Wearing surgical face mask has no significant impact on auscultation assessment.

Objective: During the COVID-19 pandemic, universal mask-wearing became one of the main public health interventions. Because of this, most physical examinations, including lung auscultation, were done while patients were wearing surgical face masks. The aim of this study was to investigate whether mask wearing has an impact on pulmonologist assessment during auscultation of the lungs. Methods: This was a repeated measures crossover design study. Three pulmonologists were instructed to auscultate patients with previously verified prolonged expiration, wheezing, or crackles while patients were wearing or not wearing masks (physician and patients were separated by an opaque barrier). As a measure of pulmonologists' agreement in the assessment of lung sounds, we used Fleiss kappa (K). Results: There was no significant difference in agreement on physician assessment of lung sounds in all three categories (normal lung sound, duration of expiration, and adventitious lung sound) whether the patient was wearing a mask or not, but there were significant differences among pulmonologists when it came to agreement of lung sound assessment. Conclusion: Clinicians and health professionals are safer from respiratory infections when they are wearing masks, and patients should be encouraged to wear masks because our research proved no significant difference in agreement on pulmonologists' assessment of auscultated lung sounds whether or not patients wore masks.

Recognizing cardiac murmurs in childhood: a survey of physicians' approaches and knowledge levels.

OBJECTIVE: This study aimed to assess physicians' approach to cardiac murmurs and their level of knowledge about this sign, which is a crucial finding in childhood cardiac anomalies. METHODS: The study intended to include all family physicians in the Adiyaman province of Turkey, but ultimately 150 out of 210 physicians participated and was completed with a percentage response rate of 71%. Participants were asked about their approach to cardiac murmurs, answered knowledge questions, and completed a questionnaire on demographic characteristics. Subsequently, eight heart sounds were played, and participants were asked to identify the nature of each sound. RESULTS: Family medicine specialists (all scores were p < 0.001) and physicians who completed a pediatric internship lasting over a month (knowledge score p = 0.012, behavioral score p = 0.021, recording score p = 0.01) demonstrated significantly higher knowledge, approach, and recording scores. Age and years in the profession showed a negative correlation with recording scores. CONCLUSIONS: The study highlights the significant impact of various factors such as gender, specialization, internship duration, experience, and theoretical knowledge on the ability to recognize and approach cardiac murmurs. These findings underscore the importance of incorporating these factors into medical education and development programs, especially those aimed at improving cardiac examination skills.

Evaluation of a digitally enhanced cardiac auscultation learning method in Cameroon: results of a controlled study.

BACKGROUND: Cardiac auscultation is an efficient and effective diagnostic tool, especially in low-income countries where access to modern diagnostic methods remains difficult. This study aimed to evaluate the effect of a digitally enhanced cardiac auscultation learning method on medical students' performance and satisfaction. METHODS: We conducted a double-arm parallel controlled trial, including newly admitted 4th -year medical students enrolled in two medical schools in Yaoundé, Cameroon and allocated into two groups: the intervention group (benefiting from theoretical lessons, clinical internship and the listening sessions of audio recordings of heart sounds) and the control group (benefiting from theoretical lessons and clinical internship). All the participants were subjected to a pretest before the beginning of the training, evaluating theoretical knowledge and recognition of cardiac sounds, and a post-test at the eighth week of clinical training associated with the evaluation of satisfaction. The endpoints were the progression of knowledge score, skills score, total (knowledge and skills) score and participant satisfaction. RESULTS: Forty-nine participants (27 in the intervention group and 22 in the control group) completed the study. The knowledge progression (+ 26.7 versus + 7.5; p ˂0.01) and the total progression (+ 22.5 versus + 14.6; p ˂ 0.01) were higher in the intervention group with a statistically significant difference compared to the control group. There was no significant difference between the two groups regarding skills progression (+ 25 versus + 17.5; p = 0.27). Satisfaction was higher in general in the intervention group (p ˂ 0.01), which recommended this method compared to the control group. CONCLUSION: The learning method of cardiac auscultation reinforced by the listening sessions of audio recordings of heart sounds improves medical students' performances (knowledge and global - knowledge and skills) who find it satisfactory and recommendable. TRIAL REGISTRATION: This trial has been registered the 29/11/2019 in the Pan African Clinical Trials Registry ( http://www.pactr.org ) under unique identification number PACTR202001504666847 and the protocol has been published in BMC Medical Education.

