Noninvasive acoustical detection of coronary artery disease: a comparative study of signal processing methods

An effective AI model for automatically detecting arteriovenous fistula stenosis

In this study, a novel artificial intelligence (AI) model is proposed to detect stenosis in arteriovenous fistulas (AVFs) using inexpensive and non-invasive audio recordings. The proposed model is a combination of two new input features based on short-time Fourier transform (STFT) and sample entropy, as well as two associated classification models (ResNet50 and ANN). The model's hyper-parameters were optimized through the use of the design of the experiment (DOE). The proposed AI model demonstrates high performance with all essential metrics, including sensitivity, specificity, accuracy, precision, and F1-score, exceeding 0.90 at detecting stenosis greater than 50%. These promising results suggest that our approach can lead to new insights and knowledge in this field. Moreover, the robust performance of our model, combined with the affordability of the audio recording device, makes it a valuable tool for detecting AVF stenosis in home-care settings.

Diagnosis of Coronary Artery Disease by Acoustic Analysis of Turbulent Murmur Caused by Coronary Artery Stenosis: A Single Center Study from China

Aim: Intracoronary murmur results from turbulent flow due to coronary artery narrowing. This study evaluated the diagnostic performance of a method for acoustic analysis of turbulent murmur caused by coronary artery stenosis in coronary artery disease (CAD) in Chinese populations.

Method: Patients admitted to the cardiovascular department of the Sixth Medical Center of the Chinese People’s Liberation Army General Hospital between September 2021 and June 2022 for elective coronary angiography were prospectively enrolled. A digital electronic stethoscope was used to record heart sounds before angiography. Quantitative coronary angiography (QCA) served as the “gold standard” for CAD diagnosis to evaluate the diagnostic performance of the acoustic analysis method for CAD.

Results: A total of 452 patients had complete QCA and heart sound data. The final interpretation results of the acoustic analysis method indicated 310 disease cases and 142 normal results. Increasing the cut-off values of coronary artery diameter stenosis from 30% to 50%, 70%, and 90% increased the sensitivity and NPV of the acoustic analysis method; the sensitivity was 75.6%, 81.9%, 83.3%, and 85.7%, respectively; the NPV was 33.1%, 57.0%, 69.7%, and 88.0%, respectively; the specificity and PPV decreased (specificity of 75.8%, 70.4%, 51.0%, and 37.5%, respectively; PPV of 95.2%, 89.0%, 69.4%, and 32.9%, respectively); and the AUC values were 0.757, 0.762, 0.672, and 0.616, respectively. The sensitivity of the acoustic analysis method for one-vessel disease was 86.6% when the cut-off value was 50%. The sensitivity for identifying left anterior descending coronary artery lesions was best, at 90.7%. The sensitivity for identifying isolated coronary artery branch lesions was 66.7%, whereas the sensitivity for identifying three-vessel disease in multi-vessel coronary artery lesions was better, at 82.9%.

Conclusion: Acoustic analysis of turbulent murmur caused by coronary artery stenosis for diagnosis of CAD may have favorable performance in the Chinese population. This method has good performance in CAD diagnosis with a cut-off coronary artery diameter for stenosis of 50%.

Custom-designed sensors embedded 3D-printed wearable device for improving the hemodialysis-related vascular dysfunction detection

BACKGROUND

The increasing prevalence of end-stage renal disease (ESRD) imposes a substantial economic burden on public health-care systems. Hemodialysis (HD) is a pivotal treatment modality for patients with ESRD. However, prolonged use of HD vessels may result in stenosis, thrombosis, and occlusion due to repeated daily punctures. Thus, early detection and prevention of the dysfunction of dialysis routes are crucial.

OBJECTIVE

In this study, we designed a wearable device for the early and accurate detection of arteriovenous access (AVA) stenosis in HD patients.

METHODS

A personalized three-dimensional (3D) printed wearable device was designed by combining the phonoangiography (PAG) and photoplethysmography (PPG) techniques. The capability of this device to monitor AVA dysfunction before and after percutaneous transluminal angioplasty (PTA) was evaluated.

RESULTS

After PTA, the amplitudes of both PAG and PPG signals increased in patients with arteriovenous fistulas and those with arteriovenous grafts; this might be due to increased blood flow.

CONCLUSION

Our designed multi-sensor wearable medical device using PAG, PPG, and 3D printing appears suitable for early and accurate detection of AVA stenosis in HD patients.

