD. History and PE data were obtained at 6-month intervals and analyzed with time-dependent Cox models to derive relative risk of cardiac death. Independent hazard ratios were used to derive a clinical severity score (CSS), the prognostic value of which was evaluated by analyzing the median survival times for different risk groups and ROC analysis. Analysis of the progression of CSS over time also was undertaken.

RESULTS

History of cough, exercise intolerance, decreased appetite, breathlessness (difficulty breathing) and syncope with PE findings of heart murmur intensity louder than III/VI and absence of respiratory sinus arrhythmia were independently associated with outcome and allowed development of the CSS. Clinical severity score distinguished groups of dogs with significantly different outcomes.

CONCLUSIONS AND CLINICAL IMPORTANCE

Routinely obtained clinical findings allow risk stratification of dogs with DMVD. Results of ancillary diagnostic tests may be complementary to history and PE findings and always should be interpreted in conjunction with these findings.

Short communication: Distribution of Porphyromonas gulae fimA genotypes in oral specimens from dogs with mitral regurgitation

Porphyromonas gulae, a suspected pathogen for periodontal disease in dogs, possesses approximately 41-kDa fimbriae (FimA) that are encoded by the fimA gene. In the present study, the association of fimA genotypes with mitral regurgitation (MR) was investigated. Twenty-five dogs diagnosed with MR (age range 6-13 years old, average 10.8 years) and 32 healthy dogs (8-15 years old, average 10.8 years) were selected at the participating clinics in a consecutive manner during the same time period. Oral swab specimens were collected from the dogs and bacterial DNA was extracted, then polymerase chain reaction analysis was performed using primers specific for each fimA genotype, with the dominant genotype determined. The rate for genotype C dominant specimens was 48.0% in the MR group, which was significantly higher than that in the control group (18.8%) (P <0.05). These results suggest that P. gulae fimA genotype C is associated with MR.

Prevalence of physiological heart murmurs in a population of 95 healthy young adult dogs

OBJECTIVES

To determine the prevalence of physiological heart murmurs in healthy young adult dogs.

MATERIALS AND METHODS

Healthy dogs aged between 1 and 5 years were enrolled prospectively. All participating dogs underwent physical examination, urinalysis, blood testing and blood pressure measurement. Cardiac auscultations were performed by three independent examiners. Dogs with heart murmurs underwent echocardiography, to exclude cardiovascular abnormalities.

RESULTS

Of 109 dogs evaluated, 95 completed the study. Heart murmurs were detected in 22 dogs. Interobserver agreement for murmur detection was moderate to fair (weighted kappa 0 · 29-0 · 56). On the basis of two different sets of echocardiographic criteria, physiological heart murmurs were diagnosed in 6 and 11 dogs, respectively, giving a prevalence of 6-12%. All physiological heart murmurs were systolic and low-grade (I-III/VI). Most were louder towards the left heart base and some radiated up to the thoracic inlet. The epidemiological features of dogs with physiological heart murmurs did not differ significantly from those of dogs without murmurs (P > 0 · 10).

CLINICAL SIGNIFICANCE

This study shows that physiological heart murmurs may not be limited to growing dogs or specific breeds, as they were commonly encountered in this population of healthy young adult dogs.

Use of discriminant analysis based on echocardiography for classification of congestive heart failure in dogs with myxomatous mitral valve disease

Mixomatous mitral valve disease (MMVD) is one of the most common cardiac abnormalities in dogs and humans that can lead to cardiac heart failure (CHF). Its diagnosis remains based on echocardiography and clinical signs. However, the early diagnose of MMVD can contribute to a better prognosis and avoid CHF. The aim of this study was to evaluate the clinical, radiographic and echocardiographic presence of CHF in dogs with MMVD in combination with a statistical model as a mathematical tool. For this purpose, dogs were divided into three groups (healthy; MMVD without CHF; and MMVD with CHF), according the clinical, radiographic and echocardiographic evaluation findings. Thus, linear discriminant functions were obtained by analyzing the variables weight, body surface area, aortic diameter, the ratio of the left atrium/aortic diameter, the ratio between the mitral regurgitation jet area and the left atrial area, vena contracta diameter and mitral valve proximal isovelocity surface area. Then, mathematical equations were established for each group of dogs. Statistical functions obtained in this study enabled to classify the dogs, regarding the presence of CHF with a probability of correct classification of 90.4%. Thus the statistical model demonstrated that it could be used as an auxiliary method for identifying CHF in dogs with MMVD.

Management of cardiac emergencies in small animals

Cardiac emergencies are life-threatening conditions that must be diagnosed quickly to avoid delays in therapy. A timely and accurate diagnosis leads to early relief of symptoms and improved survival. This article provides both a comprehensive review and updated management recommendations for common cardiac emergencies in dogs and cats. Specifically, the article confers updates for the efficient clinical recognition of decompensated cardiac patients, including focused echocardiography, cardiac biomarkers, and electrocardiogram interpretation. This article also reviews the latest recommendations for the treatment of heart failure (including the use of pimobendan) and the management of arrhythmias, pericardial effusion, and aortic thromboembolism.

