Extraction and assessment of diagnosis-relevant features for heart murmur classification.

This paper presents a heart murmur detection and multi-class classification approach via machine learning. We extracted heart sound and murmur features that are of diagnostic importance and developed additional 16 features that are not perceivable by human ears but are valuable to improve murmur classification accuracy. We examined and compared the classification performance of supervised machine learning with k-nearest neighbor (KNN) and support vector machine (SVM) algorithms. We put together a test repertoire having more than 450 heart sound and murmur episodes to evaluate the performance of murmur classification using cross-validation of 80-20 and 90-10 splits. As clearly demonstrated in our evaluation, the specific set of features chosen in our study resulted in accurate classification consistently exceeding 90% for both classifiers.

Assessment of the Cardiovascular System in Horses During Prepurchase and Insurance Examinations.

Arrhythmias detected on prepurchase examination should be confirmed with an ECG. Exercising ECG determines if the arrhythmia is overdriven during exercise or is a safety concern. An echocardiogram is needed in all horses with a grade 3/6 or louder mid to late systolic, holosystolic, or pansystolic murmur or any holodiastolic decrescendo murmur to identify the cardiac abnormality and its hemodynamic impact. Most horses with arrhythmias and murmurs have a normal performance career and life expectancy and are insurable. Risks for sudden death and congestive heart failure associated with the common murmurs and arrhythmias are identified, because these horses cannot be insured.

A computer-aided MFCC-based HMM system for automatic auscultation.

Auscultation, the act of listening to the sounds of internal organs, is a valuable medical diagnostic tool. Auscultation methods provide the information about a vast variety of internal body sounds originated by various organs such as heart, lungs, bowel, vascular disorders, etc. In this study, a cardiac sound registration system has been designed incorporating functions such as heart signals segmentation, classification and characterization for automated identification and ease of interpretation by the users. Considering a synergy with the domain of speech analysis, the authors introduced Mel-frequency cepstral coefficient (MFCC) to extract representative features and develop hidden Markov model (HMM) for signal classification. This system was applied to 1381 data sets of real and simulated, normal and abnormal domains. Classification rates for normal and abnormal heart sounds were found to be 95.7% for continuous murmurs, 96.25% for systolic murmurs and 90% for diastolic murmurs by a probabilistic comparison approach. This implies a high potential for the system as a diagnostic aid for primary health-care sectors.

Assessment of suspected aortic stenosis by auto mutual information analysis of murmurs.

Mild sclerotic thickening of the aortic valve affects 25% of the population, and the condition causes aortic valve stenosis (AS) in 2% of adults above 65 years. Echocardiography is today the clinical standard for assessing AS. However, a cost effective and uncomplicated technique that can be used for decision support in the primary health care would be of great value. In this study, recorded phonocardiographic signals were analyzed using the first local minimum of the auto mutual information (AMI) function. The AMI method measures the complexity in the sound signal, which is related to the amount of turbulence in the blood flow and thus to the severity of the stenosis. Two previously developed phonocardiographic methods for assessing AS severity were used for comparison, the murmur energy ratio and the sound spectral averaging technique. Twenty-nine patients with suspected AS were examined with Doppler echocardiography. The aortic jet velocity was used as a reference of AS severity, and it was found to correlate with the AMI method, the murmur energy ratio and the sound spectral averaging technique with the correlation coefficient R = 0.82, R = 0.73 and R = 0.76, respectively.

[Accurate assessment of heart murmurs in children: thorough medical history and physical examination required]. / Beoordeling van hartgeruisen bij kinderen: zorgvuldige anamnese en lichamelijk onderzoek vereist.

