Artificial neural network-based method of screening heart murmurs in children

Computerized screening of children congenital heart diseases

In this paper, we propose a method for automated screening of congenital heart diseases in children through heart sound analysis techniques. Our method relies on categorizing the pathological murmurs based on the heart sections initiating them. We show that these pathelogical murmur categories can be identified by examining the heart sound energy over specific frequency bands, which we call, Arash-Bands. To specify the Arash-Band for a category, we evaluate the energy of the heart sound over all possible frequency bands. The Arash-Band is the frequency band that provides the lowest error in clustering the instances of that category against the normal ones. The energy content of the Arash-Bands for different categories constitue a feature vector that is suitable for classification using a neural network. In order to train, and to evaluate the performance of the proposed method, we use a training data-bank, as well as a test data-bank, collectively consisting of ninety samples (normal and abnormal). Our results show that in more than 94% of cases, our method correctly identifies children with congenital heart diseases. This percentage improves to 100%, when we use the Jack-Knife validation method over all the 90 samples.

Utility of store-and-forward pediatric telecardiology evaluation in distinguishing normal from pathologic pediatric heart sounds

Because pediatric cardiologists can accurately diagnose innocent murmurs by physical exam alone, the authors developed a system for remote cardiac auscultation. They hypothesized that their system could accurately classify auscultatory findings as normal/innocent or pathologic. Patients undergoing evaluation underwent examination, echocardiography, and heart sound recording. Pediatric cardiologists evaluated the heart sounds and classified the case as either normal/innocent or pathologic. They reviewed103 heart sound data sets; 85% of the cases were accurately classified as either normal/innocent or pathologic, with a sensitivity of 82% and specificity of 86%. However, when accounting for clinical diagnosis, reviewer uncertainty, and ECG abnormalities, the sensitivity and specificity improved to 91% and 88% (accuracy 89%), respectively. Degree of certainty with the telecardiology diagnosis correlated with correct interpretation (P < .005). Digital heart sound recordings evaluated via telemedicine can distinguish normal/innocent murmurs from pathologic ones. Such a system could improve the use of pediatric cardiology services.

Placental determinants of fetal growth: identification of key factors in the insulin-like growth factor and cytokine systems using artificial neural networks

BACKGROUND

Changes and relationships of components of the cytokine and IGF systems have been shown in placenta and cord serum of fetal growth restricted (FGR) compared with normal newborns (AGA). This study aimed to analyse a data set of clinical and biochemical data in FGR and AGA newborns to assess if a mathematical model existed and was capable of identifying these two different conditions in order to identify the variables which had a mathematically consistent biological relevance to fetal growth.

METHODS

Whole villous tissue was collected at birth from FGR (N = 20) and AGA neonates (N = 28). Total RNA was extracted, reverse transcribed and then real-time quantitative (TaqMan) RT-PCR was performed to quantify cDNA for IGF-I, IGF-II, IGFBP-1, IGFBP-2 and IL-6. The corresponding proteins with TNF-alpha in addition were assayed in placental lysates using specific kits. The data were analysed using Artificial Neural Networks (supervised networks), and principal component analysis and connectivity map.

RESULTS

The IGF system and IL-6 allowed to predict FGR in approximately 92% of the cases and AGA in 85% of the cases with a low number of errors. IGF-II, IGFBP-2, and IL-6 content in the placental lysates were the most important factors connected with FGR. The condition of being FGR was connected mainly with the IGF-II placental content, and the latter with IL-6 and IGFBP-2 concentrations in placental lysates.

CONCLUSION

These results suggest that further research in humans should focus on these biochemical data. Furthermore, this study offered a critical revision of previous studies. The understanding of this system biology is relevant to the development of future therapeutical interventions possibly aiming at reducing IL-6 and IGFBP-2 concentrations preserving IGF bioactivity in both placenta and fetus.

