The impact of computer-assisted auscultation on physician referrals of asymptomatic patients with heart murmurs

Learning Representations from Heart Sound: A Comparative Study on Shallow and Deep Models

Leveraging the power of artificial intelligence to facilitate an automatic analysis and monitoring of heart sounds has increasingly attracted tremendous efforts in the past decade. Nevertheless, lacking on standard open-access database made it difficult to maintain a sustainable and comparable research before the first release of the PhysioNet CinC Challenge Dataset. However, inconsistent standards on data collection, annotation, and partition are still restraining a fair and efficient comparison between different works. To this line, we introduced and benchmarked a first version of the Heart Sounds Shenzhen (HSS) corpus. Motivated and inspired by the previous works based on HSS, we redefined the tasks and make a comprehensive investigation on shallow and deep models in this study. First, we segmented the heart sound recording into shorter recordings (10 s), which makes it more similar to the human auscultation case. Second, we redefined the classification tasks. Besides using the 3 class categories (normal, moderate, and mild/severe) adopted in HSS, we added a binary classification task in this study, i.e., normal and abnormal. In this work, we provided detailed benchmarks based on both the classic machine learning and the state-of-the-art deep learning technologies, which are reproducible by using open-source toolkits. Last but not least, we analyzed the feature contributions of best performance achieved by the benchmark to make the results more convincing and interpretable.

A CFD-FFT approach to hemoacoustics that enables degree of stenosis prediction from stethoscopic signals

In this paper, we identify a new (acoustic) frequency-stenosis relation whose frequencies lie within the recommended auscultation threshold of stethoscopy (< 120 Hz). We show that this relation can be used to extend the application of phonoangiography (quantifying the degree of stenosis from bruits) to widely accessible stethoscopes. The relation is successfully identified from an analysis restricted to the acoustic signature of the von Karman vortex street, which we automatically single out by means of a metric we propose that is based on an area-weighted average of the Q-criterion for the post-stenotic region. Specifically, we perform CFD simulations on internal flow geometries that represent stenotic blood vessels of different severities. We then extract their emitted acoustic signals using the Ffowcs Williams-Hawkings equation, which we subtract from a clean signal (stenosis free) at the same heart rate. Next, we transform this differential signal to the frequency domain and carefully classify its acoustic signatures per six (stenosis-)invariant flow phases of a cardiac cycle that are newly identified in this paper. We then automatically restrict our acoustic analysis to the sounds emitted by the von Karman vortex street (phase 4) by means of our Q-criterion-based metric. Our analysis of its acoustic signature reveals a strong linear relationship between the degree of stenosis and its dominant frequency, which differs considerably from the break frequency and the heart rate (known dominant frequencies in the literature). Applying our new relation to available stethoscopic data, we find that its predictions are consistent with clinical assessment. Our finding of this linear correlation is also unlike prevalent scaling laws in the literature, which feature a small exponent (i.e., low stenosis percentage sensitivity over much of the clinical range). They hence can only distinguish mild, moderate, and severe cases. Conversely, our linear law can identify variations in the degree of stenosis sensitively and accurately for the full clinical range, thus significantly improving the utility of the relevant scaling laws... Future research will investigate incorporating the vibroacoustic role of adjacent organs to expand the clinical applicability of our findings. Extending our approach to more complex 3D stenotic morphologies and including the vibroacoustic role of surrounding organs will be explored in future research to advance the clinical reach of our findings.

Computational Modeling of Aortic Stenosis With a Reduced Degree-of-Freedom Fluid-Structure Interaction Valve Model

In this study, a novel reduced degree-of-freedom (rDOF) aortic valve model is employed to investigate the fluid-structure interaction (FSI) and hemodynamics associated with aortic stenosis. The dynamics of the valve leaflets are determined by an ordinary differential equation with two parameters and this rDOF model is shown to reproduce key features of more complex valve models. The hemodynamics associated with aortic stenosis is studied for three cases: a healthy case and two stenosed cases. The focus of the study is to correlate the hemodynamic features with the source generation mechanism of systolic murmurs associated with aortic stenosis. In the healthy case, extremely weak flow fluctuations are observed. However, in the stenosed cases, simulations show significant turbulent fluctuations in the ascending aorta, which are responsible for the generation of strong wall pressure fluctuations after the aortic root mostly during the deceleration phase of the systole. The intensity of the murmur generation increases with the severity of the stenosis, and the source locations for the two diseased cases studied here lie around 1.0 inlet duct diameters (Do) downstream of the ascending aorta.