4 children, boys aged 12, 5, 1.5 and 11 years, had a heart murmur. The 12-year-old boy could also not finish a football match and appeared to have atrioseptal defects (ASD). The 1.5-year-old boy had pulmonary symptoms that were not responsive to asthma medication; he also had ASD. The 11-year-old boy had had chest pain and pressure following exertion for 2 years; he appeared to have an aortic stenosis. Symptoms disappeared in all 3 patients after surgical correction. In the 5-year-old asymptomatic boy the murmur was deemed to be innocent following medical history and physical examination. Children frequently have heart murmurs. Most heart murmurs are innocent but some are caused by heart defects. Careful evaluation of the medical history and physical examination are critical in the differentiation of innocent and pathological heart murmurs. Routine supplementary diagnostic tests in children with heart murmurs are of limited value and are often misleading. One should inquire about specific and nonspecific symptoms and also perform systematic inspection, palpation and auscultation to identify any characteristics that suggest a heart murmur caused by a heart defect.

[Heart murmur--auscultation or echocardiography in the diagnostic assessment of congenital or valvular heart disease?]. / Herzgeräusch--Auskultation oder Echokardiographie bei der Diagnose von Vitien und Herzklappenfehlern?

The incidence of patients with degenerative valvular but also of patients with congenital heart disease surviving until adulthood or even old age will increase in the next decades. Auscultation with the stethoscope remains an important diagnostic means in the detection and treatment of heart disease. Heart murmurs (especially systolic heart murmurs) are extremely common. There are helpful clues to differentiate heart murmurs. It can occasionally be relatively simple to differentiate a systolic murmur due to valvular heart disease from an innocent, ejection murmur; however, there are important limitations of auscultation. Overall, auscultation and clinical examination alone do not suffice to correctly diagnose and treat patients with heart failure or a murmur Clinically significant aortic stenosis, aortic regurgitation and mitral regurgitation as well as hypertrophic cardiomyopathy are not uncommonly missed or misinterpreted. An echocardiographic exam is mandatory in all patients with more than a soft systolic murmur, any diastolic murmur, cardiac symptoms and/or ECG changes.

Assessment and evaluation of the woman with cardiac disease during pregnancy.

Maternal heart disease complicates 0.2 to 3% of pregnancies and is responsible for 10% to 25% of maternal deaths. Many healthy women manifest subtle signs of cardiac failure during uncomplicated pregnancy and birth. Classic symptoms of heart disease mimic common symptoms of late pregnancy, such as palpitations, shortness of breath with exertion, and occasional chest pain. A complete cardiovascular examination assists the healthcare team to fully assess and evaluate the pregnant woman with known heart disease. Detailed assessment of the woman throughout pregnancy may lead to initial discovery of heart disease. Compilation of these objective data with subjective functional capacities allows for risk stratification and assignment to a New York Heart Association functional classification.

A pilot study of clinical agreement in cardiovascular preparticipation examinations: how good is the standard of care?

OBJECTIVE: To evaluate the interobserver agreement between physicians regarding a abnormal cardiovascular assessment on athletic preparticipation examinations. DESIGN: Cross-sectional clinical survey. SETTING: Outpatient Clinic, United States Military Academy, West Point, NY. PARTICIPANTS: We randomly selected 101 out of 539 cadet-athletes presenting for a preparticipation examination. Two primary care sports medicine fellows and a cardiologist examined the cadets. INTERVENTIONS: After obtaining informed consent from all participants, all 3 physicians separately evaluated all 101 cadets. The physicians recorded their clinical findings and whether they thought further cardiovascular evaluation (echocardiography) was indicated. MAIN OUTCOME MEASURES: Rate of referral for further cardiovascular evaluation, clinical agreement between sports medicine fellows, and clinical agreement between sports medicine fellows and the cardiologist. RESULTS: Each fellow referred 6 of the 101 evaluated cadets (5.9%). The cardiologist referred none. Although each fellow referred 6 cadets, only 1 cadet was referred by both. The kappa statistic for clinical agreement between fellows is 0.114 (95% CI, -0.182 to 0.411). There was no clinical agreement between the fellows and the cardiologist. CONCLUSIONS: This pilot study reveals a low level of agreement between physicians regarding which athletes with an abnormal examination deserved further testing. It challenges the standard of care and questions whether there is a need for improved technologies or improved training in cardiovascular clinical assessment.