Coronary Artery Disease Detected by Low Frequency Heart Sounds

OBJECTIVES

Previous studies have observed an increase in low frequency diastolic heart sounds in patients with coronary artery disease (CAD). The aim was to develop and validate a diagnostic, computerized acoustic CAD-score based on heart sounds for the non-invasive detection of CAD.

METHODS

Prospective study enrolling 463 patients referred for elective coronary angiography. Pre-procedure non-invasive recordings of heart sounds were obtained using a novel acoustic sensor. A CAD-score was defined as the power ratio between the 10-90 Hz frequency spectrum and the 90-300 Hz frequency spectrum of the mid-diastolic heart sound. Quantitative coronary angiography analysis was performed by a blinded core laboratory and patients grouped according to the results: obstructive CAD defined by the presence of at least one ≥ 50% stenosis, non-obstructive CAD as patients with a maximal stenosis in the 25-50% interval and non-CAD as no coronary lesions exceeding 25%. We excluded patients with potential confounders or incomplete data (n = 245). To avoid over-fitting the final cohort of 218 patients was randomly divided into to a training group for development (n = 127) and a validation group (n = 91).

RESULTS

In both the training and the validation group the CAD-score was significantly increased in CAD patients compared to non-CAD patients (p < 0.0001). In the validation group the area under the receiver-operating curve was 77% (95% CI 63-91%). Sensitivity was 71% (95% CI 59-82%) and specificity 64% (95% CI 45-83%).

CONCLUSION

The acoustic CAD-score is a new, inexpensive, non-invasive method to detect CAD, which may supplement clinical risk stratification and reduce the need for subsequent non-invasive and invasive testing.

Improved pre-test likelihood estimation of coronary artery disease using phonocardiography

Aims

Current early risk stratification of coronary artery disease (CAD) consists of pre-test probability scoring such as the 2019 ESC guidelines on chronic coronary syndromes (ESC2019), which has low specificity and thus rule-out capacity. A newer clinical risk factor model (risk factor-weighted clinical likelihood, RF-CL) showed significantly improved rule-out capacity over the ESC2019 model. The aim of the current study was to investigate if the addition of acoustic features to the RF-CL model could improve the rule-out potential of the best performing clinical risk factor models.

Methods and results

Four studies with heart sound recordings from 2222 patients were pooled and distributed into two data sets: training and test. From a feature bank of 40 acoustic features, a forward-selection technique was used to select three features that were added to the RF-CL model. Using a cutoff of 5% predicted risk of CAD, the developed acoustic-weighted clinical likelihood (A-CL) model showed significantly (P < 0.05) higher specificity of 48.6% than the RF-CL model (specificity of 41.5%) and ESC 2019 model (specificity of 6.9%) while having the same sensitivity of 84.9% as the RF-CL model. Area under the curve of the receiver operating characteristic for the three models was 72.5% for ESC2019, 76.7% for RF-CL, and 79.5% for A-CL.

Conclusion

The proposed A-CL model offers significantly improved rule-out capacity over the ESC2019 model and showed better overall performance than the RF-CL model. The addition of acoustic features to the RF-CL model was shown to significantly improve early risk stratification of symptomatic patients suspected of having stable CAD.

Ensembled Transfer Learning and Multiple Kernel Learning for Phonocardiogram based Atherosclerotic Coronary Artery Disease Detection

Conventional machine learning has paved the way for a simple, affordable, non-invasive approach for Coronary artery disease (CAD) detection using phonocardiogram (PCG). It leaves a scope to explore improvement of performance metrics by fusion of learned representations from deep learning. In this study, we propose a novel, multiple kernel learning (MKL) for their fusion using deep embeddings transferred from pre-trained convolutional neural network (CNN). The proposed MKL, finds optimal kernel combination by maximizing the similarity with ideal kernel and minimizing the redundancy with other basis kernels. Experiments are performed on 960 PCG epochs collected from 40 CAD and 40 normal subjects. The transferred embeddings attain maximum subject-level accuracy of 89.25% with kappa of 0.7850. Later, their fusion with handcrafted features using the proposed MKL gives an accuracy of 91.19% and kappa 0.8238. The study shows the potential of development of high accuracy CAD detection system by using easy to acquire, non-invasive PCG signal.