Knowledge based system with embedded intelligent heart sound analyser for diagnosing cardiovascular disorders

Cardiovascular disease (CVD) is the leading cause of death worldwide, and due to the lack of early detection techniques, the incidence of CVD is increasing day by day. In order to address this limitation, a knowledge based system with embedded intelligent heart sound analyser (KBHSA) has been developed to diagnose cardiovascular disorders at early stages. The system analyses digitized heart sounds that are recorded from an electronic stethoscope using advanced digital signal processing and artificial intelligence techniques. KBHSA takes into account data including the patient's personal and past medical history, clinical examination, auscultation findings, chest x-ray and echocardiogram, and provides a list of diseases that it has diagnosed. The system can assist the general physician in making more accurate and reliable diagnosis under emergency conditions where expert cardiologists and advanced equipment are not readily available. To test the validity of the system, abnormal heart sound samples and medical data from 40 patients were recorded and analysed. The diagnoses made by the system were counter checked by four senior cardiologists in Malaysia. The results show that the findings of KBHSA coincide with those of cardiologists.

Backpropagation artificial neural network classifier to detect changes in heart sound due to mitral valve regurgitation

The phonocardiograph (PCG) can provide a noninvasive diagnostic ability to the clinicians and technicians to compare the heart acoustic signal obtained from normal and that of pathological heart (cardiac patient). This instrument was connected to the computer through the analog to digital (A/D) converter. The digital data stored for the normal and diseased (mitral valve regurgitation) heart in the computer were decomposed through the Coifman 4th order wavelet kernel. The decomposed phonocardiographic (PCG) data were tested by backpropagation artificial neural network (ANN). The network was containing 64 nodes in the input layer, weighted from the decomposed components of the PCG in the input layer, 16 nodes in the hidden layer and an output node. The ANN was found effective in differentiating the wavelet components of the PCG from mitral valve regurgitation confirmed person (93%) to normal subjects (98%) with an overall performance of 95.5%. This system can also be used to detect the defects in cardiac valves especially, and other several cardiac disorders in general.

Phono-spectrographic analysis of heart murmur in children

BACKGROUND

More than 90% of heart murmurs in children are innocent. Frequently the skills of the first examiner are not adequate to differentiate between innocent and pathological murmurs. Our goal was to evaluate the value of a simple and low-cost phonocardiographic recording and analysis system in determining the characteristic features of heart murmurs in children and in distinguishing innocent systolic murmurs from pathological.

METHODS

The system consisting of an electronic stethoscope and a multimedia laptop computer was used for the recording, monitoring and analysis of auscultation findings. The recorded sounds were examined graphically and numerically using combined phono-spectrograms. The data consisted of heart sound recordings from 807 pediatric patients, including 88 normal cases without any murmur, 447 innocent murmurs and 272 pathological murmurs. The phono-spectrographic features of heart murmurs were examined visually and numerically. From this database, 50 innocent vibratory murmurs, 25 innocent ejection murmurs and 50 easily confusable, mildly pathological systolic murmurs were selected to test whether quantitative phono-spectrographic analysis could be used as an accurate screening tool for systolic heart murmurs in children.

RESULTS

The phono-spectrograms of the most common innocent and pathological murmurs were presented as examples of the whole data set. Typically, innocent murmurs had lower frequencies (below 200 Hz) and a frequency spectrum with a more harmonic structure than pathological cases. Quantitative analysis revealed no significant differences in the duration of S1 and S2 or loudness of systolic murmurs between the pathological and physiological systolic murmurs. However, the pathological murmurs included both lower and higher frequencies than the physiological ones (p < 0.001 for both low and high frequency limits). If the systolic murmur contained intensive frequency components of over 200 Hz, or its length accounted for over 80 % of the whole systolic duration, it was considered pathological. Using these criteria, 90 % specificity and 91 % sensitivity in screening were achieved.

CONCLUSION

Phono-spectrographic analysis improves the accuracy of primary heart murmur evaluation and educates inexperienced listener. Using simple quantitative criterias a level of pediatric cardiologist is easily achieved in screening heart murmurs in children.