[Referral practice and clinical assessment of heart murmurs in children]. / Henvisningspraksis og klinisk vurdering av bilyder hos barn.

BACKGROUND: Heart murmurs in infants and children are common, and in most cases these are physiological murmurs. In a few cases they represent congenital heart disease; it is important to detect those few children by referral to paediatric cardiologists. MATERIAL: 220 consecutive children with heart murmur were investigated prospectively as outpatients in the Children's clinic, Haukeland University Hospital from January through December 2001. Referrals were from general practitioners (n = 157), paediatricians or residents at the Children's clinic (n = 51), and from one community-based paediatrician (n = 12). The purpose was to assess the referrals for completeness and judgment before cardiological assessment. Our second goal was to see if the paediatric cardiologist could differentiate between innocent and pathological murmurs by history and clinical assessment only. RESULTS: 22 (10%) of the referred patients had congenital heart defects. They had been through a complete clinical assessment by 38.9% of the general practitioners and 83.3% by the community-based paediatrician (p = 0.0001). A conclusion regarding diagnosis before hospital evaluation was reached in only 17.8% of the patients by the general practitioners and in 50% by the paediatricians (p < 0.0001). The diagnostic accuracy of the clinical evaluation by the paediatric cardiologists had a sensitivity of 81.5%, specificity of 98.5%, positive and negative predictive values of 88 and 97.5%, respectively. Two patients with significant atrial septum defect would have been missed by clinical assessment only. INTERPRETATION: Skills in clinical assessment of heart murmurs in infants and children can be improved among general practitioners and paediatricians in training. Paediatric cardiologists can differentiate between physiological and pathologic murmurs by clinical evaluation only.

[Is transmission of heart murmurs via e-mail cost saving?]. / Er overføring av hjertebilyder via e-post kostnadsbesparende?

BACKGROUND: The use of pre-recorded heart murmur in an electronic referral for a remote consultation can save children and their parents from having to travel to the nearest out-patient clinic. The heart sound can be recorded by the GP at the local health clinic and sent by e-mail to the specialist. 41 clinics in the North Norway healt region have invested in equipment that makes pre-recorded sound referrals possible. This study analyses whether this investment is a cost-saving technology or not. METHODS: A yearly average of 50 children with a heart murmur are referred to a specialist in Troms. The costs of using pre-recorded telemedicine were compared to the costs of patient travelling to the nearest secondary care centre. RESULTS: Pre-recorded heart sound referrals cost from 216 000 NOK more per year than the alternative of bringing patients to the out-patient clinic. The number of children with a heart murmur needed in order to break even must exceed 195 per year, i.e. 1.7 children per GP per year. INTERPRETATION: The number of children with a heart murmur in Troms is too low for this method to be a cost-saving approach.

Assessment of severity of aortic stenosis through time-frequency analysis of murmur.

STUDY OBJECTIVE: The accurate and inexpensive noninvasive assessment of the presence and severity of aortic stenosis remains a challenge. In this study, we performed spectral analysis on the murmurs of a group of patients with this disease in order to assess its severity. DESIGN: An electronic stethoscope was used to generate a spectral analysis of murmurs in patients with aortic stenosis. The durations of the spectra at different frequencies (ie, 200, 250, and 300 Hz) were correlated to the Doppler echocardiogram-derived mean and peak pressure gradients. Heart murmurs from the patients were recorded, and the spectra of the recordings were produced via fast-Fourier transformation. The duration of the spectra above the three given frequencies was then measured. PATIENTS: Forty-one patients (age range, 45 to 94 years; mean age, 68 years) met the inclusion criteria, which included a minimum ejection fraction of 40% and no other significant systolic murmur or coexistent valve disease. RESULTS: The peak pressure gradient measured via Doppler echocardiogram ranged from 15.3 to 185 mm Hg with the mean of 63 mm Hg. The duration of the spectra of > 300 Hz correlated best with the peak pressure gradient measured using the Doppler echocardiogram. An exponential regression model was created showing a significant correlation coefficient of r = 0.86 (p < 0.0001). CONCLUSIONS: This study demonstrated a good correlation between the duration of spectra at 300 Hz and the Doppler derived peak pressure gradient. This simple and inexpensive technique may prove to be valuable in the evaluation and monitoring of patients with suspected and proven aortic stenosis.