Spectral analysis of heart sounds associated with coronary artery disease

Objective. The aim of this study was to find spectral differences of diagnostic interest in heart sound recordings of patients with coronary artery disease (CAD) and healthy subjects.Approach. Heart sound recordings from three studies were pooled, and patients with clear diagnostic outcomes (positive: CAD and negative: Non-CAD) were selected for further analysis. Recordings from 1146 patients (191 CAD and 955 Non-CAD) were analyzed for spectral differences between the two groups using Welch's spectral density estimate. Frequency spectra were estimated for systole and diastole segments, and time-frequency spectra were estimated for first (S1) and second (S2) heart sound segments. An ANCOVA model with terms for diagnosis, age, gender, and body mass index was used to evaluate statistical significance of the diagnosis term for each time-frequency component.Main results. Diastole and systole segments of CAD patients showed increased energy at frequencies 20-120 Hz; furthermore, this difference was statistically significant for the diastole. CAD patients showed decreased energy for the mid-S1 and mid-S2 segments and conversely increased energy before and after the valve sounds. Both S1 and S2 segments showed regions of statistically significant difference in the time-frequency spectra.Significance. Results from analysis of the diastole support findings of increased low-frequency energy from previous studies. Time-frequency components of S1 and S2 sounds showed that these two segments likely contain heretofore untapped information for risk assessment of CAD using phonocardiography; this should be considered in future works. Further development of features that build on these findings could lead to improved acoustic detection of CAD.

Detection of Coronary Artery Disease Using Multi-Domain Feature Fusion of Multi-Channel Heart Sound Signals

Heart sound signals reflect valuable information about heart condition. Previous studies have suggested that the information contained in single-channel heart sound signals can be used to detect coronary artery disease (CAD). But accuracy based on single-channel heart sound signal is not satisfactory. This paper proposed a method based on multi-domain feature fusion of multi-channel heart sound signals, in which entropy features and cross entropy features are also included. A total of 36 subjects enrolled in the data collection, including 21 CAD patients and 15 non-CAD subjects. For each subject, five-channel heart sound signals were recorded synchronously for 5 min. After data segmentation and quality evaluation, 553 samples were left in the CAD group and 438 samples in the non-CAD group. The time-domain, frequency-domain, entropy, and cross entropy features were extracted. After feature selection, the optimal feature set was fed into the support vector machine for classification. The results showed that from single-channel to multi-channel, the classification accuracy has increased from 78.75% to 86.70%. After adding entropy features and cross entropy features, the classification accuracy continued to increase to 90.92%. The study indicated that the method based on multi-domain feature fusion of multi-channel heart sound signals could provide more information for CAD detection, and entropy features and cross entropy features played an important role in it.

Flexible, Skin Coupled Microphone Array for Point of Care Vascular Access Monitoring

Point-of-care screening for hemodialysis vascular access dysfunction requires tools that are objective and efficient. Listening for bruits during physical exam is a subjective examination which can detect stenosis (vascular narrowing) when properly performed. Phonoangiograms (PAGs)-mathematical analysis of bruits-increases the objectivity and sensitivity and permits quantification of stenosis location and degree of stenosis (DOS). This work describes a flexible and body-conformal multi-channel sensor and associated signal processing methods for automated DOS characterization of vascular access. The sensor used an array of thin-film PVDF microphones integrated on polyimide to record bruits at multiple sites along a vascular access. Nonlinear signal processing was used to extract spectral features, and cardiac cycle segmentation was used to improve sensitivity. PAG signal processing algorithms to detect stenosis location and severity are also presented. Experimental results using microphone arrays on a vascular access phantom demonstrated that stenotic lesions were detected within 1 cm of the actual location and graded to three levels (mild, moderate, or severe). Additional PAG features were also used to define a simple binary classifier aimed at patients with failing vascular accesses. The classifier achieved 90% accuracy, 92% specificity, and 91% sensitivity at detecting stenosis greater than 50%. These results suggest that point-of-care screening using microphone arrays can identify at-risk patients using automated signal analysis.