The discerning ear: cardiac auscultation in the era of artificial intelligence and telemedicine

Heart murmur, a thoracic auscultatory finding of cardiovascular origin, is extremely common in childhood and can appear at any age from premature newborn to late adolescence. The objective of this review is to provide a modern examination and update of cardiac murmur auscultation in this new era of artificial intelligence (AI) and telemedicine. First, we provide a comprehensive review of the causes and differential diagnosis, clinical features, evaluation, and long-term management of paediatric heart murmurs. Next, we provide a brief history of computer-assisted auscultation and murmur analysis, along with insight into the engineering design of the digital stethoscope. We conclude with a discussion of the paradigm shifting impact of deep learning on murmur analysis, AI-assisted auscultation, and the implications of these technologies on telemedicine in paediatric cardiology. It is our hope that this article provides an updated perspective on the impact of AI on cardiac auscultation for the modern paediatric cardiologist.

Community-based aortic stenosis detection: clinical and echocardiographic screening during influenza vaccination

Background

Degenerative aortic stenosis (AS), the most common valvular heart disease in the Western world, is often diagnosed late when the mortality risk becomes substantial. We determined the feasibility of AS screening during influenza vaccination at general practitioner (GP) surgeries in the UK.

Methods

Consecutive subjects aged >65 years presenting to a GP for influenza vaccination underwent heart auscultation and 2D echocardiography (V-scan). Based on these findings, a patient management strategy was determined (referral to cardiologist, review within own practice or no follow-up measures) and status at 3 months was determined.

Results

167 patients were enrolled with a mean age of 75 years. On auscultation, a heart murmur was detected in 30 of 167 (18%) patients (6 subjects with an AS-specific and 24 with a non-specific murmur). 75.2% of those with no murmur had a negative V-scan finding. Conversely, 16 of 30 (53%) patients with any murmur had an abnormal V-scan finding that was largely related to the aortic valve. Using clinical auscultation and V-scan screening, a decision not to pursue follow-up measures was taken in 147 (88%) cases, whereas 18 (10.8%) subjects were referred onward; with 5 of 18 (27.8%) and 3 of 18 (16.7%) being diagnosed with mild and moderate AS.

Conclusions

Our pilot study confirms feasibility of valvular heart disease screening in the elderly in a primary care setting. Using simple and inexpensive diagnostic measures and 7.3 million UK inhabitants undergoing influenza vaccination, nationwide screening could potentially identify 130 000 patients with moderate AS and a significant number of patients with severe AS.

Automatic Evaluation of Heart Condition According to the Sounds Emitted and Implementing Six Classification Methods

The main cause of death in Mexico and the world is heart disease, and it will continue to lead the death rate in the next decade according to data from the World Health Organization (WHO) and the National Institute of Statistics and Geography (INEGI). Therefore, the objective of this work is to implement, compare and evaluate machine learning algorithms that are capable of classifying normal and abnormal heart sounds. Three different sounds were analyzed in this study; normal heart sounds, heart murmur sounds and extra systolic sounds, which were labeled as healthy sounds (normal sounds) and unhealthy sounds (murmur and extra systolic sounds). From these sounds, fifty-two features were calculated to create a numerical dataset; thirty-six statistical features, eight Linear Predictive Coding (LPC) coefficients and eight Cepstral Frequency-Mel Coefficients (MFCC). From this dataset two more were created; one normalized and one standardized. These datasets were analyzed with six classifiers: k-Nearest Neighbors, Naive Bayes, Decision Trees, Logistic Regression, Support Vector Machine and Artificial Neural Networks, all of them were evaluated with six metrics: accuracy, specificity, sensitivity, ROC curve, precision and F1-score, respectively. The performances of all the models were statistically significant, but the models that performed best for this problem were logistic regression for the standardized data set, with a specificity of 0.7500 and a ROC curve of 0.8405, logistic regression for the normalized data set, with a specificity of 0.7083 and a ROC curve of 0.8407, and Support Vector Machine with a lineal kernel for the non-normalized data; with a specificity of 0.6842 and a ROC curve of 0.7703. Both of these metrics are of utmost importance in evaluating the performance of computer-assisted diagnostic systems.

A Framework for AI-Assisted Detection of Patent Ductus Arteriosus from Neonatal Phonocardiogram

The current diagnosis of Congenital Heart Disease (CHD) in neonates relies on echocardiography. Its limited availability requires alternative screening procedures to prioritise newborns awaiting ultrasound. The routine screening for CHD is performed using a multidimensional clinical examination including (but not limited to) auscultation and pulse oximetry. While auscultation might be subjective with some heart abnormalities not always audible it increases the ability to detect heart defects. This work aims at developing an objective clinical decision support tool based on machine learning (ML) to facilitate differentiation of sounds with signatures of Patent Ductus Arteriosus (PDA)/CHDs, in clinical settings. The heart sounds are pre-processed and segmented, followed by feature extraction. The features are fed into a boosted decision tree classifier to estimate the probability of PDA or CHDs. Several mechanisms to combine information from different auscultation points, as well as consecutive sound cycles, are presented. The system is evaluated on a large clinical dataset of heart sounds from 265 term and late-preterm newborns recorded within the first six days of life. The developed system reaches an area under the curve (AUC) of 78% at detecting CHD and 77% at detecting PDA. The obtained results for PDA detection compare favourably with the level of accuracy achieved by an experienced neonatologist when assessed on the same cohort.

