scholarly journals Deep Learning Algorithm for Automated Cardiac Murmur Detection via a Digital Stethoscope Platform

2021 ◽  
Author(s):  
John S. Chorba ◽  
Avi M. Shapiro ◽  
Le Le ◽  
John Maidens ◽  
John Prince ◽  
...  
Keyword(s):  
Heart Disease ◽  
Deep Learning ◽  
Mitral Regurgitation ◽  
Aortic Stenosis ◽  
Valvular Heart Disease ◽  
Learning Algorithm ◽  
Cardiac Murmur ◽  
Significant Information ◽  
Deep Learning Algorithm ◽  
Clinically Significant

Background Clinicians vary markedly in their ability to detect murmurs during cardiac auscultation and identify the underlying pathological features. Deep learning approaches have shown promise in medicine by transforming collected data into clinically significant information. The objective of this research is to assess the performance of a deep learning algorithm to detect murmurs and clinically significant valvular heart disease using recordings from a commercial digital stethoscope platform. Methods and Results Using >34 hours of previously acquired and annotated heart sound recordings, we trained a deep neural network to detect murmurs. To test the algorithm, we enrolled 962 patients in a clinical study and collected recordings at the 4 primary auscultation locations. Ground truth was established using patient echocardiograms and annotations by 3 expert cardiologists. Algorithm performance for detecting murmurs has sensitivity and specificity of 76.3% and 91.4%, respectively. By omitting softer murmurs, those with grade 1 intensity, sensitivity increased to 90.0%. Application of the algorithm at the appropriate anatomic auscultation location detected moderate‐to‐severe or greater aortic stenosis, with sensitivity of 93.2% and specificity of 86.0%, and moderate‐to‐severe or greater mitral regurgitation, with sensitivity of 66.2% and specificity of 94.6%. Conclusions The deep learning algorithm’s ability to detect murmurs and clinically significant aortic stenosis and mitral regurgitation is comparable to expert cardiologists based on the annotated subset of our database. The findings suggest that such algorithms would have utility as front‐line clinical support tools to aid clinicians in screening for cardiac murmurs caused by valvular heart disease. Registration URL: https://clinicaltrials.gov ; Unique Identifier: NCT03458806.

scholarly journals A Deep Learning Algorithm for Automated Cardiac Murmur Detection Via a Digital Stethoscope Platform

2020 ◽  
Author(s):  
John S. Chorba ◽  
Avi M. Shapiro ◽  
Le Le ◽  
John Maidens ◽  
John Prince ◽  
...  
Keyword(s):  
Heart Disease ◽  
Deep Learning ◽  
Mitral Regurgitation ◽  
Aortic Stenosis ◽  
Valvular Heart Disease ◽  
Learning Algorithm ◽  
Cardiac Murmur ◽  
Significant Information ◽  
Deep Learning Algorithm ◽  
Clinically Significant

AbstractBackgroundThere is variability among clinicians in their ability to detect murmurs during cardiac auscultation and identify the underlying pathology. Deep learning approaches have shown promise in medicine by transforming collected data into clinically significant information.ObjectiveThe objective of this research is to assess the performance of a deep learning algorithm to detect murmurs and clinically significant valvular heart disease using recordings from a commercial digital stethoscope platform.MethodsUsing over 34 hours of previously acquired and annotated heart sound recordings, we trained a deep neural network to detect murmurs. To test the algorithm, we enrolled 373 patients in a clinical study and collected recordings at the four primary auscultation locations. Ground truth was established using patient echocardiograms and annotations by three expert cardiologists.ResultsAlgorithm performance for detecting murmurs has sensitivity and specificity of 76.3% and 91.4%, respectively. By omitting softer murmurs, those with grade 1, sensitivity increases to 90.0%. The algorithm detects moderate-to-severe or greater aortic stenosis with sensitivity of 97.5% and specificity of 77.7% and detects moderate-to-severe or greater mitral regurgitation with sensitivity of 64.0% and specificity of 90.5%.ConclusionThe deep learning algorithm’s ability to detect murmurs and clinically significant aortic stenosis and mitral regurgitation is comparable to expert cardiologists. The research findings attest to the reliability and utility of such algorithms as front-line clinical support tools to aid clinicians in screening for cardiac murmurs caused by valvular heart disease.