Experimental and numerical investigation on soft tissue dynamic response due to turbulence-induced arterial vibration

Peripheral arterial occlusive disease is a serious cardiovascular disorder. The arterial occlusion leads to turbulent flow and arterial sound generation on the inner vessel wall. Stenosis-induced vibro-acoustic waves propagate through the surrounding soft tissues and reach the skin surface. In this study, the feasibility of noninvasive acoustic detection of the peripheral arterial stenosis is investigated using the vibration responses by means of experimental and computational models. Latex rubber tube is used to model the artery, and it is surrounded by a tissue mimicking phantom made of bovine gelatin. Vibration responses on phantom surface are measured using laser Doppler vibrometer, and computational results are obtained performing modal analysis. Experimental findings and computational results showed well agreement in terms of spectral content and vibration amplitudes. The effects of various stenosis severities, flow rates, and phantom thicknesses on the vibration responses are investigated from diagnostic perspective. Stenosis severities greater than 70% resulted in a considerable increase in vibration amplitudes. The structural mode shapes of the tissue phantom are dominant between 0 and 100 Hz, suppressing the signals generated by the stenosis. The optimum range of frequency for acoustic stenosis detection is concluded to be between 200 and 500 Hz, particularly around 300 Hz. Graphical abstract .

FEASIBILITY OF SMART HEMODIALYSIS PATIENT CARE USING SENSORS EMBEDDED IN PERSONALIZED 3D PRINTING CAST

The ever-increasing incidence of end-stage renal disease (ESRD) has already become a major burden to health budgets and a threat to public health nationwide in Taiwan. According to the United States Renal Data System Annual Data Report in 2015, the prevalence and incidence of ESRD in Taiwan are the highest in the world. Moreover, for the population of 82 thousand ESRD patients receiving hemodialysis treatments, the total cost is up to NT$34.2 billion annually out of the National Health Insurance (NHI) program budget. This project is to design a wearable medical device which can measure and monitor the fluid dynamics of the dialysis access using sensor of phonoangiography (PAG) for exploring vascular pitch pattern and sensor of Photoplethysmography (PPG) for estimating the flow volume as a double checking of the AV access condition. We use arteriovenous access (AVA) stenosis detector based on phonoangiography technique and autoregressive model to detect access stenosis and simultaneously estimate the status of AVA life cycle by tracking and obtaining changes in frequency spectra domain. It helps hemodialysis patients to be aware earlier of the dysfunction of AVA and reminds them to make a return visit. The purpose of the complement deployment of vital sign sensors is to improve the prognosis and optimize overall health by providing analysis of physiological signals, including water content index, pulse oximetry, and blood pressure at the same time. With these sensors, the concept of holistic hemodialysis patient care (HHPC) might be proved.

Stenosis Characterization and Identification for Dialysis Vascular Access

Vascular access dysfunction is the leading cause of hospitalization for hemodialysis patients and accounts for the most medical costs in this patient population. Vascular access flow is commonly hindered by blood vessel narrowing (stenosis). Current screening methods involving imaging to detect stenosis are too costly for routine use at the point of care. Noninvasive, real-time screening of patients at risk of vascular access dysfunction could potentially identify high-risk patients and reduce the likelihood of emergency surgical interventions. Bruits (sounds produced by turbulent blood flow near stenoses) can be interpreted by skilled clinical staff using conventional stethoscopes. To improve the sensitivity of detection, digital analysis of blood flow sounds (phonoangiograms or PAGs) is a promising approach for classifying vascular access stenosis using non-invasive auditory recordings. Here, we demonstrate auditory and spectral features of PAGs which estimate both the location and degree of stenosis (DOS). Auditory recordings from nine stenosis phantoms with variable DOS and hemodynamic flow rate were obtained using a digital recording stethoscope and analyzed to extract classification features. Autoregressive modeling and discrete wavelet transforms were used for multiresolution signal decomposition to produce 14 distinct features, most of which were linearly correlated with DOS. Our initial results suggest that the widely-used auditory spectral centroid is a simple way to calculate features which can estimate both the location and severity of vascular access stenosis.

Bruit-enhancing phonoangiogram filter using sub-band autoregressive linear predictive coding

Subjective analysis of bruits has long been an element of vascular access physical exams. Digital recordings of blood flow bruits-phonoangiograms (PAGs)-may provide an objective, non-imaging measure of vascular access stenosis. We have analyzed the long-term stability in PAGs from typical dialysis patients with arteriovenous fistulas and grafts and found that typical patients have correlated PAG spectra. PAGs can be analyzed using nonlinear, sub-band frequency-domain linear prediction to produce both bruit-enhanced recordings and a bruit-enhanced power envelope. This approach is novel over prior methods because it adaptively predicts signal envelopes based on physiologic properties of blood flow determined from chronic dialysis recipients. Our results indicate that a generalized bruit-enhancing filter can be developed for dialysis vascular access. Outputs from this filter may be analyzed to determine vascular physiology, including re-stenosis risk.