Narrative review of the role of artificial intelligence to improve aortic valve disease management

Valvular heart disease (VHD) is a chronic progressive condition with an increasing prevalence in the Western world due to aging populations. VHD is often diagnosed at a late stage when patients are symptomatic and the outcomes of therapy, including valve replacement, may be sub-optimal due the development of secondary complications, including left ventricular (LV) dysfunction. The clinical application of artificial intelligence (AI), including machine learning (ML), has promise in supporting not only early and more timely diagnosis, but also hastening patient referral and ensuring optimal treatment of VHD. As physician auscultation lacks accuracy in diagnosis of significant VHD, computer-aided auscultation (CAA) with the help of a commercially available digital stethoscopes improves the detection and classification of heart murmurs. Although used little in current clinical practice, CAA can screen large populations at low cost with high accuracy for VHD and faciliate appropriate patient referral. Echocardiography remains the next step in assessment and planning management and AI is delivering major changes in speeding training, improving image quality by pattern recognition and image sorting, as well as automated measurement of multiple variables, thereby improving accuracy. Furthermore, AI then has the potential to hasten patient disposal, by automated alerts for red-flag findings, as well as decision support in dealing with results. In management, there is great potential in ML-enabled tools to support comprehensive disease monitoring and individualized treatment decisions. Using data from multiple sources, including demographic and clinical risk data to image variables and electronic reports from electronic medical records, specific patient phenotypes may be identified that are associated with greater risk or modeled to the estimate trajectory of VHD progression. Finally, AI algorithms are of proven value in planning intervention, facilitating transcatheter valve replacement by automated measurements of anatomical dimensions derived from imaging data to improve valve selection, valve size and method of delivery.

Artificial Intelligence-Assisted Auscultation of Heart Murmurs: Validation by Virtual Clinical Trial

Artificial intelligence (AI) has potential to improve the accuracy of screening for valvular and congenital heart disease by auscultation. However, despite recent advances in signal processing and classification algorithms focused on heart sounds, clinical acceptance of this technology has been limited, in part due to lack of objective performance data. We hypothesized that a heart murmur detection algorithm could be quantitatively and objectively evaluated by virtual clinical trial. All cases from the Johns Hopkins Cardiac Auscultatory Recording Database (CARD) with either a pathologic murmur, an innocent murmur or no murmur were selected. The test algorithm, developed independently of CARD, analyzed each recording using an automated batch processing protocol. 3180 heart sound recordings from 603 outpatient visits were selected from CARD. Algorithm estimation of heart rate was similar to gold standard. Sensitivity and specificity for detection of pathologic cases were 93% (CI 90-95%) and 81% (CI 75-85%), respectively, with accuracy 88% (CI 85-91%). Performance varied according to algorithm certainty measure, age of patient, heart rate, murmur intensity, location of recording on the chest and pathologic diagnosis. This is the first reported comprehensive and objective evaluation of an AI-based murmur detection algorithm to our knowledge. The test algorithm performed well in this virtual clinical trial. This strategy can be used to efficiently compare performance of other algorithms against the same dataset and improve understanding of the potential clinical usefulness of AI-assisted auscultation.

Computational Modeling and Analysis of Murmurs Generated by Modeled Aortic Stenoses

In this study, coupled hemodynamic-acoustic simulations are employed to study the generation and propagation of murmurs associated with aortic stenoses where the aorta with a stenosed aortic valve is modeled as a curved pipe with a constriction near the inlet. The hemodynamics of the post-stenotic flow is investigated in detail in our previous numerical study. The temporal history of the pressure on the aortic lumen is recorded during the hemodynamic study and used as the murmur source in the acoustic simulations. The thorax is modeled as an elliptic cylinder and the thoracic tissue is assumed to be homogeneous, linear and viscoelastic. A previously developed high-order numerical method that is capable of dealing with immersed bodies is applied in the acoustic simulations. To mimic the clinical practice of auscultation, the sound signals from the epidermal surface are collected. The simulations show that the source of the aortic stenosis murmur is located at the proximal end of the aortic arch and that the sound intensity pattern on the epidermal surface can predict the source location of the murmurs reasonably well. Spectral analysis of the murmur reveals the disconnect between the break frequency obtained from the flow and from the murmur signal. Finally, it is also demonstrated that the source locations can also be predicted by solving an inverse problem using the free-space Green's function. The implications of these results for cardiac auscultation are discussed.