Feasibility and Acceptability of Pediatric Smartphone Lung Auscultation by Parents: Cross-Sectional Study.

Background: The use of a smartphone built-in microphone for auscultation is a feasible alternative to the use of a stethoscope, when applied by physicians. Objective: This cross-sectional study aims to assess the feasibility of this technology when used by parents-the real intended end users. Methods: Physicians recruited 46 children (male: n=33, 72%; age: mean 11.3, SD 3.1 y; children with asthma: n=24, 52%) during medical visits in a pediatric department of a tertiary hospital. Smartphone auscultation using an app was performed at 4 locations (trachea, right anterior chest, and right and left lung bases), first by a physician (recordings: n=297) and later by a parent (recordings: n=344). All recordings (N=641) were classified by 3 annotators for quality and the presence of adventitious sounds. Parents completed a questionnaire to provide feedback on the app, using a Likert scale ranging from 1 ("totally disagree") to 5 ("totally agree"). Results: Most recordings had quality (physicians' recordings: 253/297, 85.2%; parents' recordings: 266/346, 76.9%). The proportions of physicians' recordings (34/253, 13.4%) and parents' recordings (31/266, 11.7%) with adventitious sounds were similar. Parents found the app easy to use (questionnaire: median 5, IQR 5-5) and were willing to use it (questionnaire: median 5, IQR 5-5). Conclusions: Our results show that smartphone auscultation is feasible when performed by parents in the clinical context, but further investigation is needed to test its feasibility in real life.

Beat-to-beat alterations of acoustic intensity and frequency at the maximum power of heart sounds are associated with NT-proBNP levels.

Background: Auscultatory features of heart sounds (HS) in patients with heart failure (HF) have been studied intensively. Recent developments in digital and electrical devices for auscultation provided easy listening chances to recognize peculiar sounds related to diastolic HS such as S3 or S4. This study aimed to quantitatively assess HS by acoustic measures of intensity (dB) and audio frequency (Hz). Methods: Forty consecutive patients aged between 46 and 87 years (mean age, 74 years) with chronic cardiovascular disease (CVD) were enrolled in the present study after providing written informed consent during their visits to the Kitasato University Outpatient Clinic. HS were recorded at the fourth intercostal space along the left sternal border using a highly sensitive digital device. Two consecutive heartbeats were quantified on sound intensity (dB) and audio frequency (Hz) at the peak power of each spectrogram of S1-S4 using audio editing and recording application software. The participants were classified into three groups, namely, the absence of HF (n = 27), HF (n = 8), and high-risk HF (n = 5), based on the levels of NT-proBNP < 300, ≥300, and ≥900 pg/ml, respectively, and also the levels of ejection fraction (EF), such as preserved EF (n = 22), mildly reduced EF (n = 12), and reduced EF (n = 6). Results: The intensities of four components of HS (S1-S4) decreased linearly (p < 0.02-0.001) with levels of body mass index (BMI) (range, 16.2-33.0 kg/m2). Differences in S1 intensity (ΔS1) and its frequency (ΔfS1) between two consecutive beats were non-audible level and were larger in patients with HF than those in patients without HF (ΔS1, r = 0.356, p = 0.024; ΔfS1, r = 0.356, p = 0.024). The cutoff values of ΔS1 and ΔfS1 for discriminating the presence of high-risk HF were 4.0 dB and 5.0 Hz, respectively. Conclusions: Despite significant attenuations of all four components of HS by BMI, beat-to-beat alterations of both intensity and frequency of S1 were associated with the severity of HF. Acoustic quantification of HS enabled analyses of sounds below the audible level, suggesting that sound analysis might provide an early sign of HF.

Improved cardiac auscultation competency interweaving visual, auditory, and tactile stimuli: a preliminary study.

Methods:   A pilot randomized controlled trial was conducted at our institution's simulation center with 32 first year medical students from a single medical institution. Participants were randomly divided into two equal groups and completed an educational module the identification and pathophysiology of five common cardiac sounds. The control group utilized traditional education methods, while the interventional group incorporated multisensory stimuli. Afterwards, participants listened to randomly selected cardiac sounds and competency data was collected through a multiple-choice post-assessment in both groups. Mann-Whitney U test was used to analyze the data. Results: Data were analyzed using the Mann-Whitney U test. Diagnostic accuracy was significantly higher in the multisensory group (Mdn=100%) compared to the control group (Mdn=60%) on the post-assessment (U=73.5, p<0.042). Likewise, knowledge acquisition was substantially better in the multisensory group (Mdn=80%) than in the control group (Mdn=50%) (U= 49, p<0.031). Conclusions: These findings suggest the incorporation of multisensory stimuli significantly improves cardiac auscultation competency. Given its cost-effectiveness and simplicity, this approach offers a viable alternative to more expensive simulation technologies like the Harvey simulator, particularly in settings with limited resources. Consequently, this teaching modality holds promise for global applicability, addressing the worldwide deterioration in cardiac auscultation skills and potentially leading to better patient outcomes. Future studies should broaden the sample size, span multiple institutions, and investigate long-term retention rates.