Comparison of traditional and sensor-based electronic stethoscopes in beagle dogs

The objective of this study was to compare the auscultatory findings using traditional and electronic sensor-based stethoscopes. Thirty-three adult healthy Beagles (20 females, 13 males, mean age: 4.8 years, range 1.4-8 years) were auscultated by four investigators with different experiences (INVEST-1, -2, -3 and -4) independently with both stethoscopes. Final cardiological diagnoses were established by echocardiography. Mitral murmurs were heard with both stethoscopes by all investigators and echocardiography revealed mild mitral valve insufficiency in 7 dogs (21%, 4 females, 3 males). The statistical sensitivity (Se) in recognising cardiac murmurs proved to be 82% using the traditional stethoscope and 75% using the electronic one in the mean of the four examiners, whilst statistical specificity (Sp) was 99% by the traditional and 100% by the electronic stethoscope. The means of the auscultatory sensitivity differences between the two stethoscopes were 0.36 on the left and 0.59 on the right hemithorax, demonstrating an advantage for the electronic stethoscope being more obvious above the right hemithorax (P = 0.0340). The electronic stethoscope proved to be superior to the traditional one in excluding cardiac murmurs and especially in auscultation over the right hemithorax. Mitral valve disease was relatively common in this clinically healthy research Beagle population.

Survival characteristics and prognostic variables of dogs with preclinical chronic degenerative mitral valve disease attributable to myxomatous degeneration

BACKGROUND

Preclinical myxomatous mitral valve degeneration (MMVD) includes a heterogeneous group of dogs. Therefore, identifying risk factors for progression of the disease is of clinical importance.

OBJECTIVES

To investigate survival time and risk factors for clinical and echocardiographic variables taken at initial examination for clinical progression in preclinical MMVD dogs.

ANIMALS

A total of 256 dogs with stage B1 or B2 MMVD.

MATERIALS AND METHODS

Medical records of 256 dogs with preclinical MMVD were reviewed retrospectively. Long-term outcome was assessed by telephone interview. Dogs alive at the time of phone interview were asked to return to the hospital for re-evaluation of their cardiac status.

RESULTS

Seventy of 256 (27.3%) dogs died during the observation period. The median survival time, regardless of cause of death, was 588 (range 75-1,668) days. The presence of a murmur was associated with an increased risk of death (AHR 2.14; 95% CI 1.12, 4.11; P = 0.022). Thirty (12%) deaths were considered cardiac related. LA/Ao > 1.4 was the only negative predictor (AHR 2.64; 1.13, 6.13; P = 0.024) for cardiac-related deaths. Eighty-three dogs were re-examined, of which 34 progressed to a more advanced stage of MMVD. The presence of Emax > 1.2 (AHR 2.75; 95% CI 1.01, 7.48; P = 0.047) and cough (AHR 7.89; 95% CI 3.18, 20.07; P < 0.001) were significant in the multivariate analysis.

CONCLUSIONS AND CLINICAL IMPORTANCE

Preclinical MMVD represents a relatively benign condition in dogs. Clinicians might find stratification of this dog population according to risk factors based on clinical and echocardiographic findings helpful in determining treatment.

Sound recording and digital phonocardiography of cardiac murmurs in dogs by using a sensor-based electronic stethoscope

The goals of this study were to present a technique of digitalised sound recordings and phonocardiograms (dPCGs), and to analyse its diagnostic capabilities. Heart sounds of 20 dogs were auscultated in vivo (on-line) and recorded with dPCGs by two authors using a Welch Allyn Meditron Stethoscope System. Sound recordings were auscultated off-line and blindly by four different observers having various auscultatory experiences, then listened to while viewing dPCGs. The results were compared to echocardiographic diagnoses. There was a significant agreement (p < 0.001) between on-line and off-line auscultatory findings regarding the four observers, ranging from 45% to 75% (weighted kappa values: 0.72 to 0.87). The best agreement was achieved by Observer 1 having the highest experience. Significant differences (p < 0.05) were found between Observer 1 and Observer 4 (with the lowest experience) in judging the quality of the murmurs during the off-line and blind auscultation. However, there were only minimal differences (95% to 100% agreements) in dPCG analyses among the four observers regarding intensity and quality of the murmurs while simultaneously listening to and viewing the dPCGs. Significant correlations were found between the traditional '0 to 6 scale' and a new '0 to 3 scale' murmur intensity gradings by all observers (correlation coefficients 0.640 to 0.908; p < 0.01 to p < 0.001). Analysis of dPCGs might be a valuable, additional tool helping with the diagnosis of canine cardiac murmurs, especially for those with less cardiological experience.

Canine degenerative myxomatous mitral valve disease: natural history, clinical presentation and therapy

Myxomatous mitral valve disease is a common condition in geriatric dogs. Most dogs affected are clinically asymptomatic for a long time. However, about 30% of these animals present a progression to heart failure and eventually die as a consequence of the disease. Left atrial enlargement, and particularly a change in left atrial size, seems to be the most reliable predictor of progression in some studies, however further studies are needed to clarify how to recognize asymptomatic patients at higher risk of developing heart failure. According to the published data on the natural history of the disease and the results of published studies evaluating the effect of early therapy on delaying the progression of the disease, it seems that no currently available treatment delays the onset of clinical signs of congestive heart failure (CHF). Although the ideal treatment of more severely affected dogs is probably surgical mitral valve repair or mitral valve replacement, this is not a currently available option. The results of several clinical trials together with clinical experience suggest that dogs with overt CHF can be managed with acceptable quality of life for a relatively long time period with medical treatment including furosemide, an angiotensin-converting enzyme inhibitor, pimobendan, and spironolactone.