Heart energy signature spectrogram for cardiovascular diagnosis

A new method and application is proposed to characterize intensity and pitch of human heart sounds and murmurs. Using recorded heart sounds from the library of one of the authors, a visual map of heart sound energy was established. Both normal and abnormal heart sound recordings were studied. Representation is based on Wigner-Ville joint time-frequency transformations. The proposed methodology separates acoustic contributions of cardiac events simultaneously in pitch, time and energy. The resolution accuracy is superior to any other existing spectrogram method. The characteristic energy signature of the innocent heart murmur in a child with the S3 sound is presented. It allows clear detection of S1, S2 and S3 sounds, S2 split, systolic murmur, and intensity of these components. The original signal, heart sound power change with time, time-averaged frequency, energy density spectra and instantaneous variations of power and frequency/pitch with time, are presented. These data allow full quantitative characterization of heart sounds and murmurs. High accuracy in both time and pitch resolution is demonstrated. Resulting visual images have self-referencing quality, whereby individual features and their changes become immediately obvious.

A Framework for the Analysis of Acoustical Cardiac Signals

Skilled cardiologists perform cardiac auscultation, acquiring and interpreting heart sounds, by implicitly carrying out a sequence of steps. These include discarding clinically irrelevant beats, selectively tuning in to particular frequencies and aggregating information across time to make a diagnosis. In this paper, we formalize a series of analytical stages for processing heart sounds, propose algorithms to enable computers to approximate these steps, and investigate the effectiveness of each step in extracting relevant information from actual patient data. Through such reasoning, we provide insight into the relative difficulty of the various tasks involved in the accurate interpretation of heart sounds. We also evaluate the contribution of each analytical stage in the overall assessment of patients. We expect our framework and associated software to be useful to educators wanting to teach cardiac auscultation, and to primary care physicians, who can benefit from presentation tools for computer-assisted diagnosis of cardiac disorders. Researchers may also employ the comprehensive processing provided by our framework to develop more powerful, fully automated auscultation applications.

Assessing children's heart sounds at a distance with digital recordings

OBJECTIVE

The objective of this study was to assess whether computer-stored digital sound recordings can be used to distinguish innocent from pathologic systolic murmurs.

METHODS

Recordings of 55 children aged 1 month to 19 years were made remotely with the use of a digital stethoscope and were e-mailed to a computer in our center for later assessment. Eight-second recordings were made by a physician in 2 to 4 locations on the chest. Three cardiologists who were blinded to the diagnosis reviewed the recordings independently using stethophones to assess the splitting of the second heart sound and whether murmurs were innocent or pathologic. Diagnoses were confirmed with echocardiography.

RESULTS

Seventeen children had innocent murmurs and 38 had pathologic murmurs. For the 3 cardiologists, sensitivity was 0.87 to 1.0, specificity was 0.82 to 0.88, negative predictive value was 0.75 to 1.0, and positive predictive value was 0.93 to 0.95. Assessment of splitting of second heart sound was highly accurate.

CONCLUSIONS

Digital recordings of children's heart sounds allow reliable differentiation between innocent and pathologic murmurs. Use of this technology may allow remote diagnosis of childhood murmurs and avoid the expense and stress of travel to pediatric cardiology centers for some children. Cardiologists who use recordings should assess their diagnostic accuracy before clinical application.

Feature extraction for systolic heart murmur classification

Heart murmurs are often the first signs of pathological changes of the heart valves, and they are usually found during auscultation in the primary health care. Distinguishing a pathological murmur from a physiological murmur is however difficult, why an "intelligent stethoscope" with decision support abilities would be of great value. Phonocardiographic signals were acquired from 36 patients with aortic valve stenosis, mitral insufficiency or physiological murmurs, and the data were analyzed with the aim to find a suitable feature subset for automatic classification of heart murmurs. Techniques such as Shannon energy, wavelets, fractal dimensions and recurrence quantification analysis were used to extract 207 features. 157 of these features have not previously been used in heart murmur classification. A multi-domain subset consisting of 14, both old and new, features was derived using Pudil's sequential floating forward selection (SFFS) method. This subset was compared with several single domain feature sets. Using neural network classification, the selected multi-domain subset gave the best results; 86% correct classifications compared to 68% for the first runner-up. In conclusion, the derived feature set was superior to the comparative sets, and seems rather robust to noisy data.