The clinical evaluation of the CADence device in the acoustic detection of coronary artery disease

The noninvasive detection of turbulent coronary flow may enable diagnosis of significant coronary artery disease (CAD) using novel sensor and analytic technology. Eligible patients (n = 1013) with chest pain and CAD risk factors undergoing nuclear stress testing were studied using the CADence (AUM Cardiovascular Inc., Northfield MN) acoustic detection (AD) system. The trial was designed to demonstrate non-inferiority of AD for diagnostic accuracy in detecting significant CAD as compared to an objective performance criteria (sensitivity 83% and specificity 80%, with 15% non-inferiority margins) for nuclear stress testing. AD analysis was blinded to clinical, core lab-adjudicated angiographic, and nuclear data. The presence of significant CAD was determined by computed tomographic (CCTA) or invasive angiography. A total of 1013 subjects without prior coronary revascularization or Q-wave myocardial infarction were enrolled. Primary analysis was performed on subjects with complete angiographic and AD data (n = 763) including 111 subjects (15%) with severe CAD based on CCTA (n = 34) and invasive angiography (n = 77). The sensitivity and specificity of AD were 78% (p = 0.012 for non-inferiority) and 35% (p < 0.001 for failure to demonstrate non-inferiority), respectively. AD results had a high 91% negative predictive value for the presence of significant CAD. AD testing failed to demonstrate non-inferior diagnostic accuracy as compared to the historical performance of a nuclear stress OPC due to low specificity. AD sensitivity was non-inferior in detecting significant CAD with a high negative predictive value supporting a potential value in excluding CAD.

A new approach to early diagnosis of congestive heart failure disease by using Hilbert-Huang transform

Congestive heart failure (CHF) is a degree of cardiac disease occurring as a result of the heart's inability to pump enough blood for the human body. In recent studies, coronary artery disease (CAD) is accepted as the most important cause of CHF. This study focuses on the diagnosis of both the CHF and the CAD. The Hilbert-Huang transform (HHT), which is effective on non-linear and non-stationary signals, is used to extract the features from R-R intervals obtained from the raw electrocardiogram data. The statistical features are extracted from instinct mode functions that are obtained applying the HHT to R-R intervals. Classification performance is examined with extracted statistical features using a multilayer perceptron neural network. The designed model classified the CHF, the CAD patients and a normal control group with rates of 97.83%, 93.79% and 100%, accuracy, specificity and sensitivity, respectively. Also, early diagnosis of the CHF was performed by interpretation of the CAD with a classification accuracy rate of 97.53%, specificity of 98.18% and sensitivity of 97.13%. As a result, a single system having the ability of both diagnosis and early diagnosis of CHF is performed by integrating the CAD diagnosis method to the CHF diagnosis method.

Health-Enabling and Ambient Assistive Technologies: Past, Present, Future

BACKGROUND

During the last decades, health-enabling and ambient assistive technologies became of considerable relevance for new informatics-based forms of diagnosis, prevention, and therapy.

OBJECTIVES

To describe the state of the art of health-enabling and ambient assistive technologies in 1992 and today, and its evolution over the last 25 years as well as to project where the field is expected to be in the next 25 years. In the context of this review, we define health-enabling and ambient assistive technologies as ambiently used sensor-based information and communication technologies, aiming at contributing to a person's health and health care as well as to her or his quality of life.

METHODS

Systematic review of all original articles with research focus in all volumes of the IMIA Yearbook of Medical Informatics. Surveying authors independently on key projects and visions as well as on their lessons learned in the context of health-enabling and ambient assistive technologies and summarizing their answers. Surveying authors independently on their expectations for the future and summarizing their answers.

RESULTS

IMIA Yearbook papers containing statements on health-enabling and ambient assistive technologies appear first in 2002. These papers form a minor part of published research articles in medical informatics. However, during recent years the number of articles published has increased significantly. Key projects were identified. There was a clear progress on the use of technologies. However proof of diagnostic relevance and therapeutic efficacy remains still limited. Reforming health care processes and focussing more on patient needs are required.

CONCLUSIONS

Health-enabling and ambient assistive technologies remain an important field for future health care and for interdisciplinary research. More and more publications assume that a person's home and their interaction therein, are becoming important components in health care provision, assessment, and management.