Accuracy of analog telephonic stethoscopy for pediatric telecardiology.

OBJECTIVE: Wide-bandwidth electronic stethoscopy is reliable and accurate for pediatric telecardiology. We tested a much less expensive and more convenient system for the same purpose, a narrow-bandwidth telephonic stethoscope (TS). METHODS: Seventy-six consecutive patients (mean age: 10.0; standard deviation: 6.5 years) in a pediatric cardiology outpatient clinic were studied. One pediatric cardiologist examined the patients with his acoustic stethoscope (AS); a second examined them within a few minutes using a remote TS. A nurse placed the TS chest piece as directed by the remote examiner via intercom, but neither video examination nor conversation with the parent/patient were permitted. Examiners independently recorded the stethoscope findings for all heart sounds, all murmurs, and heart disease (present/absent). TS accuracy was indexed using the kappa statistic for TS/AS agreement and for TS agreement with auscultatory findings predicted from echocardiographic (echo) studies (N = 49). RESULTS: TS/AS agreement was satisfactory for presence/absence of heart disease (kappa = 0.63) and for organic, functional, vibratory, diastolic aortic, and diastolic pulmonic murmurs (kappa range: 0.65-0.75). For other specific murmurs and all heart sounds, TS/AS agreement was either unsatisfactory (kappa < or = 0.60) or indeterminate because prevalence was 0. TS-AS agreement improved when the TS was used by the more-experienced TS examiner and with patients at least 5 years of age. When the older children were examined by the more TS-experienced examiner, the TS-echo comparison yielded kappa = 0.90, raw agreement = 0.96, sensitivity = 0.94, and specificity = 1.00. CONCLUSIONS: In pediatric patients, a narrow-bandwidth telephonic stethoscope can accurately distinguish between functional and organic murmurs and thus can detect heart disease. Accuracy is greatest when the instrument is used by an experienced examiner with patients at least 5 years of age.

[Assessment of heart murmurs in childhood]. / Avaliação do sopro cardíaco na infância.

OBJECTIVE: To discuss clinical and laboratorial evaluation of heart murmurs in children, an important problem faced by pediatricians in their practice. SOURCES: This review was based on a critical analysis of the current literature, as well as pediatrics and pediatric cardiology textbooks, which were found to be an important source of information on the subject. SUMMARY OF THE FINDINGS: It is important for pediatricians to know how to obtain precise information regarding the patient's medical history and to perform extensive physical examination of a child with heart murmur. The diagnosis of innocent heart murmur is essentially clinical and it can help the pediatrician to identify situations which are associated with cardiovascular diseases. CONCLUSIONS: The pediatrician is usually the first physician to see a child with heart murmur and he should be able to distinguish between innocent and pathologic heart murmurs.

An assessment of the terminology used by diplomates and students to describe the character of equine mitral and aortic valve regurgitant murmurs: correlations with the physical properties of the sounds.