A Deep Machine Learning Method for Classifying Cyclic Time Series of Biological Signals Using Time-Growing Neural Network

This paper presents a novel method for learning the cyclic contents of stochastic time series: the deep time-growing neural network (DTGNN). The DTGNN combines supervised and unsupervised methods in different levels of learning for an enhanced performance. It is employed by a multiscale learning structure to classify cyclic time series (CTS), in which the dynamic contents of the time series are preserved in an efficient manner. This paper suggests a systematic procedure for finding the design parameter of the classification method for a one-versus-multiple class application. A novel validation method is also suggested for evaluating the structural risk, both in a quantitative and a qualitative manner. The effect of the DTGNN on the performance of the classifier is statistically validated through the repeated random subsampling using different sets of CTS, from different medical applications. The validation involves four medical databases, comprised of 108 recordings of the electroencephalogram signal, 90 recordings of the electromyogram signal, 130 recordings of the heart sound signal, and 50 recordings of the respiratory sound signal. Results of the statistical validations show that the DTGNN significantly improves the performance of the classification and also exhibits an optimal structural risk.

Estimating pressure gradients by auscultation: How technology (echocardiography) can help improve clinical skills

AIM

To extend our previously-published experience in estimating pressure gradients (PG) via physical examination in a large patient cohort.

METHODS

From January 1, 1997 through December 31, 2009, an attending pediatric cardiologist compared clinical examination (EXAM) with Doppler-echo (ECHO), in 1193 patients with pulmonic stenosis (PS, including tetralogy of Fallot), aortic stenosis (AS), and ventricular septal defect (VSD). EXAM PG estimates were based primarily on a murmur’s pitch, grade, and length. ECHO peak instantaneous PG was derived from the modified Bernoulli equation. Patients were 0-38.4 years old (median 4.8).

RESULTS

For all patients, EXAM correlated highly with ECHO: ECHO = 0.99 (EXAM) + 3.2 mmHg; r = +0.89; P < 0.0001. Agreement was excellent (mean difference = -2.9 ± 16.1 mmHg). In 78% of all patients, agreement between EXAM and ECHO was within 15 mmHg and within 5 mmHg in 45%. Clinical estimates of PS PG were more accurate than of AS and VSD. A palpable precordial thrill and increasing loudness of the murmur predicted higher gradients (P < 0.0001). Weight did not influence accuracy. A learning curve was evident, such that the most recent quartile of patients showed ECHO = 1.01 (EXAM) + 1.9, r = +0.92, P < 0.0001; during this time, the attending pediatric cardiologist had been > 10 years in practice.

CONCLUSION

Clinical examination can accurately estimate PG in PS, AS, or VSD. Continual correlation of clinical findings with echocardiography can lead to highly accurate diagnostic skills.

A Computational Method for Analyzing the Biomechanics of Arterial Bruits

A computational framework consisting of a one-way coupled hemodynamic-acoustic method and a wave-decomposition based postprocessing approach is developed to investigate the biomechanics of arterial bruits. This framework is then applied for studying the effect of the shear wave on the generation and propagation of bruits from a modeled stenosed artery. The blood flow in the artery is solved by an immersed boundary method (IBM) based incompressible flow solver. The sound generation and propagation in the blood volume are modeled by the linearized perturbed compressible equations, while the sound propagation through the surrounding tissue is modeled by the linear elastic wave equation. A decomposition method is employed to separate the acoustic signal into a compression/longitudinal component (curl free) and a shear/transverse component (divergence free), and the sound signals from cases with and without the shear modulus are monitored on the epidermal surface and are analyzed to reveal the influence of the shear wave. The results show that the compression wave dominates the detected sound signal in the immediate vicinity of the stenosis, whereas the shear wave has more influence on surface signals further downstream of the stenosis. The implications of these results on cardiac auscultation are discussed.

Initial Field Test of a Cloud-Based Cardiac Auscultation System to Determine Murmur Etiology in Rural China

A system for collection, distribution, and long distant, asynchronous interpretation of cardiac auscultation has been developed and field-tested in rural China. We initiated a proof-of-concept test as a critical component of design of a system to allow rural physicians with little experience in evaluation of congenital heart disease (CHD) to obtain assistance in diagnosis and management of children with significant heart disease. The project tested the hypothesis that acceptable screening of heart murmurs could be accomplished using a digital stethoscope and internet cloud transmittal to deliver phonocardiograms to an experienced observer. Of the 7993 children who underwent school-based screening in the Menghai District of Yunnan Province, Peoples Republic of China, 149 had a murmur noted by a screener. They had digital heart sounds and phonocardiograms collected with the HeartLink tele auscultation system, and underwent echocardiography by a cardiology resident from the First Affiliated Hospital of Kunming Medical University. The digital phonocardiograms, stored on a cloud server, were later remotely reviewed by a board-certified American pediatric cardiologist. Fourteen of these subjects were found to have CHD confirmed by echocardiogram. Using the HeartLink system, the pediatric cardiologist identified 11 of the 14 subjects with pathological murmurs, and missed three subjects with atrial septal defects, which were incorrectly identified as venous hum or Still's murmur. In addition, ten subjects were recorded as having pathological murmurs, when no CHD was confirmed by echocardiography during the field study. The overall test accuracy was 91% with 78.5% sensitivity and 92.6% specificity. This proof-of-concept study demonstrated the feasibility of differentiating pathologic murmurs due to CHD from normal functional heart murmurs with the HeartLink system. This field study is an initial step to develop a cost-effective CHD screening strategy in low-resource settings with a shortage of trained medical professionals and pediatric heart programs.