Detection of heart murmurs using wavelet analysis and artificial neural networks

This paper presents the algorithm and technical aspects of an intelligent diagnostic system for the detection of heart murmurs. The purpose of this research is to address the lack of effectively accurate cardiac auscultation present at the primary care physician office by development of an algorithm capable of operating within the hectic environment of the primary care office. The proposed algorithm consists of three main stages. First; denoising of input data (digital recordings of heart sounds), via Wavelet Packet Analysis. Second; input vector preparation through the use of Principal Component Analysis and block processing. Third; classification of the heart sound using an Artificial Neural Network. Initial testing revealed the intelligent diagnostic system can differentiate between normal healthy heart sounds and abnormal heart sounds (e.g., murmurs), with a specificity of 70.5% and a sensitivity of 64.7%.

Diagnosing aortic valve stenosis by correlation analysis of wavelet filtered heart sounds

Traditional auscultation performed by the general practitioner remains problematic and often gives significant results only in a late stage of heart valve disease. Valve stenoses and insufficiencies are nowadays diagnosed with accurate but expensive ultrasonic devices. This study aimed to develop a new heart sound analysis method for diagnosing aortic valve stenoses (AVS) based on a wavelet and correlation technique approach. Heart sounds recorded from 373 patients (107 AVS patients, 61 healthy controls (REF) and 205 patients with other valve diseases (OVD)) with an electronic stethoscope were wavelet filtered, and envelopes were calculated. Three correlations on the basis of these envelopes were performed: within the AVS group, between the groups AVS and REF and between the groups AVS and OVD, resulting in the mean correlation coefficients rAVS, rAVSv.REF and rAVSv.OVD. These results showed that rAVS (0.783 +/- 0.097) is significantly higher (p < 0.0001) than rAVSv.REF (0.590 +/- 0.056) and rAVSv.OVD (0.516 +/- 0.056), leading to a highly significant discrimination between the groups. The wavelet and correlation-based heart sound analysis system should be useful to general practitioners for low-cost, easy-to-use automatic diagnosis of aortic valve stenoses.

A classifier based on the artificial neural network approach for cardiologic auscultation in pediatrics

OBJECTIVE

This research work was aimed at developing a reliable screening device for diagnosis of heart murmurs in pediatrics. This is a significant problem in pediatric cardiology because of the high rate of incidence of heart murmurs in this population (reportedly 77-95%), of which only a small fraction arises from congenital heart disease. The screening devices currently available (e.g. chest X-ray, electrocardiogram, etc.) suffer from poor sensitivity and specificity in detecting congenital heart disease. Thus, patients with heart murmurs today are frequently assessed by consultation as well with advanced imaging techniques. The most prominent among these is echocardiography. However, echocardiography is expensive and is usually only available in healthcare centers in major cities. Thus, for patients being evaluated with a heart murmur, developing a more accurate screening device is vital to efforts in reducing health care costs.

METHODS AND MATERIAL

The data set was collected from incoming pediatrics at the cardiology clinic of The Children's Hospital (Denver, Colorado), on whom echocardiography had been performed to identify congenital heart disease. Recordings of approximately 10-15s duration were made at 44,100Hz and the average record length was approximately 60,000 points. The best three cycles with respect to signal quality sounds were extracted from the original recording. The resulting data comprised 241 examples, of which 88 were examples of innocent murmurs and 153 were examples of pathological murmurs. The selected phonocardiograms were subject to the digital signal processing (DSP) technique of fast Fourier transform (FFT) to extract the energy spectrum in frequency domain. The spectral range was 0-300Hz at a resolution of 1Hz. The processed signals were used to develop statistical classifiers and a classifier based on our in-house artificial neural network (ANN) software. For the latter, we also tried enhancements to the basic ANN scheme. These included a method for setting the decision-threshold and a scheme for consensus-based decision by a committee of experts.