Twenty students and 16 diplomates listened to 7 recordings made from 7 horses with either aortic (n = 3) or mitral valve (n = 4) regurgitant murmurs. A total of 30 different terms were used to describe the character of these murmurs. However, only 4 terms were used in a repeatable and consistent manner. Most people described the character of a given mitral or aortic valve murmur with 1 or 2 terms. Diplomates drew from a pool of terms that was about half the size of that used by students--8.1 +/- 2.0 terms for diplomats (mean +/- 1 SD) versus 13.1 +/- 1.8 terms for students (P > .001). Only blowing, honking, buzzing, and musical were markedly associated with the recording played. Frequency analysis of the murmurs allowed them to be classified as containing harmonics (n = 4) or not containing harmonics (n = 3). Blowing was used to describe murmurs without harmonics on 39 of 48 occasions and corresponds to the term noisy used in some older descriptions of equine murmurs. Honking, musical, and buzzing were markedly associated with murmurs that contained harmonics; these terms were used 23, 13, and 12 of a possible 64 times, respectively. The frequency of buzzing and honking murmurs (72.7 +/- 9.3 and 88.4 +/- 46.3 Hz, respectively) was markedly lower than that of musical murmurs (156.8 +/- 81.1 Hz) (all P values < .01). Honking murmurs (0.392 +/- 0.092 seconds) were shorter than those described as buzzing or musical (0.496 +/- 0.205 and 0.504 +/- 0.116 seconds, respectively). The data suggest that the terminology for the character of aortic and mitral regurgitant murmurs should be restricted to 4 terms: blowing, honking, buzzing, and musical. Honking, buzzing, and musical describe murmurs with a peak dominant frequency and harmonics; blowing describes murmurs without a peak frequency. Effective communication could be enhanced by playing examples of reference sounds when these terms are taught so that nomenclature is used more uniformly.

Evaluation of heart murmurs in children: cost-effectiveness and practical implications.

OBJECTIVE: To assess the cost-effectiveness of various strategies to evaluate heart murmurs in children. METHODS: We modeled 6 strategies to follow the initial examination by the pediatrician: (1) refer suspected pathologic murmurs to a cardiologist, (2) obtain a chest radiograph (CXR) and electrocardiogram (ECG) and refer suspected pathologic murmurs to a cardiologist, (3) refer suspected pathologic murmurs for an echocardiogram (ECHO), (4) obtain a CXR and ECG and refer suspected pathologic murmurs for an ECHO, (5) refer all patients with murmurs to a cardiologist, or (6) refer all patients with murmurs for an ECHO. RESULTS: The least effective was strategy 1, which detects 82% of pathologic murmurs at $72 per patient evaluated. Strategy 5 detects 95% of pathologic murmurs at $38,000 per additional case detected over strategy 1. The most effective, strategy 6, detects 100% of pathologic murmurs at $158,000 per additional case detected over strategy 5. Strategies 2, 3, and 4 were not cost-effective. The results were sensitive to the costs of cardiology referral and ECHO. CONCLUSIONS: Adding a CXR and ECG to the pediatrician's evaluation, or selectively referring directly to ECHO increases costs with little gain in accuracy. Given the current cost constraints present in health care, whether the optimal strategy involves referring to a cardiologist or obtaining an ECHO for all patients with murmurs depends on how much society should allocate to diagnose pathologic murmurs.

Heart murmurs recorded by a sensor based electronic stethoscope and e-mailed for remote assessment.

BACKGROUND: Heart murmurs are common in children, and they are often referred to a specialist for examination. A clinically innocent murmur does not need further investigation. The referral area of the University Hospital is large and sparsely populated. A new service for remote auscultation (telemedicine) of heart murmurs in children was established where heart sounds and short texts were sent as an attachment to e-mails. AIM: To assess the clinical quality of this method. METHODS: Heart sounds from 47 patients with no murmur (n = 7), with innocent murmurs (n = 20), or with pathological murmurs (n = 20) were recorded using a sensor based stethoscope and e-mailed to a remote computer. The sounds were repeated, giving 100 cases that were randomly distributed on a compact disc. Four cardiologists assessed and categorised the cases as having "no murmur", "innocent murmur", or "pathological murmur", recorded the assessment time per case, their degree of certainty, and whether they recommended referral. RESULTS: On average, 2.1 minutes were spent on each case. The mean sensitivity and specificity were 89.7% and 98.2% respectively, and the inter-observer and intra-observer variabilities were low (kappa 0.81 and 0.87), respectively. A total of 93.4% of cases with a pathological murmur and 12.6% of cases with an innocent murmur were recommended for referral. CONCLUSION: Telemedical referral of patients with heart murmurs for remote assessment by a cardiologist is safe and saves time. Skilled auscultation is adequate to detect patients with innocent murmurs.

