-
Journal of the American Heart... Oct 2023Background The success of cardiac auscultation varies widely among medical professionals, which can lead to missed treatments for structural heart disease. Applying...
Background The success of cardiac auscultation varies widely among medical professionals, which can lead to missed treatments for structural heart disease. Applying machine learning to cardiac auscultation could address this problem, but despite recent interest, few algorithms have been brought to clinical practice. We evaluated a novel suite of Food and Drug Administration-cleared algorithms trained via deep learning on >15 000 heart sound recordings. Methods and Results We validated the algorithms on a data set of 2375 recordings from 615 unique subjects. This data set was collected in real clinical environments using commercially available digital stethoscopes, annotated by board-certified cardiologists, and paired with echocardiograms as the gold standard. To model the algorithm in clinical practice, we compared its performance against 10 clinicians on a subset of the validation database. Our algorithm reliably detected structural murmurs with a sensitivity of 85.6% and specificity of 84.4%. When limiting the analysis to clearly audible murmurs in adults, performance improved to a sensitivity of 97.9% and specificity of 90.6%. The algorithm also reported timing within the cardiac cycle, differentiating between systolic and diastolic murmurs. Despite optimizing acoustics for the clinicians, the algorithm substantially outperformed the clinicians (average clinician accuracy, 77.9%; algorithm accuracy, 84.7%.) Conclusions The algorithms accurately identified murmurs associated with structural heart disease. Our results illustrate a marked contrast between the consistency of the algorithm and the substantial interobserver variability of clinicians. Our results suggest that adopting machine learning algorithms into clinical practice could improve the detection of structural heart disease to facilitate patient care.
Topics: Adult; Humans; Deep Learning; Heart Murmurs; Heart Diseases; Heart Auscultation; Algorithms
PubMed: 37830333
DOI: 10.1161/JAHA.123.030377 -
Circulation Journal : Official Journal... Feb 2022Coexistent pulmonary hypertension with severe aortic stenosis confers a greater risk of mortality for patients undergoing transcatheter aortic valve replacement (TAVR)....
BACKGROUND
Coexistent pulmonary hypertension with severe aortic stenosis confers a greater risk of mortality for patients undergoing transcatheter aortic valve replacement (TAVR). In this patient population, the impact of significant decoupling between pulmonary artery diastolic and pulmonary capillary wedge, as it relates to clinical risk, remained uncertain.Methods and Results:Patients with severe aortic stenosis who underwent TAVR and completed pre-procedural and post-procedural invasive hemodynamic assessments with right heart catheterization were retrospectively assessed. The impact of post-TAVR decoupling, defined as a pressure difference ≥3 mmHg, on 2-year all-cause mortality or risk of heart failure admission was analyzed. Among 77 included patients (median age 86 years, 23 men), 16 had post-TAVR decoupling. The existence of post-TAVR decoupling was associated with a higher cumulative incidence of the primary endpoint (44% vs. 7%, P=0.001), with an adjusted hazard ratio of 5.87 (95% confidence interval 1.58-21.9, P=0.008).
CONCLUSIONS
A greater risk of worse outcomes in those with post-TAVR decoupling was observed. A therapeutic strategy for post-TAVR decoupling and its clinical implication need to be created and investigated in the future.
Topics: Aged, 80 and over; Aortic Valve; Aortic Valve Stenosis; Heart Murmurs; Humans; Male; Pulmonary Artery; Pulmonary Wedge Pressure; Retrospective Studies; Risk Factors; Severity of Illness Index; Transcatheter Aortic Valve Replacement; Treatment Outcome
PubMed: 34602582
DOI: 10.1253/circj.CJ-21-0573 -
Turkish Journal of Urology Jul 2019The aim of this study was to evaluate the prevalence of innocent heart murmurs in children affected by nocturnal enuresis (NE).
OBJECTIVE
The aim of this study was to evaluate the prevalence of innocent heart murmurs in children affected by nocturnal enuresis (NE).
RESULTS
The prevalence of innocent heart murmurs in G2 was 6.34%. This condition was significantly more frequent in children who suffered from NE. Indeed, in G1, the prevalence of innocent heart murmurs was 21.45%, although there were few differences between the children with monosymptomatic NE and non-monosymptomatic NE; moreover, this prevalence was higher in males.
