-
Journal of the American Heart... May 2021Background Clinicians vary markedly in their ability to detect murmurs during cardiac auscultation and identify the underlying pathological features. Deep learning...
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.
Topics: Adolescent; Adult; Aged; Aged, 80 and over; Algorithms; Cross-Sectional Studies; Deep Learning; Diagnosis, Computer-Assisted; Equipment Design; Female; Heart Auscultation; Heart Murmurs; Humans; Male; Middle Aged; Reproducibility of Results; Stethoscopes; Young Adult
PubMed: 33899504
DOI: 10.1161/JAHA.120.019905 -
BioMed Research International 2022Most researchers use features of diastolic murmurs to identify coronary artery disease. However, the diastolic murmurs of coronary artery disease are usually very weak...
Most researchers use features of diastolic murmurs to identify coronary artery disease. However, the diastolic murmurs of coronary artery disease are usually very weak and are easily contaminated by noise and valvular murmurs. Therefore, the diagnostic accuracy of coronary artery disease when only using diastolic murmurs is not well. An algorithm for improving the accuracy in the identification of coronary artery disease by combining the features of the first heart sound and diastolic murmurs was proposed. Firstly, a first heart sound feature extraction algorithm was used to identify coronary artery disease from noncoronary artery disease. Secondly, the Empirical Wavelet Transform algorithm was used to decompose the diastolic heart sound into three modes, and the spectral energy of each mode was calculated to distinguish coronary artery disease from noncoronary artery disease. Then, the features of the fist heart sound, the second diastolic spectral energy, and the parameter P3, which was used to discriminate the diastolic murmurs in coronary artery disease and in valvular disease, were combined together to improve the diagnostic accuracy of coronary artery disease. The comparison experiment results show that the accuracy of the proposed algorithm is superior to some state-of-the-art methods when they are used to diagnose coronary artery disease.
Topics: Algorithms; Coronary Artery Disease; Heart Murmurs; Heart Sounds; Humans; Wavelet Analysis
PubMed: 35252442
DOI: 10.1155/2022/3058835 -
Echocardiography (Mount Kisco, N.Y.) Nov 2022Left ventricular diastolic dysfunction (LVDD) is associated with poor outcomes in the intensive care unit (ICU). Nonetheless, precise reporting of LVDD in COVID-19...
PURPOSE
Left ventricular diastolic dysfunction (LVDD) is associated with poor outcomes in the intensive care unit (ICU). Nonetheless, precise reporting of LVDD in COVID-19 patients is currently lacking and assessment could be challenging.
METHODS
We performed an echocardiography study in COVID-19 patients admitted to ICU with the aim to describe the feasibility of full or simplified LVDD assessment and its incidence. We also evaluated the association of LVDD or of single echocardiographic parameters with hospital mortality.
RESULTS
Between 06.10.2020 and 18.02.2021, full diastolic assessment was feasible in 74% (n = 26/35) of patients receiving a full echocardiogram study. LVDD incidence was 46% (n = 12/26), while the simplified assessment produced different results (incidence 81%, n = 21/26). Nine patients with normal function on full assessment had LVDD with simplified criteria (grade I = 2; grade II = 3; grade III = 4). Nine patients were hospital-survivors (39%); the incidence of LVDD (full assessment) was not different between survivors (n = 2/9, 22%) and non-survivors (n = 10/17, 59%; p = .11). The E/e' ratio lateral was lower in survivors (7.4 [3.6] vs. non-survivors 10.5 [6.3], p = .03). We also found that s' wave was higher in survivors (average, p = .01).
CONCLUSION
In a small single-center study, assessment of LVDD according to the latest guidelines was feasible in three quarters of COVID-19 patients. Non-survivors showed a trend toward greater LVDD incidence; moreover, they had significantly worse s' values (all) and higher E/e' ratio (lateral).
Topics: Humans; Incidence; COVID-19; Feasibility Studies; Ventricular Function, Left; Diastole; Ventricular Dysfunction, Left; Intensive Care Units; Heart Murmurs
PubMed: 36200491
DOI: 10.1111/echo.15462 -
JAMA Cardiology Apr 2018Hutchinson-Gilford progeria syndrome (HGPS) is an ultrarare disorder associated with premature death due to cardiovascular events during the second decade of life.... (Observational Study)
Observational Study
IMPORTANCE
Hutchinson-Gilford progeria syndrome (HGPS) is an ultrarare disorder associated with premature death due to cardiovascular events during the second decade of life. However, because of its rarity (107 identified living patients), the natural history of cardiac disease remains uncharacterized. Therefore, meaningful cardiac end points for clinical trials have been difficult to establish.
OBJECTIVE
To examine the course of appearance of cardiac abnormalities in patients with HGPS to identify meaningful cardiac end points for use in future clinical trials.
DESIGN, SETTING, AND PARTICIPANTS
In this prospective, cross-sectional, observational study, 27 consecutive patients with clinically and genetically confirmed classic HGPS were evaluated at a single center for 1 visit from July 1, 2014, through February 29, 2016, before initiation of treatment.