RESULTS

Of the different classifiers tested, the ANN-based classifier performed the best. With this classifier, we were able to achieve classification accuracy of 83% sensitivity and 90% specificity in discriminating between innocent and pathological heart murmurs. For the problem of discrimination between innocent murmurs and murmurs of the ventricular septal defect (VSD), the accuracy was higher, with sensitivity of 90% and specificity of 93%.

CONCLUSIONS

An ANN-based approach for detection and identification of congenital heart disease in pediatrics from heart murmurs can result in an accurate screening device. Considering that only a simple feature set was used for classification, the results are very encouraging and point out the need for further development using improved feature set with more potent diagnostic variables.

A decision tree--based method for the differential diagnosis of Aortic Stenosis from Mitral Regurgitation using heart sounds

BACKGROUND

New technologies like echocardiography, color Doppler, CT, and MRI provide more direct and accurate evidence of heart disease than heart auscultation. However, these modalities are costly, large in size and operationally complex and therefore are not suitable for use in rural areas, in homecare and generally in primary healthcare set-ups. Furthermore the majority of internal medicine and cardiology training programs underestimate the value of cardiac auscultation and junior clinicians are not adequately trained in this field. Therefore efficient decision support systems would be very useful for supporting clinicians to make better heart sound diagnosis. In this study a rule-based method, based on decision trees, has been developed for differential diagnosis between "clear" Aortic Stenosis (AS) and "clear" Mitral Regurgitation (MR) using heart sounds.

METHODS

For the purposes of our experiment we used a collection of 84 heart sound signals including 41 heart sound signals with "clear" AS systolic murmur and 43 with "clear" MR systolic murmur. Signals were initially preprocessed to detect 1st and 2nd heart sounds. Next a total of 100 features were determined for every heart sound signal and relevance to the differentiation between AS and MR was estimated. The performance of fully expanded decision tree classifiers and Pruned decision tree classifiers were studied based on various training and test datasets. Similarly, pruned decision tree classifiers were used to examine their differentiation capabilities. In order to build a generalized decision support system for heart sound diagnosis, we have divided the problem into sub problems, dealing with either one morphological characteristic of the heart-sound waveform or with difficult to distinguish cases.

RESULTS

Relevance analysis on the different heart sound features demonstrated that the most relevant features are the frequency features and the morphological features that describe S1, S2 and the systolic murmur. The results are compatible with the physical understanding of the problem since AS and MR systolic murmurs have different frequency contents and different waveform shapes. On the contrary, in the diastolic phase there is no murmur in both diseases which results in the fact that the diastolic phase signals cannot contribute to the differentiation between AS and MR. We used a fully expanded decision tree classifier with a training set of 34 records and a test set of 50 records which resulted in a classification accuracy (total corrects/total tested) of 90% (45 correct/50 total records). Furthermore, the method proved to correctly classify both AS and MR cases since the partial AS and MR accuracies were 91.6% and 88.5% respectively. Similar accuracy was achieved using decision trees with a fraction of the 100 features (the most relevant). Pruned Differentiation decision trees did not significantly change the classification accuracy of the decision trees both in terms of partial classification and overall classification as well.

DISCUSSION

Present work has indicated that decision tree algorithms decision tree algorithms can be successfully used as a basis for a decision support system to assist young and inexperienced clinicians to make better heart sound diagnosis. Furthermore, Relevance Analysis can be used to determine a small critical subset, from the initial set of features, which contains most of the information required for the differentiation. Decision tree structures, if properly trained can increase their classification accuracy in new test data sets. The classification accuracy and the generalization capabilities of the Fully Expanded decision tree structures and the Pruned decision tree structures have not significant difference for this examined sub-problem. However, the generalization capabilities of the decision tree based methods were found to be satisfactory. Decision tree structures were tested on various training and test data set and the classification accuracy was found to be consistently high.

Comparison of two educational interventions on pediatric resident auscultation skills

OBJECTIVE

Multiple cross-sectional physician surveys have documented poor cardiac auscultation skills. We evaluated the impact of 2 different educational interventions on pediatric resident auscultation skills.