MATERIAL AND METHODS
We enrolled a total of 401 children (G1), 300 males and 101 females, aged 5-15 years, affected by NE and referred to the Service of Pediatrics, "Campus Bio-Medico" University Hospital of Rome, from September 2013 to September 2018, into the study. The control group was composed of 394 children without NE (G2). The study was carried out in compliance with the Helsinki Declaration.
CONCLUSION
These findings made us aware of the presence of possible underlying mechanisms, which explain the association between a higher prevalence of innocent heart murmurs and enuresis, and further studies are required to explore this issue.
PubMed: 30817273
DOI: 10.5152/tud.2019.16363 -
Heart (British Cardiac Society) Sep 2020
Topics: Adult; Heart Atria; Heart Murmurs; Heart Neoplasms; Hemangiosarcoma; Humans; Magnetic Resonance Imaging; Male; Multimodal Imaging; Positron-Emission Tomography; Predictive Value of Tests
PubMed: 32788289
DOI: 10.1136/heartjnl-2020-316736 -
Journal of Veterinary Cardiology : the... Aug 2017To assess the prevalence of functional ejection murmurs and murmurs of mitral regurgitation (MR) due to myxomatous mitral valve disease in healthy whippets; to assess...
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).
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 were calculated and correlated to age. Accuracy of auscultation to predict MR was calculated.
RESULTS
Left-sided systolic heart murmurs were detected in 185/200 (93%) of dogs. Left apical systolic murmurs (L) were detected in 57/200 (29%) and left basilar systolic murmurs (L) in 128/200 of the dogs (64%). MR was present in 76/200 (38%) dogs. Prevalence MR 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 predicted MR with sensitivity 65%, specificity 94%, positive predictive value 86%, and negative predictive value 81%; and accuracy improved when only dogs with more intense L (grade ≥ 3/6) were considered.
CONCLUSIONS
Systolic murmurs are common in North American Whippets and this breed exhibits a high prevalence of MR, which may be documented at a relatively early age. Whippets with non-clinical MR 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.
Topics: Animals; Cross-Sectional Studies; Dog Diseases; Dogs; Echocardiography; Female; Heart Murmurs; Male; Mitral Valve; Mitral Valve Insufficiency; Prevalence; United States
PubMed: 28666945
DOI: 10.1016/j.jvc.2017.04.004 -
Biomedical Engineering Online Aug 2018There are two major challenges in automated heart sound analysis: segmentation and classification. An efficient segmentation is capable of providing valuable diagnostic...
BACKGROUND
There are two major challenges in automated heart sound analysis: segmentation and classification. An efficient segmentation is capable of providing valuable diagnostic information of patients. In addition, it is crucial for some feature-extraction based classification methods. Therefore, the segmentation of heart sound is of significant value.
METHODS
This paper presents an automatic heart sound segmentation method that combines the time-domain analysis, frequency-domain analysis and time-frequency-domain analysis. Employing this method, the boundaries of heart sound components are first located, and the components are then recognized. Finally, the heart sounds are divided into several segments on the basis of the results of boundary localization and component identification.
RESULTS
In order to evaluate the performance of the proposed method, quantitative experiments are performed on an authoritative heart sound database. The experimental results show that the boundary localization has a sensitivity (Se) of 100%, a positive predictive value (PPV) of 99.3% and an accuracy (Acc) of 99.93%. Moreover, the Se, PPV and Acc of component identification reach 98.63, 99.86 and 98.49%, respectively.
CONCLUSION
The proposed method shows reliable performance on the segmentation of heart sounds. Compared with previous works, this method can be applied to not only normal heart sounds, but also the sounds with S3, S4 and murmurs, thus greatly increasing the applied range.
Topics: Automation; Heart Murmurs; Heart Sounds; Signal Processing, Computer-Assisted
PubMed: 30081909
DOI: 10.1186/s12938-018-0538-9 -
Nature Reviews. Cardiology Jul 2021
Topics: Artificial Intelligence; Heart Murmurs; Humans
PubMed: 33976396
DOI: 10.1038/s41569-021-00567-8 -
Heart (British Cardiac Society) Jul 2016An asymptomatic 29-year-old woman presented for prenatal counselling. She had a history of a heart murmur since childhood and a previous echocardiogram suggesting...
CLINICAL INTRODUCTION
An asymptomatic 29-year-old woman presented for prenatal counselling. She had a history of a heart murmur since childhood and a previous echocardiogram suggesting 'enlargement of the heart'. Physical exam revealed normal jugular venous pressure and contour. Precordial palpation was unremarkable. Auscultation, however, was abnormal; findings on inspiration and expiration are presented in Figure 1, sound clip.