EXPOSURE
Classic HGPS.
MAIN OUTCOMES AND MEASURES
Echocardiography was used to assess ventricular and valve function using standard techniques. Diastolic left ventricular (LV) function was assessed using tissue Doppler imaging. Previously published normative data were used to adjust findings to age and body size.
RESULTS
This study included 27 patients (median age, 5.6 years; age range, 2-17 years; 15 [56%] male). Among echocardiographic indicators, LV diastolic dysfunction, defined as a tissue Doppler septal or lateral early velocity z score less than -2, was the most prevalent abnormality, seen in 16 patients (59%). Diastolic dysfunction was seen in all age groups, and its prevalence increased with age, mirroring findings seen during normal aging. Indicators of LV diastolic function were more abnormal in older patients. The z scores for lateral and septal early velocities were lower (r = -0.77, P < .001; and r = -0.66, P < .001, respectively), whereas those for the ratio of early mitral inflow velocity to early diastolic tissue Doppler myocardial velocity were higher (r = 0.80, P < .001; and r = 0.72, P < .001, respectively) in older patients. Other echocardiographic findings, including LV hypertrophy, LV systolic dysfunction, and valve disease, were less prevalent in the first decade and were seen more frequently in the second decade.
CONCLUSIONS AND RELEVANCE
In this largest-to-date cohort of patients with HGPS, LV diastolic dysfunction was the most prevalent echocardiographic abnormality and its prevalence increased with aging. Echocardiographic indicators of LV diastolic function may be useful end points in future clinical trials in this patient population.
Topics: Adolescent; Blood Pressure; Child; Child, Preschool; Cross-Sectional Studies; Echocardiography; Electrocardiography; Female; Heart; Heart Murmurs; Humans; Male; Myocardium; Progeria; Prospective Studies; Pulse Wave Analysis
PubMed: 29466530
DOI: 10.1001/jamacardio.2017.5235 -
Veterinary Research Forum : An... Sep 2022Heart murmurs and valvular regurgitation are common in horses and often have no effect on their performance. However, when structural changes occur in the heart size,...
Heart murmurs and valvular regurgitation are common in horses and often have no effect on their performance. However, when structural changes occur in the heart size, they can affect performance adversely. This study aimed to examine the correlation between cardiac valves disease and poor performance in athletic horses. A total of 300 athletic Thoroughbred and mix-breed horses including 164 mares and 136 stallions, with a history of poor performance, were selected. Horses with cardiac murmurs were identified and further cardiac examination including precise auscultation, base-apex electrocardiogram for possible dysrhythmias at rest and after exercise, echocardiographic and hematological tests were conducted in two stages. The first was at admission time and the second examination was done four to six months later to evaluate the outcome of the possible disorders. Respiratory system and musculoskeletal diseases were diagnosed respectively in 93 and 149 out of 300 examined horses and 36 horses showed heart murmur without any other complications. Echocardiography was performed in horses with heart murmur and 25 of them showed regurgitation of the cardiac valve. During the first examination, 7 horses were diagnosed with regurgitation and changes in the size of cardiac chambers, whereas this number increased to 25 during the second examination. There was no significant relationship between degree of murmur and severity of regurgitant jet in horses. The valvular regurgitation can affect the performance when causing changes in the size of the cardiac chambers which can consequently jeopardize the athletic future of the horse.
PubMed: 36320295
DOI: 10.30466/vrf.2021.130366.2997 -
Circulation Journal : Official Journal... Oct 2016
Topics: Echocardiography; Female; Heart Murmurs; Heart Neoplasms; Humans; Middle Aged; Phonocardiography
PubMed: 27581059
DOI: 10.1253/circj.CJ-16-0804 -
Sensors (Basel, Switzerland) Jun 2023(1) Background: Mastery of auscultation can be challenging for many healthcare providers. Artificial intelligence (AI)-powered digital support is emerging as an aid to...
(1) Background: Mastery of auscultation can be challenging for many healthcare providers. Artificial intelligence (AI)-powered digital support is emerging as an aid to assist with the interpretation of auscultated sounds. A few AI-augmented digital stethoscopes exist but none are dedicated to pediatrics. Our goal was to develop a digital auscultation platform for pediatric medicine. (2) Methods: We developed StethAid-a digital platform for artificial intelligence-assisted auscultation and telehealth in pediatrics-that consists of a wireless digital stethoscope, mobile applications, customized patient-provider portals, and deep learning algorithms. To validate the StethAid platform, we characterized our stethoscope and used the platform in two clinical applications: (1) Still's murmur identification and (2) wheeze detection. The platform has been deployed in four children's medical centers to build the first and largest pediatric cardiopulmonary datasets, to our knowledge. We have trained and tested deep-learning models using these datasets. (3) Results: The frequency response of the StethAid stethoscope was comparable to those of the commercially available Eko Core, Thinklabs One, and Littman 3200 stethoscopes. The labels provided by our expert physician offline were in concordance with the labels of providers at the bedside using their acoustic stethoscopes for 79.3% of lungs cases and 98.3% of heart cases. Our deep learning algorithms achieved high sensitivity and specificity for both Still's murmur identification (sensitivity of 91.9% and specificity of 92.6%) and wheeze detection (sensitivity of 83.7% and specificity of 84.4%). (4) Conclusions: Our team has created a technically and clinically validated pediatric digital AI-enabled auscultation platform. Use of our platform could improve efficacy and efficiency of clinical care for pediatric patients, reduce parental anxiety, and result in cost savings.