Exploring the link between a novel approach for computer aided lung sound analysis and imaging biomarkers: a cross-sectional study.

BACKGROUND: Computer Aided Lung Sound Analysis (CALSA) aims to overcome limitations associated with standard lung auscultation by removing the subjective component and allowing quantification of sound characteristics. In this proof-of-concept study, a novel automated approach was evaluated in real patient data by comparing lung sound characteristics to structural and functional imaging biomarkers. METHODS: Patients with cystic fibrosis (CF) aged > 5y were recruited in a prospective cross-sectional study. CT scans were analyzed by the CF-CT scoring method and Functional Respiratory Imaging (FRI). A digital stethoscope was used to record lung sounds at six chest locations. Following sound characteristics were determined: expiration-to-inspiration (E/I) signal power ratios within different frequency ranges, number of crackles per respiratory phase and wheeze parameters. Linear mixed-effects models were computed to relate CALSA parameters to imaging biomarkers on a lobar level. RESULTS: 222 recordings from 25 CF patients were included. Significant associations were found between E/I ratios and structural abnormalities, of which the ratio between 200 and 400 Hz appeared to be most clinically relevant due to its relation with bronchiectasis, mucus plugging, bronchial wall thickening and air trapping on CT. The number of crackles was also associated with multiple structural abnormalities as well as regional airway resistance determined by FRI. Wheeze parameters were not considered in the statistical analysis, since wheezing was detected in only one recording. CONCLUSIONS: The present study is the first to investigate associations between auscultatory findings and imaging biomarkers, which are considered the gold standard to evaluate the respiratory system. Despite the exploratory nature of this study, the results showed various meaningful associations that highlight the potential value of automated CALSA as a novel non-invasive outcome measure in future research and clinical practice.

Breath Measurement Method for Synchronized Reproduction of Biological Tones in an Augmented Reality Auscultation Training System.

An educational augmented reality auscultation system (EARS) is proposed to enhance the reality of auscultation training using a simulated patient. The conventional EARS cannot accurately reproduce breath sounds according to the breathing of a simulated patient because the system instructs the breathing rhythm. In this study, we propose breath measurement methods that can be integrated into the chest piece of a stethoscope. We investigate methods using the thoracic variations and frequency characteristics of breath sounds. An accelerometer, a magnetic sensor, a gyro sensor, a pressure sensor, and a microphone were selected as the sensors. For measurement with the magnetic sensor, we proposed a method by detecting the breathing waveform in terms of changes in the magnetic field accompanying the surface deformation of the stethoscope based on thoracic variations using a magnet. During breath sound measurement, the frequency spectra of the breath sounds acquired by the built-in microphone were calculated. The breathing waveforms were obtained from the difference in characteristics between the breath sounds during exhalation and inhalation. The result showed the average value of the correlation coefficient with the reference value reached 0.45, indicating the effectiveness of this method as a breath measurement method. And the evaluations suggest more accurate breathing waveforms can be obtained by selecting the measurement method according to breathing method and measurement point.

UK student midwives' theoretical knowledge, confidence, and experience of intermittent auscultation of the fetal heart rate during labour: An online cross-sectional survey.

AIM: This study aimed to explore student midwives' theoretical knowledge of intrapartum intermittent auscultation, their confidence in, and their experience of this mode of fetal monitoring. DESIGN AND SETTING: An online cross-section survey with closed and open questions. Descriptive statistics were used to analyse participants' intermittent auscultation knowledge, confidence, and experience. Reflexive thematic analysis was used to identify patterns within the free text about participants' experiences. PARTICIPANTS: Undergraduate midwifery students (n = 303) from Nursing and Midwifery Council-approved educational institutions within the United Kingdom. FINDINGS: Most participants demonstrated good theoretical knowledge. They had witnessed the technique being used in clinical practice, and when performed, the practice was reported to be in line with national guidance. In closed questions, participants reported feeling confident in their intermittent auscultation skills; however, these data contrasted with free-text responses. CONCLUSION: This cross-sectional survey found that student midwives possess adequate knowledge of intermittent auscultation. However, reflecting individual clinical experiences, their confidence in their ability to perform intermittent auscultation varied. A lack of opportunity to practice intermittent auscultation, organisational culture, and midwives' preferences have caused student midwives to question their capabilities with this essential clinical skill, leaving some with doubt about their competency close to registration.