In defence of auscultation: a glorious future?

Auscultation of the heart using a simple stethoscope continues to be a central aspect of the cardiovascular examination despite declining proficiency and availability of competing technologies such as hand-held ultrasound. In the ears and mind of a trained cardiologist, heart sounds can provide important information to help screen for certain diseases such as valvar lesions and many congenital defects. Using emerging technology, auscultation is poised to undergo a transformation that will simultaneously improve the teaching and evaluation of this important clinical skill and create a new generation of smart stethoscopes, capable of assisting the clinician in quickly and confidently screening for heart disease. These developments have important implications for global health, screening of athletes and recognition of congenital heart disease.

The Diagnostic Utility of Computer-Assisted Auscultation for the Early Detection of Cardiac Murmurs of Structural Origin in the Periodic Health Evaluation

BACKGROUND

Identification of the nature of cardiac murmurs during the periodic health evaluation (PHE) of athletes is challenging due to the difficulty in distinguishing between murmurs of physiological or structural origin. Previously, computer-assisted auscultation (CAA) has shown promise to support appropriate referrals in the nonathlete pediatric population.

HYPOTHESIS

CAA has the ability to accurately detect cardiac murmurs of structural origin during a PHE in collegiate athletes.

STUDY DESIGN

Cross-sectional, descriptive study.

LEVEL OF EVIDENCE

Level 3.

METHODS

A total of 131 collegiate athletes (104 men, 28 women; mean age, 20 ± 2 years) completed a sports physician (SP)-driven PHE consisting of a cardiac history questionnaire and a physical examination. An independent CAA assessment was performed by a technician who was blinded to the SP findings. Athletes with suspected structural murmurs or other clinical reasons for concern were referred to a cardiologist for confirmatory echocardiography (EC).

RESULTS

Twenty-five athletes were referred for further investigation (17 murmurs, 6 abnormal electrocardiographs, 1 displaced apex, and 1 possible case of Marfan syndrome). EC confirmed 3 structural and 22 physiological murmurs. The SP flagged 5 individuals with possible underlying structural pathology; 2 of these murmurs were confirmed as structural in nature. Fourteen murmurs were referred by CAA; 3 of these were confirmed as structural in origin by EC. One such murmur was not detected by the SP, however, and detected by CAA. The sensitivity of CAA was 100% compared with 66.7% shown by the SP, while specificity was 50% and 66.7%, respectively.

CONCLUSION

CAA shows potential to be a feasible adjunct for improving the identification of structural murmurs in the athlete population. Over-referral by CAA for EC requires further investigation and possible refinements to the current algorithm. Further studies are needed to determine the true sensitivity, specificity, and cost efficacy of the device among the athletic population.

CLINICAL RELEVANCE

CAA may be a useful cardiac screening adjunct during the PHE of athletes, particularly as it may guide appropriate referral of suspected structural murmurs for further investigation.

Computer-aided auscultation of murmurs in children: evaluation of commercially available software

BACKGROUND

Heart murmurs are common in children and may represent congenital or acquired cardiac pathology. Auscultation is challenging and many primary-care physicians lack the skill to differentiate innocent from pathologic murmurs. We sought to determine whether computer-aided auscultation (CardioscanTM) identifies which children require referral to a cardiologist.

METHODS

We consecutively enrolled children aged between 0 and 17 years with a murmur, innocent or pathologic, being evaluated in a tertiary-care cardiology clinic. Children being evaluated for the first time and patients with known cardiac pathology were eligible. We excluded children who had undergone cardiac surgery previously or were unable to sit still for auscultation. CardioscanTM auscultation was performed in a quiet room with the subject in the supine position. The sensitivity and specificity of a potentially pathologic murmur designation by CardioscanTM - that is, requiring referral - was determined using echocardiography as the reference standard.

RESULTS

We enrolled 126 subjects (44% female) with a median age of 1.7 years, with 93 (74%) having cardiac pathology. The sensitivity and specificity of a potentially pathologic murmur determination by CardioscanTM for identification of cardiac pathology were 83.9 and 30.3%, respectively, versus 75.0 and 71.4%, respectively, when limited to subjects with a heart rate of 50-120 beats per minute. The combination of a CardioscanTM potentially pathologic murmur designation or an abnormal electrocardiogram improved sensitivity to 93.5%, with no haemodynamically significant lesions missed.

CONCLUSIONS

Sensitivity of CardioscanTM when interpreted in conjunction with an abnormal electrocardiogram was high, although specificity was poor. Re-evaluation of computer-aided auscultation will remain necessary as advances in this technology become available.