Valvular Heart Disease - Part II

2021 ◽  
Author(s):  
Miriam S. Jacob ◽  
Brian P Griffin
Keyword(s):  
Heart Disease ◽  
Mitral Valve ◽  
Mitral Regurgitation ◽  
Aortic Stenosis ◽  
Aortic Regurgitation ◽  
Valvular Heart Disease ◽  
Mitral Valve Prolapse ◽  
Developed Countries ◽  
Cardiac Morbidity ◽  
Mechanical Prostheses

Valvular heart disease is an important cause of cardiac morbidity in developed countries despite a decline in the prevalence of rheumatic disease in those countries. This chapter discusses the many etiologies of valvular heart disease and presents methods for assessment and management. Specific valvular lesions discussed include mitral stenosis, mitral regurgitation, mitral valve prolapse, aortic stenosis, aortic regurgitation, and tricuspid and pulmonary disease. The section on tricuspid disease includes a discussion of mechanical prostheses (ball-in-cage and tilting-disk) and biologic prostheses (xenografts, allografts, and autografts) and their complications.  This review contains 5 figures, 9 tables, and 53 references. Keywords: Valvular heart disease, stenosis, regurgitation, mitral regurgitation, mitral valve prolapse (MVP), aortic stenosis, congenital bicuspid valve, senile valvular calcification, aortic regurgitation, chordae or papillary muscles

scholarly journals Contemporary Presentation and Management of Valvular Heart Disease

Circulation ◽  
2019 ◽  
Vol 140 (14) ◽  
pp. 1156-1169 ◽  
Author(s):  
Bernard Iung ◽  
Victoria Delgado ◽  
Raphael Rosenhek ◽  
Susanna Price ◽  
Bernard Prendergast ◽  
...  
Keyword(s):  
Heart Disease ◽  
Mitral Regurgitation ◽  
Aortic Stenosis ◽  
Aortic Regurgitation ◽  
European Society ◽  
Valvular Heart Disease ◽  
Mitral Stenosis ◽  
Heart Association ◽  
Class I ◽  
European Society Of Cardiology

Background: Valvular heart disease (VHD) is an important cause of mortality and morbidity and has been subject to important changes in management. The VHD II survey was designed by the EURObservational Research Programme of the European Society of Cardiology to analyze actual management of VHD and to compare practice with guidelines. Methods: Patients with severe native VHD or previous valvular intervention were enrolled prospectively across 28 countries over a 3-month period in 2017. Indications for intervention were considered concordant if the intervention was performed or scheduled in symptomatic patients, corresponding to Class I recommendations specified in the 2012 European Society of Cardiology and in the 2014 American Heart Association/American College of Cardiology VHD guidelines. Results: A total of 7247 patients (4483 hospitalized, 2764 outpatients) were included in 222 centers. Median age was 71 years (interquartile range, 62–80 years); 1917 patients (26.5%) were ≥80 years; and 3416 were female (47.1%). Severe native VHD was present in 5219 patients (72.0%): aortic stenosis in 2152 (41.2% of native VHD), aortic regurgitation in 279 (5.3%), mitral stenosis in 234 (4.5%), mitral regurgitation in 1114 (21.3%; primary in 746 and secondary in 368), multiple left-sided VHD in 1297 (24.9%), and right-sided VHD in 143 (2.7%). Two thousand twenty-eight patients (28.0%) had undergone previous valvular intervention. Intervention was performed in 37.0% and scheduled in 26.8% of patients with native VHD. The decision for intervention was concordant with Class I recommendations in symptomatic patients with severe single left-sided native VHD in 79.4% (95% CI, 77.1–81.6) for aortic stenosis, 77.6% (95% CI, 69.9–84.0) for aortic regurgitation, 68.5% (95% CI, 60.8–75.4) for mitral stenosis, and 71.0% (95% CI, 66.4–75.3) for primary mitral regurgitation. Valvular interventions were performed in 2150 patients during the survey; of them, 47.8% of patients with single left-sided native VHD were in New York Heart Association class III or IV. Transcatheter procedures were performed in 38.7% of patients with aortic stenosis and 16.7% of those with mitral regurgitation. Conclusions: Despite good concordance between Class I recommendations and practice in patients with aortic VHD, the suboptimal number in mitral VHD and late referral for valvular interventions suggest the need to improve further guideline implementation.

scholarly journals Natriuretic Peptide Release during Exercise in Patients with Valvular Heart Disease: a Systematic Review.