[Critical care nurses' decision-making regarding verification of blindly inserted gastric tubes: A cross-sectional questionnaire study]. / Entscheidungsfindung von Intensivpflegefachpersonen zur Verifikation blind applizierter Magensonden.

Critical care nurses' decision-making regarding verification of blindly inserted gastric tubes: A cross-sectional questionnaire study Abstract: Background: The placement and verification of the correct position of blindly applied gastric tubes is regularly performed by nurses in clinical practice. International guidelines recommend a radiological verification as a "first-line" method or if pH measurement is not possible. For Germany, neither evidence-based recommendations nor current data are available. Question: Which methods are used by nurses in German intensive care units for verification of the correct position of blindly applied gastric tubes and how do they assess the reliability of different methods? Methods: Multicenter questionnaire survey. Intensive care units in a non-probability, citeria-based sampling of hospitals in and around Cologne, Germany were included. One nurse was included per participating ward. Analyses were mostly descriptive. Results: In 22 hospitals, 38 wards agreed to participate and 32 (84%) responded to the survey. Auscultation of the upper abdomen with simultaneous air insufflation and aspiration of gastric secretions are frequently used methods for determining the position of gastric tubes. Participants consider auscultation, aspiration of gastric secretions, and radiological control as reliable methods. Conclusions: The findings are in contrast to international recommendations and support the need for evidence-based best practice recommendations and training. Likewise, there is a need for research on feasible bedside methods.

The Effectiveness of Different Teaching Modalities for the Detection of Heart Murmurs in Undergraduate Medical Education: A Review.

One of the many physical exam skills introduced to medical students during their pre-clerkship education is cardiac auscultation, one purpose of which is to teach the detection and identification of heart murmurs. Cardiac auscultation with a stethoscope has been the standard method of teaching. Another method, point-of-care ultrasound (POCUS), has been recently introduced as another modality by which students learn to detect and identify murmurs. The emerging popularity of POCUS in undergraduate medical curricula has led many institutions to include it in their curricula; however, doing so is challenging. Not only is cost a major factor, but reorganizing curricula to allow sufficient time for POCUS training has proven to be difficult. Additionally, the presence of notable gaps in the literature regarding the efficacy of POCUS for teaching the detection and identification of heart murmur has increased scrutiny of its value. Studies that assessed teaching cardiac auscultation to medical students in their pre-clinical years via stethoscope have used different teaching methods. However, evaluation of these studies identified numerous limitations, one being little long-term retention of cardiac auscultation knowledge. Furthermore, several barriers to integration of POCUS in undergraduate medical education were identified. The purpose of this review is to synthesize the literature comparing the effectiveness of these different tools of a cardiac exam for detection of heart murmurs in undergraduate medical education and identify gaps in literature requiring future exploration.

Breath characteristics and adventitious lung sounds in healthy and asthmatic horses.

BACKGROUND: Standard thoracic auscultation suffers from limitations, and no systematic analysis of breath sounds in asthmatic horses exists. OBJECTIVES: First, characterize breath sounds in horses recorded using a novel digital auscultation device (DAD). Second, use DAD to compare breath variables and occurrence of adventitious sounds in healthy and asthmatic horses. ANIMALS: Twelve healthy control horses (ctl), 12 horses with mild to moderate asthma (mEA), 10 horses with severe asthma (sEA) (5 in remission [sEA-], and 5 in exacerbation [sEA+]). METHODS: Prospective multicenter case-control study. Horses were categorized based on the horse owner-assessed respiratory signs index. Each horse was digitally auscultated in 11 locations simultaneously for 1 hour. One-hundred breaths per recording were randomly selected, blindly categorized, and statistically analyzed. RESULTS: Digital auscultation allowed breath sound characterization and scoring in horses. Wheezes, crackles, rattles, and breath intensity were significantly more frequent, higher (P < .001, P < .01, P = .01, P < .01, respectively) in sEA+ (68.6%, 66.1%, 17.7%, 97.9%, respectively), but not in sEA- (0%, 0.7%, 1.3%, 5.6%) or mEA (0%, 1.0%, 2.4%, 1.7%) horses, compared to ctl (0%, 0.6%, 1.8%, -9.4%, respectively). Regression analysis suggested breath duration and intensity as explanatory variables for groups, wheezes for tracheal mucus score, and breath intensity and wheezes for the 23-point weighted clinical score (WCS23). CONCLUSIONS AND CLINICAL IMPORTANCE: The DAD permitted characterization and quantification of breath variables, which demonstrated increased adventitious sounds in sEA+. Analysis of a larger sample is needed to determine differences among ctl, mEA, and sEA- horses.