Outpatient services and primary care: scoping review, substudies and international comparisons

Aim

This study updates a previous scoping review published by the National Institute for Health Research (NIHR) in 2006 (Roland M, McDonald R, Sibbald B.Outpatient Services and Primary Care: A Scoping Review of Research Into Strategies For Improving Outpatient Effectiveness and Efficiency. Southampton: NIHR Trials and Studies Coordinating Centre; 2006) and focuses on strategies to improve the effectiveness and efficiency of outpatient services.

Findings from the scoping review

Evidence from the scoping review suggests that, with appropriate safeguards, training and support, substantial parts of care given in outpatient clinics can be transferred to primary care. This includes additional evidence since our 2006 review which supports general practitioner (GP) follow-up as an alternative to outpatient follow-up appointments, primary medical care of chronic conditions and minor surgery in primary care. Relocating specialists to primary care settings is popular with patients, and increased joint working between specialists and GPs, as suggested in the NHS Five Year Forward View, can be of substantial educational value. However, for these approaches there is very limited information on cost-effectiveness; we do not know whether they increase or reduce overall demand and whether the new models cost more or less than traditional approaches. One promising development is the increasing use of e-mail between GPs and specialists, with some studies suggesting that better communication (including the transmission of results and images) could substantially reduce the need for some referrals.

Findings from the substudies

Because of the limited literature on some areas, we conducted a number of substudies in England. The first was of referral management centres, which have been established to triage and, potentially, divert referrals away from hospitals. These centres encounter practical and administrative challenges and have difficulty getting buy-in from local clinicians. Their effectiveness is uncertain, as is the effect of schemes which provide systematic review of referrals within GP practices. However, the latter appear to have more positive educational value, as shown in our second substudy. We also studied consultants who held contracts with community-based organisations rather than with hospital trusts. Although these posts offer opportunities in terms of breaking down artificial and unhelpful primary–secondary care barriers, they may be constrained by their idiosyncratic nature, a lack of clarity around roles, challenges to professional identity and a lack of opportunities for professional development. Finally, we examined the work done by other countries to reform activity at the primary–secondary care interface. Common approaches included the use of financial mechanisms and incentives, the transfer of work to primary care, the relocation of specialists and the use of guidelines and protocols. With the possible exception of financial incentives, the lack of robust evidence on the effect of these approaches and the contexts in which they were introduced limits the lessons that can be drawn for the English NHS.

Conclusions

For many conditions, high-quality care in the community can be provided and is popular with patients. There is little conclusive evidence on the cost-effectiveness of the provision of more care in the community. In developing new models of care for the NHS, it should not be assumed that community-based care will be cheaper than conventional hospital-based care. Possible reasons care in the community may be more expensive include supply-induced demand and addressing unmet need through new forms of care and through loss of efficiency gained from concentrating services in hospitals. Evidence from this study suggests that further shifts of care into the community can be justified only if (a) high value is given to patient convenience in relation to NHS costs or (b) community care can be provided in a way that reduces overall health-care costs. However, reconfigurations of services are often introduced without adequate evaluation and it is important that new NHS initiatives should collect data to show whether or not they have added value, and improved quality and patient and staff experience.

Funding

The NIHR Health Services and Delivery Research programme.

Computer-assisted diagnosis for chronic heart failure by the analysis of their cardiac reserve and heart sound characteristics

An innovative computer-assisted diagnosis system for chronic heart failure (CHF) was proposed in this study, based on cardiac reserve (CR) indexes extraction, heart sound hybrid characteristics extraction and intelligent diagnosis model definition. Firstly, the modified wavelet packet-based denoising method was applied to data pre-processing. Then, the CR indexes such as the ratio of diastolic to systolic duration (D/S) and the amplitude ratio of the first to second heart sound (S1/S2) were extracted. The feature set consisting of the heart sound characteristics such as multifractal spectrum parameters, the frequency corresponding to the maximum peak of the normalized PSD curve (fPSDmax) and adaptive sub-band energy fraction (sub_EF) were calculated based on multifractal detrended fluctuation analysis (MF-DFA), maximum entropy spectra estimation (MESE) and empirical mode decomposition (EMD). Statistical methods such as t-test and receiver operating characteristic (ROC) curve analysis were performed to analyze the difference of each parameter between the healthy and CHF patients. Finally, least square support vector machine (LS-SVM) was employed for the implementation of intelligent diagnosis. The result indicates the achieved diagnostic accuracy, sensitivity and specificity of the proposed system are 95.39%, 96.59% and 93.75% for the detection of CHF, respectively. The selected cutoff values of the diagnosis features are D/S=1.59, S1/S2=1.31, Δα=1.34 and fPSDmax=22.49, determined by ROC curve analysis. This study suggests the proposed methodology could provide a technical clue for the CHF point-of-care system design and be a supplement for CHF diagnosis.

[Heart murmurs in asymptomatic children: When should you refer?]