Topics: Humans; Child; Artificial Intelligence; Auscultation; Stethoscopes; Heart Murmurs; Algorithms; Respiratory Sounds
PubMed: 37420914
DOI: 10.3390/s23125750 -
Circulation Journal : Official Journal... May 2019
Topics: Aged; Aortic Valve Insufficiency; Aortic Valve Stenosis; Heart Murmurs; Humans; Male
PubMed: 30282849
DOI: 10.1253/circj.CJ-18-0697 -
Veterinary Sciences Oct 2022Cardiac auscultation is one of the most important clinical tools to identify patients with a potential heart disease. Although several publications have reported the...
BACKGROUND
Cardiac auscultation is one of the most important clinical tools to identify patients with a potential heart disease. Although several publications have reported the prevalence of murmurs in cats, little information is available in relation to the exact origin of the blood flow turbulences responsible for these murmurs. The aim of this study was to determine the prevalence and clinical significance of murmurs detected during physical examination in cats.
METHODS
Retrospective evaluation of clinical records and echocardiographic examinations performed in cats for investigation of heart murmurs; Results: Records of 856 cats with full clinical information were available for review. The cause of murmur was identified in 93.1% of cases (72.3% with single blood flow turbulence, 26.4% with two, and 1.3% with three identifiable sources of murmur). Systolic anterior motion of the mitral valve (SAM) was the primary cause of murmur in this population (39.2%), followed by dynamic right ventricular outflow tract obstruction (DRVOTO) (32%) and flow murmurs (6.9%). Most cats with a murmur (56.7%) did not present any structural cardiac abnormality.
CONCLUSIONS
This study indicates that some heart murmur characteristics (timing, loudness and point of maximal intensity) can potentially predict the presence of an underlying cardiac disease.
PubMed: 36288177
DOI: 10.3390/vetsci9100564 -
Journal of Osteopathic Medicine Jun 2023The acquisition of clinical skills is an essential part of the osteopathic medical school curriculum. Preclinical medical students, especially at osteopathic medical...
CONTEXT
The acquisition of clinical skills is an essential part of the osteopathic medical school curriculum. Preclinical medical students, especially at osteopathic medical schools, have limited exposure to abnormal physical examination (PE) findings that are not typically seen in a student's peers or in a standardized patient (SP). The early exposure of first-year medical students (MS1s) to normal and abnormal findings in the simulation settings better equips them to identify abnormalities when they encounter them in a clinical setting.
OBJECTIVES
The aim of this project was to develop and implement the introductory course on learning abnormal PE signs and pathophysiology of abnormal clinical findings to address the educational needs of MS1s.
METHODS
The didactic part of the course consisted of PowerPoint presentations and lecture on the topics related to the simulation. The practical skill session was 60 min, during which time students first practiced PE signs and then were assessed on their ability to accurately identify abnormal PE signs on a high-fidelity (HF) mannequin. Faculty instructors guided students through clinical cases and challenged them with probing questions in clinically relevant content. Before- and after-simulation evaluations were created to assess students' skills and confidence. Student satisfaction levels after the training course were also assessed.
RESULTS
This study demonstrated significant improvements in five PE skills (p<0.0001) after the introductory course of abnormal PE clinical signs. The average score for five clinical skills increased from 63.1 to 88.74% (before to after simulation). The confidence of students in performing clinical skills and their understanding of the pathophysiology of abnormal clinical findings also increased significantly (p<0.0001) after simulation activity and educational instruction. The average confidence score increased from 3.3 to 4.5% (before to after simulation) on a 5-point Likert scale. Survey results demonstrated high satisfaction with the course among learners with mean satisfaction score 4.7 ± 0.4 on 5-point Likert scale. The introductory course was well received by MS1s and they left positive feedback.
CONCLUSIONS
This introductory course offered MS1s with novice PE skills the ability to learn a variety of abnormal PE signs, including heart murmurs and rhythms, lung sounds, measurement of blood pressure (BP), and palpation of the femoral pulse. This course also allowed abnormal PE findings to be taught in a time-efficient and faculty-resource-efficient manner.
Topics: Humans; Curriculum; Learning; Physical Examination; Internship and Residency; Students, Medical
PubMed: 36998103
DOI: 10.1515/jom-2022-0163