AI diagnosis of heart sounds differentiated with super StethoScope.

In the aging global society, heart failure and valvular heart diseases, including aortic stenosis, are affecting millions of people and healthcare systems worldwide. Although the number of effective treatment options has increased in recent years, the lack of effective screening methods is provoking continued high mortality and rehospitalization rates. Appropriately, auscultation has been the primary option for screening such patients, however, challenges arise due to the variability in auscultation skills, the objectivity of the clinical method, and the presence of sounds inaudible to the human ear. To address challenges associated with the current approach towards auscultation, the hardware of Super StethoScope was developed. This paper is composed of (1) a background literature review of bioacoustic research regarding heart disease detection, (2) an introduction of our approach to heart sound research and development of Super StethoScope, (3) a discussion of the application of remote auscultation to telemedicine, and (4) results of a market needs survey on traditional and remote auscultation. Heart sounds and murmurs, if collected properly, have been shown to closely represent heart disease characteristics. Correspondingly, the main characteristics of Super StethoScope include: (1) simultaneous collection of electrocardiographic and heart sound for the detection of heart rate variability, (2) optimized signal-to-noise ratio in the audible frequency bands, and (3) acquisition of heart sounds including the inaudible frequency ranges. Due to the ability to visualize the data, the device is able to provide quantitative results without disturbance by sound quality alterations during remote auscultations. An online survey of 3648 doctors confirmed that auscultation is the common examination method used in today's clinical practice and revealed that artificial intelligence-based heart sound analysis systems are expected to be integrated into clinicians' practices. Super StethoScope would open new horizons for heart sound research and telemedicine.

Exploring classical machine learning for identification of pathological lung auscultations.

The use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to expand this body of knowledge by applying machine learning to pulmonary auscultation signals. Despite improvements in digital stethoscopes and attempts to find synergy between them and artificial intelligence, solutions for their use in clinical settings remain scarce. Physicians continue to infer initial diagnoses with less sophisticated means, resulting in low accuracy, leading to suboptimal patient care. To arrive at a correct preliminary diagnosis, the auscultation diagnostics need to be of high accuracy. Due to the large number of auscultations performed, data availability opens up opportunities for more effective sound analysis. In this study, digital 6-channel auscultations of 45 patients were used in various machine learning scenarios, with the aim of distinguishing between normal and abnormal pulmonary sounds. Audio features (such as fundamental frequencies F0-4, loudness, HNR, DFA, as well as descriptive statistics of log energy, RMS and MFCC) were extracted using the Python library Surfboard. Windowing, feature aggregation, and concatenation strategies were used to prepare data for machine learning algorithms in unsupervised (fair-cut forest, outlier forest) and supervised (random forest, regularized logistic regression) settings. The evaluation was carried out using 9-fold stratified cross-validation repeated 30 times. Decision fusion by averaging the outputs for a subject was also tested and found to be helpful. Supervised models showed a consistent advantage over unsupervised ones, with random forest achieving a mean AUC ROC of 0.691 (accuracy 71.11%, Kappa 0.416, F1-score 0.675) in side-based detection and a mean AUC ROC of 0.721 (accuracy 68.89%, Kappa 0.371, F1-score 0.650) in patient-based detection.

Improving Valvular Pathologies and Ventricular Dysfunction Diagnostic Efficiency Using Combined Auscultation and Electrocardiography Data: A Multimodal AI Approach.