QUESTION
Based on the phonocardiogram and online supplementary audio clip, which of the following is correct? An early diastolic filling sound (S3) is heard, indicating increased right ventricular filling pressures.An ejection click without respiratory variation and a systolic ejection murmur are heard, consistent with bicuspid aortic valve stenosis.An ejection click with respiratory variation and a systolic ejection murmur are heard, consistent with pulmonic valve stenosis.A holosystolic murmur with inspiratory augmentation is heard, indicating tricuspid regurgitation.
Topics: Adult; Echocardiography; Electrocardiography; Female; Heart Murmurs; Humans; Phonocardiography; Pregnancy; Pregnancy Complications, Cardiovascular; Prenatal Care; Pulmonary Valve Stenosis
PubMed: 26919867
DOI: 10.1136/heartjnl-2015-309131 -
Journal of Healthcare Engineering 2020Heart auscultation is a convenient tool for early diagnosis of heart diseases and is being developed to be an intelligent tool used in online medicine. Currently, there...
Heart auscultation is a convenient tool for early diagnosis of heart diseases and is being developed to be an intelligent tool used in online medicine. Currently, there are few studies on intelligent diagnosis of pediatric murmurs due to congenital heart disease (CHD). The purpose of the study was to develop a method of intelligent diagnosis of pediatric CHD murmurs. Phonocardiogram (PCG) signals of 86 children were recorded with 24 children having normal heart sounds and 62 children having CHD murmurs. A segmentation method based on the discrete wavelet transform combined with Hadamard product was implemented to locate the first and the second heart sounds from the PCG signal. Ten features specific to CHD murmurs were extracted as the input of classifier after segmentation. Eighty-six artificial neural network classifiers were composed into a classification system to identify CHD murmurs. The accuracy, sensitivity, and specificity of diagnosis for heart murmurs were 93%, 93.5%, and 91.7%, respectively. In conclusion, a method of intelligent diagnosis of pediatric CHD murmurs is developed successfully and can be used for online screening of CHD in children.
Topics: Adolescent; Algorithms; Child; Child, Preschool; Heart Auscultation; Heart Defects, Congenital; Heart Murmurs; Humans; Infant; Neural Networks, Computer; Signal Processing, Computer-Assisted; Wavelet Analysis
PubMed: 32454963
DOI: 10.1155/2020/9640821 -
European Heart Journal. Cardiovascular... Sep 2022The left atrium (LA) has a pivotal role in cardiac performance and LA deformation is a well-known prognostic predictor in several clinical conditions including heart...
AIMS
The left atrium (LA) has a pivotal role in cardiac performance and LA deformation is a well-known prognostic predictor in several clinical conditions including heart failure with reduced ejection fraction. The aim of this study is to investigate the effect of cardiac resynchronization therapy (CRT) on both LA morphology and function and to assess the impact of LA reservoir strain (LARS) on left ventricular (LV) systolic and diastolic remodelling after CRT.
METHODS AND RESULTS
Two hundred and twenty-one CRT-candidates were prospectively included in the study in four tertiary centres and underwent echocardiography before CRT-implantation and at 6-month follow-up (FU). CRT-response was defined by a 15% reduction in LV end-systolic volume. LV systolic and diastolic remodelling were defined as the percent reduction in LV end-systolic and end-diastolic volume at FU. Indexed LA volume (LAVI) and LV-global longitudinal (GLS) strain were the main parameters correlated with LARS, with LV-GLS being the strongest determinant of LARS (r = -0.59, P < 0.0001). CRT induced a significant improvement in LAVI and LARS in responders (both P < 0.0001). LARS was an independent predictor of both LV systolic and diastolic remodelling at follow-up (r = -0.14, P = 0.049 and r = -0.17, P = 0.002, respectively).
CONCLUSION
CRT induces a significant improvement in LAVI and LARS in responders. In CRT candidates, the evaluation of LARS before CRT delivery is an independent predictor of LV systolic and diastolic remodelling at FU.
Topics: Cardiac Resynchronization Therapy; Diastole; Echocardiography; Heart Atria; Heart Failure; Heart Murmurs; Heart Ventricles; Humans; Treatment Outcome; Ventricular Dysfunction, Left
PubMed: 34432006
DOI: 10.1093/ehjci/jeab163