Heart murmurs are common in children and adolescents. Although most are innocent, an isolated heart murmur in asymptomatic children may be the sole finding indicating serious heart disease. Historical elements of familial heart disease, cardiovascular symptoms and a well-conducted medical examination can identify children with an increased risk of heart disease. The distinction between an innocent heart murmur and a pathologic heart murmur is not always easy for primary care physicians because most of them have little experience with auscultation searching for congenital heart malformation. Echocardiography provides a definitive diagnosis of heart disease but is not required in case of innocent murmur. Inappropriate pediatric cardiologist and echocardiographic referral leads to useless and expensive examinations, resulting in a work overload for pediatric cardiologists. The objective of this review is to provide the keys to differentiate innocent and pathologic murmurs, and to help physicians decide on the optimal diagnostic strategy.

An Intelligent Phonocardiography for Automated Screening of Pediatric Heart Diseases

This paper presents a robust device for automated screening of pediatric heart diseases based on our unique processing method in murmur characterization; the Arash-Band method. The present study modifies the Arash-Band method and employs output of the modified method in conjunction with the two other original techniques to extract indicative feature vectors for the screening. The extracted feature vectors are classified by using the support vector machine method. Results show that the proposed modifications significantly enhances performance of the Arash-Band in terms of the both accuracy and sensitivity as the corresponding effect sizes are sufficiently large. The proposed algorithm has been incorporated into an Android-based tablet to constitute an intelligent phonocardiogram with the automatic screening capability. In order to obtain confidence interval of the accuracy and sensitivity, an inferable statistical test is applied on our database containing the phonocardiogram signals recorded from 263 of the referrals to a hospital. The expected value of the accuracy/sensitivity is estimated to be 87.45 % / 87.29 % with a 95 % confidence interval of (80.19 % - 92.47 %) / (76.01 % - 95.78 %) exhibiting superior performance than a pediatric cardiologist who relies on conventional or even computer-assisted auscultation.

A Novel Method for Screening Children with Isolated Bicuspid Aortic Valve

This paper presents a novel processing method for heart sound signal: the statistical time growing neural network (STGNN). The STGNN performs a robust classification by merging supervised and unsupervised statistical methods to overcome non-stationary behavior of the signal. By combining available preprocessing and segmentation techniques and the STGNN classifier, we build an automatic tool for screening children with isolated BAV, the congenital heart malformation which can lead to serious cardiovascular lesions. Children with BAV (22 individuals) and healthy condition (28 individuals) are subjected to the study. The performance of the STGNN is compared to that of a time growing neural network (CTGNN) and a conventional support vector (CSVM) machine, using balanced repeated random sub sampling. The average of the accuracy/sensitivity is estimated to be 87.4/86.5 for the STGNN, 81.8/83.4 for the CTGNN, and 72.9/66.8 for the CSVM. Results show that the STGNN offers better performance and provides more immunity to the background noise as compared to the CTGNN and CSVM. The method is implementable in a computer system to be employed in primary healthcare centers to improve the screening accuracy.

Efficiency, sensitivity and specificity of automated auscultation diagnosis device for detection and discrimination of cardiac murmurs in children

OBJECTIVE

Intelligent electronic stethoscopes and computer-aided auscultation systems have highlighted a new era in cardiac auscultation in children. Several collaborative multidisciplinary researches in this field are performed by physicians and computer specialists. Recently, a novel medical software device, Automated Auscultation Diagnosis Device (AADD), has been reported with intelligent diagnosing ability to differentiate cardiac murmur from breath sounds in children with normal and abnormal hearts due to congenital heart disease. The aim of this study is to determine efficiency, sensitivity and specificity of the diagnoses made by this AADD in children with and without cardiac disease.

METHODS

We performed a cross-sectional study to determine efficiency, sensitivity and specificity of diagnoses made by AADD. Our patient population was two groups of children with and without cardiac disease(563 patients and 50 normal). SPSS version 16 was used to calculate sensitivity, specificity and efficiency and descriptive analysis.

FINDINGS

Using cardiac sound recording in four conventional cardiac areas of auscultation (including aortic, pulmonary, tricuspid and mitral), AADD proved to have a ≥90% sensitivity, specificity and efficiency for making the correct diagnosis in children with heart disease and 100% diagnostic accuracy in children with normal hearts either with or without innocent murmurs.

CONCLUSION

Considering the high sensitivity, specificity and efficiency of AADD for making the correct diagnosis, application of this software is recommended for family physicians to enhance proper and timely patients' referral to pediatric cardiologists in order to provide better diagnostic facilities for pediatric patients who live in deprived and underserved rural areas with lack access to pediatric cardiologists.

Biomedical informatics for computer-aided decision support systems: a survey

The volumes of current patient data as well as their complexity make clinical decision making more challenging than ever for physicians and other care givers. This situation calls for the use of biomedical informatics methods to process data and form recommendations and/or predictions to assist such decision makers. The design, implementation, and use of biomedical informatics systems in the form of computer-aided decision support have become essential and widely used over the last two decades. This paper provides a brief review of such systems, their application protocols and methodologies, and the future challenges and directions they suggest.