METHODS

The auscultation skills of all first-year (PGY1; n = 20) and second-year pediatric residents (PGY2; n = 20) were evaluated at the beginning and end of the academic year. Five patient recordings were presented: atrial septal defect, ventricular septal defect, pulmonary valve stenosis, bicuspid aortic valve with insufficiency, and innocent murmur. Residents were asked to classify the second heart sound, identify a systolic ejection click, describe the murmur, and provide a diagnosis. All PGY1 and most PGY2 (14 of 20) participated on the inpatient cardiology service for 1 month. PGY2 on the cardiology service also attended outpatient clinic. PGY1 did not attend outpatient clinic but were allotted 2 hours/week to use a self-directed cardiac auscultation computer teaching program.

RESULTS

Resident auscultation skills on initial evaluation were dependent on training level (PGY1: 42 +/- 15% correct; PGY2: 53 +/- 13% correct), primarily as a result of better classification of second heart sound (PGY1: 45%; PGY2: 63%) and diagnosis of an innocent murmur (PGY1: 35%; PGY2: 65%). There was no difference in the ability to identify correctly a systolic ejection click (20% vs 23%) or to arrive at the correct diagnosis (35% vs 40%). At the end of the academic year, the PGY1 scores improved by 21%, primarily as a result of improved diagnostic accuracy of the innocent murmur (35% to 65%). PGY2 scores remained unchanged (53% vs 51%), regardless of participation in a cardiology rotation (cardiology rotation: 50%; no cardiology rotation: 51%). Combined, diagnostic accuracy was best for ventricular septal defect (55%) and innocent murmur (60%) and worst for atrial septal defect (18%) and pulmonary valve stenosis (15%). However, 40% identified the innocent murmur as pathologic and 21% of pathologic murmurs were diagnosed as innocent.

CONCLUSIONS

Pediatric resident auscultation skills were poor and did not improve after an outpatient cardiology rotation. Auscultation skills did improve after the use of a self-directed cardiac auscultation teaching program. These data have relevance given the American College of Graduate Medical Education's emphasis on measuring educational outcomes and documenting clinical competencies during residency training.

Approach to a child with a heart murmur

The vast majority of children with heart murmurs have an 'innocent' murmur. Differentiation of such murmurs from those due to structural cardiac disease, so called 'pathological' murmurs, is largely clinical. Pediatricians are capable of differentiating one from the other, provided a detailed evaluation is done. This article outlines the salient features of innocent murmurs that help us recognize them clinically.

Heart murmurs recorded by a sensor based electronic stethoscope and e-mailed for remote assessment

BACKGROUND

Heart murmurs are common in children, and they are often referred to a specialist for examination. A clinically innocent murmur does not need further investigation. The referral area of the University Hospital is large and sparsely populated. A new service for remote auscultation (telemedicine) of heart murmurs in children was established where heart sounds and short texts were sent as an attachment to e-mails.

AIM

To assess the clinical quality of this method.

METHODS

Heart sounds from 47 patients with no murmur (n = 7), with innocent murmurs (n = 20), or with pathological murmurs (n = 20) were recorded using a sensor based stethoscope and e-mailed to a remote computer. The sounds were repeated, giving 100 cases that were randomly distributed on a compact disc. Four cardiologists assessed and categorised the cases as having "no murmur", "innocent murmur", or "pathological murmur", recorded the assessment time per case, their degree of certainty, and whether they recommended referral.

RESULTS

On average, 2.1 minutes were spent on each case. The mean sensitivity and specificity were 89.7% and 98.2% respectively, and the inter-observer and intra-observer variabilities were low (kappa 0.81 and 0.87), respectively. A total of 93.4% of cases with a pathological murmur and 12.6% of cases with an innocent murmur were recommended for referral.

CONCLUSION

Telemedical referral of patients with heart murmurs for remote assessment by a cardiologist is safe and saves time. Skilled auscultation is adequate to detect patients with innocent murmurs.