2020 ◽  
Author(s):  
Sveeta Badiani ◽  
Jet van Zalen ◽  
Aeshah Althunayyan ◽  
Sahar Al-borikan ◽  
Thomas Treibel ◽  
...  
Keyword(s):  
Systematic Review ◽  
Heart Disease ◽  
Mitral Regurgitation ◽  
Aortic Stenosis ◽  
Natriuretic Peptide ◽  
Valvular Heart Disease ◽  
Blood Pressure Response ◽  
Heart Valve Disease ◽  
Optimal Timing ◽  
The Relationship

Aims Serum biomarkers have a potential role in the risk stratification of patients with heart valve disease and may help determine the optimal timing of intervention. Much of the published literature relates to biomarker sampling in a resting state, but the relationship of exercise biomarkers is less well described. We performed a systematic review to examine the significance of exercise natriuretic peptides on echocardiographic variables and cardiovascular events, in valvular heart disease. Methods A search for studies that assessed exercise biomarkers in patients with moderate to severe valve lesions was performed. We examined the relationship between rest and exercise BNP and also the endpoints of symptoms, haemodynamic or echocardiographic variables and clinical outcomes. Results 11 prospective studies were identified (844 participants). 61% were male and the mean age was 55.2 ± 9.6 years. The majority of the blood samples were taken at baseline and within 3 minutes of stopping exercise. There was a significant increase in exercise BNP compared with rest, in patients with aortic stenosis, mitral regurgitation and mitral stenosis. Elevated exercise BNP levels correlated with mean gradient and left atrial area, and there was a relationship between a higher exercise BNP and a blunted blood pressure response, in aortic stenosis. Furthermore, exercise BNP was independently associated with cardiac events, over and above resting values, in patients with mitral regurgitation and aortic stenosis. Conclusions The results suggesting that exercise natriuretic peptide levels may have additive prognostic importance over resting levels, as well as demographic and echocardiographic data.

Valvular heart disease

2012 ◽  
Keyword(s):  
Heart Disease ◽  
Mitral Valve ◽  
Mitral Regurgitation ◽  
Aortic Stenosis ◽  
Rheumatic Fever ◽  
Aortic Regurgitation ◽  
Valvular Heart Disease ◽  
Mitral Valve Prolapse ◽  
Mitral Stenosis ◽  
Acute Rheumatic Fever

General considerations 144Acute rheumatic fever 146Mitral stenosis: clinical features 150Mitral stenosis: investigations 152Mitral stenosis guidelines 156Mitral regurgitation 158Mitral regurgitation guidelines 161Mitral valve prolapse 162Aortic stenosis 164Management of aortic stenosis 168Aortic regurgitation 170Aortic regurgitation guidelines ...

Thromboembolism and bleeding complications in anticoagulated patients with atrial fibrillation and native aortic or mitral valvular heart disease: a descriptive nationwide cohort study

2020 ◽  
Author(s):  
Line Melgaard ◽  
Thure Filskov Overvad ◽  
Martin Jensen ◽  
Gregory Y H Lip ◽  
Torben Bjerregaard Larsen ◽  
...  
Keyword(s):  
Heart Disease ◽  
Mitral Regurgitation ◽  
Aortic Stenosis ◽  
Major Bleeding ◽  
Valvular Heart Disease ◽  
Mitral Stenosis ◽  
Vitamin K Antagonist ◽  
Bleeding Complications ◽  
Using Data ◽  
Anticoagulated Patients

Abstract Aims To describe the risks of thromboembolism and major bleeding complications in anticoagulated patients with atrial fibrillation (AF) and native aortic or mitral valvular heart disease using data reflecting clinical practice. Methods and results Descriptive cohort study of anticoagulated patients with incident AF and native aortic or mitral valvular heart disease, identified in nationwide Danish registries from 2000 to 2018. A total of 10 043 patients were included, of which 5190 (51.7%) patients had aortic stenosis, 1788 (17.8%) patients had aortic regurgitation, 327 (3.3%) patients had mitral stenosis, and 2738 (27.3%) patients had mitral regurgitation. At 1 year after AF diagnosis, the risk of thromboembolism was 4.6% in patients with mitral stenosis taking a vitamin K antagonist (VKA), and 2.6% in patients with aortic stenosis taking a VKA or non-vitamin K antagonist oral anticoagulant (NOAC). For patients with aortic or mitral regurgitation, the risks of thromboembolism ranged between 1.5%-1.8% in both treatment groups. For the endpoint of major bleeding, the risk was ∼5.5% in patients with aortic stenosis or mitral stenosis treated with a VKA, and 3.3–4.0% in patients with aortic or mitral regurgitation. For patients treated with a NOAC, the risk of major bleeding was 3.7% in patients with aortic stenosis and ∼2.5% in patients with aortic or mitral regurgitation. Conclusion When using data reflecting contemporary clinical practice, our observations suggested that 1 year after a diagnosis of AF, anticoagulated patients with aortic or mitral valvular heart disease had dissimilar risk of thromboembolism and major bleeding complications. Specifically, patients with aortic stenosis or mitral stenosis were high-risk subgroups. This observation may guide clinicians regarding intensity of clinical follow-up.