Skills of primary healthcare physicians in paediatric cardiac auscultation

AIM

To evaluate the performance of primary healthcare physicians in paediatric cardiac auscultation and the impact of a multimedia-based teaching intervention.

METHODS

A total of 106 primary healthcare physicians (77 paediatricians, 14 general practitioners and 15 medical graduates) attended four paediatric cardiac auscultation teaching courses based on virtual patients' presentation (digital phonocardiography). Their auscultatory performance was documented at the beginning of each course and at the end of two of the courses.

RESULTS

Participants initially detected 73% of abnormal murmurs and 17% of additional sounds, while 22% of innocent murmurs were interpreted as abnormal. Overall cardiac auscultation performance, assessed by a combined auscultation score, was low and independent of training level (graduates: 39.5/trainees: 42.8/board certified: 42.6, p = 0.89) or specialty (paediatricians: 42.7/general practitioners: 43.1, p = 0.89). Multimedia-based teaching was associated with a significant improvement in abnormal murmur (92.5%) and additional sound (40%) detection (p < 0.001), while 25% of innocent murmurs were still interpreted as abnormal (p = 0.127).

CONCLUSION

Clinical skills of primary healthcare physicians in paediatric cardiac auscultation, independent of training level or specialty, still leave potential for improvement. Multimedia-based teaching interventions represent an effective means of improving paediatric cardiac auscultatory skills.

Evaluation of cardiac auscultation skills in pediatric residents

Auscultation skills are in decline, but few studies have shown which specific aspects are most difficult for trainees. We evaluated individual aspects of cardiac auscultation among pediatric residents using recorded heart sounds to determine which elements pose the most difficulty.

METHODS

Auscultation proficiency was assessed among 34 trainees following a pediatric cardiology rotation using an open-set format evaluation module, similar to the actual clinical auscultation description process.

RESULTS

Diagnostic accuracy for distinguishing normal from abnormal cases was 73%. Findings most commonly correctly identified included pathological systolic and diastolic murmurs and widely split second heart sounds. Those least likely to be identified included continuous murmurs and clicks. Accuracy was low for identifying specific diagnoses.

CONCLUSIONS

Given time constraints for clinical skills teaching, this suggests that focusing on distinguishing normal from abnormal heart sounds and murmurs instead of making specific diagnoses may be a more realistic goal for pediatric resident auscultation training.

The promise of computer-assisted auscultation in screening for structural heart disease and clinical teaching

Abstract

Cardiac auscultation has been the central clinical tool for the diagnosis of valvular and other structural heart diseases for over a century. Physicians acquire competence in this technique through considerable training and experience. In Africa, however, we face a shortage of physicians and have the lowest health personnel-to-population ratio in the world. One of the proposed solutions for tackling this crisis is the adoption of health technologies and product innovations to support different cadres of health workers as part of task shifting.

Computer-assisted auscultation (CAA) uses a digital stethoscope combined with acoustic neural networking to provide a visual display of heart sounds and murmurs, and analyses the recordings to distinguish between innocent and pathological murmurs. In so doing, CAA may serve as an objective tool for the screening of structural heart disease and facilitate the teaching of cardiac auscultation. This article reviews potential clinical applications of CAA.

Multi-center, multi-topic heart sound databases and their applications

This paper describes a large resource of multi-center and multi-topic heart sound databases, which were based on the measured data from more than 9,000 heart sound samples (saved in WAV file format). According to different research topics, these samples were respectively stored in different folders (corresponding to different research topics and distributed over various cooperative research centers), most of which as subfolds were stored in a pooled folder in the principal center. According to different research topics, the measured data from these samples were used to create different databases. Relevant data for a specific topic can be pooled in a large database for further analysis. This resource is shared by members of related centers for their own specific topic. The applications of this resource include evaluation of cardiac safety of pregnant women, evaluation of cardiac reserve for children, athletes, addicts, astronauts, and general populations, as well as studies on a bedside method for evaluating cardiac energy, reversal of S1-S2 ratio, etc.

Automated heartsound analysis/computer-aided auscultation: a cardiologist's perspective and suggestions for future development

Heart disease is a major cause of worldwide morbidity and mortality. Properly performed, the cardiac auscultatory examination (listening to the heart with a stethoscope) is an inexpensive, widely available tool in the detection and management of heart disease. Unfortunately, accurate interpretation of heartsounds by primary care providers is fraught with error, leading to missed diagnosis of disease and/or excessive costs associated with evaluation of normal variants. Therefore, automated heartsound analysis, also known as computer aided auscultation (CAA), has the potential to become a cost-effective screening and diagnostic tool in the primary care setting. A cardiologist's suggestions for CAA system design and algorithmic development are provided.