Simple sensor-based procedures, including auscultation and electrocardiography (ECG), can facilitate early diagnosis of valvular diseases, resulting in timely treatment. This study assessed the impact of combining these sensor-based procedures with machine learning on diagnosing valvular abnormalities and ventricular dysfunction. Data from auscultation at three distinct locations and 12-lead ECGs were collected from 1052 patients undergoing echocardiography. An independent cohort of 103 patients was used for clinical validation. These patients were screened for severe aortic stenosis (AS), severe mitral regurgitation (MR), and left ventricular dysfunction (LVD) with ejection fractions ≤ 40%. Optimal neural networks were identified by a fourfold cross-validation training process using heart sounds and various ECG leads, and their outputs were combined using a stacking technique. This composite sensor model had high diagnostic efficiency (area under the receiver operating characteristic curve (AUC) values: AS, 0.93; MR, 0.80; LVD, 0.75). Notably, the contribution of individual sensors to disease detection was found to be disease-specific, underscoring the synergistic potential of the sensor fusion approach. Thus, machine learning models that integrate auscultation and ECG can efficiently detect conditions typically diagnosed via imaging. Moreover, this study highlights the potential of multimodal artificial intelligence applications.

Self-Reported Utilization of International Guidelines for Staging Dogs with Myxomatous Mitral Valve Degeneration: A Survey among Veterinary Practitioners.

BACKGROUND: ACVIM developed and published guidelines for staging myxomatous mitral valve degeneration in dogs in 2009. An updated version was published in 2019. The present study aimed to investigate whether these guidelines are actually used by the intended public more than a decade after their first publication. METHODS: An online survey was distributed among Dutch and Belgian veterinarians through online channels and mailing lists. RESULTS: Of the 524 responses, only 363 complete surveys were analyzed. The ACVIM guidelines are used by 60% of the respondents. Veterinarians find it more difficult to differentiate stage B1 from B2 in asymptomatic dogs compared to diagnosing stage C. Three-quarters of the respondents would recommend echocardiography for an incidentally detected new murmur with an intensity of 3 out of 6 in an adult dog. Two-thirds of the respondents find coughing a convincing finding for stage C disease. Close to half of the respondents associate a horizontal, dull percussion line with pulmonary edema. For confirming cardiogenic pulmonary edema, 98% of the respondents used thoracic radiographs. CONCLUSIONS: Veterinary practitioners might not have the expected training and equipment to be able to apply the guidelines in their practices, especially in the differentiation of stage B1 from stage B2.

Exploring Microphone Technologies for Digital Auscultation Devices.

The aim of this work is to present a preliminary study for the design of a digital auscultation system, i.e., a novel wearable device for patient chest auscultation and a digital stethoscope. The development and testing of the electronic stethoscope prototype is reported with an emphasis on the description and selection of sound transduction systems and analog electronic processing. The focus on various microphone technologies, such as micro-electro-mechanical systems (MEMSs), electret condensers, and piezoelectronic diaphragms, intends to emphasize the most suitable transducer for auscultation. In addition, we report on the design and development of a digital acquisition system for the human body for sound recording by using a modular device approach in order to fit the chosen analog and digital mics. Tests were performed on a designed phantom setup, and a qualitative comparison between the sounds recorded with the newly developed acquisition device and those recorded with two commercial digital stethoscopes is reported.

Heart Murmur Classification Using a Capsule Neural Network.

The healthcare industry has made significant progress in the diagnosis of heart conditions due to the use of intelligent detection systems such as electrocardiograms, cardiac ultrasounds, and abnormal sound diagnostics that use artificial intelligence (AI) technology, such as convolutional neural networks (CNNs). Over the past few decades, methods for automated segmentation and classification of heart sounds have been widely studied. In many cases, both experimental and clinical data require electrocardiography (ECG)-labeled phonocardiograms (PCGs) or several feature extraction techniques from the mel-scale frequency cepstral coefficient (MFCC) spectrum of heart sounds to achieve better identification results with AI methods. Without good feature extraction techniques, the CNN may face challenges in classifying the MFCC spectrum of heart sounds. To overcome these limitations, we propose a capsule neural network (CapsNet), which can utilize iterative dynamic routing methods to obtain good combinations for layers in the translational equivariance of MFCC spectrum features, thereby improving the prediction accuracy of heart murmur classification. The 2016 PhysioNet heart sound database was used for training and validating the prediction performance of CapsNet and other CNNs. Then, we collected our own dataset of clinical auscultation scenarios for fine-tuning hyperparameters and testing results. CapsNet demonstrated its feasibility by achieving validation accuracies of 90.29% and 91.67% on the test dataset.

Deep Learning Algorithms to Detect Murmurs Associated With Structural Heart Disease.

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.