scholarly journals Deep Learning-Based Assessment of Adverse Cardiovascular Events in Elderly Patients with Coronary Heart Disease after Percutaneous Coronary Intervention Using Intravascular Ultrasound Images

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Shu Wang
Keyword(s):  
Coronary Heart Disease ◽  
Heart Disease ◽  
Deep Learning ◽  
Cardiovascular Events ◽  
Learning Algorithm ◽  
Density Lipoprotein ◽  
Coronary Intervention ◽  
Deep Learning Algorithm ◽  
Percutaneous Coronary ◽  
Sensitivity Specificity

This study aimed to analyze the risk factors of adverse cardiovascular events (ACVEs) in elderly patients with coronary heart disease (CHD) after percutaneous coronary intervention (PCI) using the intravascular ultrasound (IVUS) images based on the deep learning of convolutional neural networks (CNNs). This study included 90 patients with coronary heart disease as the research object. All the patients were randomly divided into a control group (group C) and an experimental group (group E), and all were treated with PCI. The patients in group C were diagnosed by angiography, and patients in group E underwent IVUS examination under deep learning. The levels of blood lipids and inflammatory factors between the two groups before and after PCI were compared, and the sensitivity, specificity, and positive predictive value (PPV) were recorded. Compared with angiography diagnosis, ultrasound diagnosis based on deep learning algorithm had higher sensitivity (92.3% vs. 81.4%), specificity (90.1% vs. 88.6%), and PPV (94.8% vs. 75.3%) ( P < 0.05 ). Compared with group C, patients in group E had a higher narrowest lesion diameter (2.54 ± 0.18 mm vs. 2.21 ± 0.19 mm) and detection rate of eccentric plaques (80.1% vs. 45.3%) ( P < 0.05 ). High-density lipoprotein cholesterol (HDL-C) after PCI in the two groups was significantly higher than that before surgery, while low-density lipoprotein cholesterol (LDL-C), tumor necrosis factor (TNF), and C-reactive protein (CRP) were significantly lower than those before surgery, and the difference was statistically significant ( P < 0.05 ). In short, the ultrasonic detection method based on deep learning algorithm has high sensitivity, specificity, and accuracy for CHD detection; PCI can improve the patient’s blood lipid level, relieve the patient’s inflammation, and reduce the occurrence of ACVEs in the patient.

scholarly journals Type of Valvular Heart Disease Requiring Surgery in the 21st Century: Mortality and Length-of-Stay Related to Surgery

2013 ◽  
Vol 7 (1) ◽  
pp. 104-109 ◽  
Author(s):  
Konstantinos Dean Boudoulas ◽  
Yazhini Ravi ◽  
Daniel Garcia ◽  
Uksha Saini ◽  
Gbemiga G. Sofowora ◽  
...  
Keyword(s):  
Heart Disease ◽  
Mitral Valve ◽  
Length Of Stay ◽  
Mitral Regurgitation ◽  
Aortic Stenosis ◽  
Valvular Heart Disease ◽  
Aortic Insufficiency ◽  
Mitral Valve Surgery ◽  
Valve Surgery ◽  
Surgical Mortality