Opening Pandora's box: parental anxiety and the assessment of childhood murmurs.

BACKGROUND: Most family physicians and pediatricians recognize the induction of parental anxiety when a newly diagnosed childhood murmur is discussed with a child's parent. OBJECTIVES: To assess parental anxiety before and after consultation with a pediatric cardiologist for assessment of a childhood murmur. The study investigated the relationship between anxiety and parental understanding of murmurs, and assessed the possible role of the primary physician's initial diagnosis of the child's murmur on the anxiety level of parents. SUBJECTS AND METHODS: One hundred ninety-five consecutive parents who presented with their child to the Alberta Children's Hospital Cardiology Clinic, Calgary, Alberta, were recruited. The children were referred for an initial consultation with a pediatric cardiologist for assessment of a heart murmur noted previously by the referring physicians. Before consultation, the patients were divided into three murmur groups for diagnosis: innocent, pathological and unknown. Anxiety questionnaires, as well as questionnaires assessing basic parent understanding of childhood murmurs, were administered to one of the parents pre- and postconsultation. RESULTS: The initial diagnosis given to the caregiver by the primary care physician as the reason for referral did not seem to affect the level of parental anxiety within groups. As expected, postconsultation anxiety levels were significantly higher in parents whose children received a pathological diagnosis from the pediatric cardiologist. A significant drop in parental anxiety post-consultation was seen in all parent groups, including parents of a child diagnosed with a significant cardiac problem or pathology requiring further investigation and/or cardiac follow-up. There was a consistent correlation between higher scores on parental understanding and lower levels of parental anxiety. CONCLUSION: The present study confirms that the finding of a childhood murmur by the family doctor or pediatrician induces significant parental anxiety, even when the presumptive diagnosis is that of an 'innocent' murmur. Pediatric cardiology consultation decreases parental anxiety, even in parents whose child has been given a diagnosis of pathology. The correlation between poor understanding of murmurs and high parental anxiety suggests that further study is required on the role of the referring physician in augmenting parental understanding of the term 'heart murmur' and the referral process.

An assessment of the ability of diplomates, practitioners, and students to describe and interpret recordings of heart murmurs and arrhythmia.

The ability of clinicians, ie, 10 veterinary students, 10 general practitioners, and 10 board certified internists, to describe and interpret common normal and abnormal heart sounds was assessed. Recordings of heart sounds from 7 horses with a variety of normal and abnormal rhythms, heart sounds, and murmurs were analyzed by digital sonography. The perception of the presence or absence of the heart sounds S1, S2, and S4 was similar for clinicians irrespective of their level of training and was in agreement with the sonographic interpretation on 89, 82, and 78% of occasions, respectively. However, practitioners were less likely to correctly describe the presence of S3. The heart rhythm was correctly described as being regular or irregular on 89% of occasions, and this outcome was not affected by level of training. Differentiation of the type of irregularity was less reliable. The perception of the intensity of a heart murmur was accurate and correlated with the grade assigned in the living horses, R2 = .68, and with sonographic measurements of the murmur's intensity, R2 = .69. Clinicians overestimated the duration of cardiac murmurs, particularly that of the loud systolic murmur. Only diplomates could reliably differentiate systolic from diastolic murmurs. The ability to diagnose the underlying cardiac problem was significantly affected by training; diplomates, practitioners, and undergraduates made the correct diagnosis on 53, 33, and 29% of occasions, respectively. The poor diagnostic ability of practitioners and the lack of improvement in diagnostic skill after the 2nd year of veterinary school emphasizes the need for better teaching of these skills. Digital sonograms that combine sound files with synchronous visual interpretations may be useful in this regard.