Aim: While the incidence of rheumatic heart disease has declined dramatically over the last half-century, the number of valve surgeries has not changed. This study was undertaken to define the most common type of valvular heart disease requiring surgery today, and determine in-hospital surgical mortality and length-of-stay (LOS) for isolated aortic or mitral valve surgery in a United States tertiary-care hospital. Methods: Patients with valve surgery between January 2002 to June 2008 at The Ohio State University Medical Center were studied. Patients only with isolated aortic or mitral valve surgery were analyzed. Results: From 915 patients undergoing at least aortic or mitral valve surgery, the majority had concomitant cardiac proce-dures mostly coronary artery bypass grafting (CABG); only 340 patients had isolated aortic (n=204) or mitral (n=136) valve surgery. In-hospital surgical mortality for mitral regurgitation (n=119), aortic stenosis (n=151), aortic insufficiency (n=53) and mitral stenosis (n=17) was 2.5% (replacement 3.4%; repair 1.6%), 3.9%, 5.6% and 5.8%, respectively (p=NS). Median LOS for aortic insufficiency, aortic stenosis, mitral regurgitation, and mitral stenosis was 7, 8, 9 (replacement 11.5; repair 7) and 11 days, respectively (p<0.05 for group). In-hospital surgical mortality for single valve surgery plus CABG was 10.2% (p<0.005 compared to single valve surgery). Conclusions: Aortic stenosis and mitral regurgitation are the most common valvular lesions requiring surgery today. Surgery for isolated aortic or mitral valve disease has low in-hospital mortality with modest LOS. Concomitant CABG with valve surgery increases mortality substantially. Hospital analysis is needed to monitor quality and stimulate improvement among Institutions.

Valvular Heart Disease - Part I

2021 ◽  
Author(s):  
Miriam S. Jacob ◽  
Brian P Griffin
Keyword(s):  
Heart Disease ◽  
Mitral Valve ◽  
Mitral Regurgitation ◽  
Aortic Stenosis ◽  
Aortic Regurgitation ◽  
Valvular Heart Disease ◽  
Mitral Valve Prolapse ◽  
Developed Countries ◽  
Cardiac Morbidity ◽  
Mechanical Prostheses

Valvular heart disease is an important cause of cardiac morbidity in developed countries despite a decline in the prevalence of rheumatic disease in those countries. This chapter discusses the many etiologies of valvular heart disease and presents methods for assessment and management. Specific valvular lesions discussed include mitral stenosis, mitral regurgitation, mitral valve prolapse, aortic stenosis, aortic regurgitation, and tricuspid and pulmonary disease. The section on tricuspid disease includes a discussion of mechanical prostheses (ball-in-cage and tilting-disk) and biologic prostheses (xenografts, allografts, and autografts) and their complications.  This review contains 6 figures, 13 tables, 69 references. Keywords: Valvular heart disease, stenosis, regurgitation, mitral regurgitation, mitral valve prolapse (MVP), aortic stenosis, congenital bicuspid valve, senile valvular calcification, aortic regurgitation, chordae or papillary muscles

scholarly journals The Evolving Epidemiology of Elderly with Degenerative Valvular Heart Disease: The Guangzhou (China) Heart Study

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Shangfei He ◽  
Hai Deng ◽  
Junrong Jiang ◽  
Fangzhou Liu ◽  
Hongtao Liao ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Heart Disease ◽  
Mitral Regurgitation ◽  
Aortic Stenosis ◽  
Renal Insufficiency ◽  
Pressure Gradient ◽  
Tricuspid Regurgitation ◽  
Valvular Heart Disease ◽  
Southern China ◽  
The Mean

Aim. The present study was aimed at investigating the prevalence, incidence, progression, and prognosis of degenerative valvular heart disease (DVHD) in permanent residents aged ≥65 years from Guangzhou, China. Methods. This was a prospective study based on community population. Over a 3-year span, we conducted repeated questionnaires, blood tests, and echocardiographic and electrocardiogram examinations (2018) of a random sample of initially 3538 subjects. Results. The prevalence of DVHD increased with age, average values being 30.6%, 49.2%, and 62.9% in 65-74, 75-84, and ≥85 years of age, respectively. The incidence rate was 1.7%/year. Aortic stenosis was the result of DVHD, and the mean transvalvular pressure gradient increased by 5.6 mmHg/year. The increase of mild aortic stenosis was lower than that of more severe disease, showing a nonlinear development of gradient, but with great individual variations. Mortality was significantly increased in the DVHD group ( HR = 2.49 ). Risk factors for higher mortality included age ( χ 2 = 1.9 , P < 0.05 ), renal insufficiency ( χ 2 = 12.5 , P < 0.01 ), atrial fibrillation ( χ 2 = 12.2 , P < 0.01 ), mitral regurgitation ( χ 2 = 1.8 , P < 0.05 ), and tricuspid regurgitation ( χ 2 = 6.7 , P < 0.05 ) in a DVHD population. Conclusions. DVHD was highly prevalent among residents in southern China. With the progression of the disease, the mean transvalvular pressure gradient accelerated. DVHD was an independent predictor of death, and the mortality was higher in those with older age, renal insufficiency, atrial fibrillation, mitral regurgitation, and tricuspid regurgitation.

Sign in / Sign up

Export Citation Format

Share Document