Audible Coronary Artery Stenosis

OBJECTIVE

Hemodynamically significant coronary artery stenoses generate turbulent blood flow patterns that manifest as intracoronary murmurs. This study aims to evaluate the performance of modern acoustic detection of these murmurs by acoustic signals captured from patients undergoing gold standard comparative coronary angiography.

METHODS

We prospectively studied 156 patients undergoing elective coronary angiography, excluding those with acute coronary syndrome, prior chest surgery, or significant valvular disease. Acoustic signals were captured before arterial access. Angiographic degree of stenosis in each coronary artery was graded blinded to clinical and acoustic data. Acoustic data were analyzed blinded to clinical and angiographic data, categorizing subjects as "normal," "diseased," or "inconclusive." Of 156 patients examined, 123 generated analyzable data.

RESULTS

Angiographically significant stenosis (≥50%) prevalence was 52% (18%, 23%, 11% with 1-, 2-, 3-vessel disease, respectively). Acoustic detection sensitivity and specificity for stenosis ≥50% in any vessel were 0.70 and 0.80, respectively (negative predictive value, 0.71; positive predictive value, 0.79). Acoustic detection optimally identified stenosis ≥50% with an area under the curve of 0.75. For stenosis ≥50% in major vessels only (left main, proximal-mid left anterior descending, proximal-mid circumflex, proximal-mid right coronary), prevalence was 46%; sensitivity and specificity were 0.72 and 0.76, respectively (negative predictive value, 0.76; positive predictive value, 0.72; area under the curve, 0.76).

CONCLUSIONS

Acoustic signal patterns and modern analysis techniques may be used to identify intracoronary murmurs generated by hemodynamically significant coronary artery stenoses in all major vessels. Further investigation is warranted to compare the clinical performance of this modality with current noninvasive approaches that evaluate patients at risk for atherosclerotic and obstructive coronary artery disease.

Improved Heart Sound Detection and Signal-to-Noise Estimation Using a Low-Mass Sensor

GOAL

The purpose of this paper is to improve the detection of high-frequency sounds from the heart for better identification of turbulent blood flow in partially occluded coronary arteries. This paper also describes a method for the quantitative assessment of data quality.

METHODS

A very light-weight dual accelerometer has been developed that places a small mechanical load on the chest. When used in conjunction with a novel correlation-based analysis, this dual-signal transducer provides an estimate to the signal-to-noise ratio (SNR) of the acoustic signal.

RESULTS

The new transducer has significantly better SNR properties than the traditional cardiac microphones. This improvement is due to increased sensitivity to high-frequency signals not a reduction in noise and is likely the result of reduced mechanical loading on the chest.

CONCLUSION

Substantial improvement in the detection of high-frequency heart sounds is possible as is quantitative assessment of data quality.

SIGNIFICANCE

The new transducer and analysis will lead to substantial improvements in the acoustic detection of partially occluded arteries associated with coronary artery disease. It is finally possible to obtain a measurement of the quality of heart sound signals as they are being recorded.

Acoustic Features for the Identification of Coronary Artery Disease

GOAL

Earlier studies have documented that coronary artery disease (CAD) produces weak murmurs, which might be detected through analysis of heart sounds. An electronic stethoscope with a digital signal processing unit could be a low cost and easily applied method for diagnosis of CAD. The current study is a search for heart sound features which might identify CAD.

METHODS

Nine different types of features from five overlapping frequency bands were obtained and analyzed using 435 recordings from 133 subjects.

RESULTS

New features describing an increase in low-frequency power in CAD patients were identified. The features of the different types were relatively strongly correlated. Using a quadratic discriminant function, multiple features were combined into a CAD-score. The area under the receiving operating characteristic for the CAD score was 0.73 (95% CI: 0.69-0.78).

CONCLUSION

The result confirms that there is a potential in heart sounds for the diagnosis of CAD, but that further improvements are necessary to gain clinical relevance.

A rule-based decision-making diagnosis system to evaluate arteriovenous shunt stenosis for hemodialysis treatment of patients using fuzzy petri nets

This paper proposes a rule-based decision-making diagnosis system to evaluate arteriovenous shunt (AVS) stenosis for long-term hemodialysis treatment of patients using fuzzy petri nets (FPNs). AVS stenoses are often associated with blood sounds, resulting from turbulent flow over the narrowed blood vessel. Phonoangiography provides a noninvasive technique to monitor the sounds of the AVS. Since the power spectra changes in frequency and amplitude with the degree of AVS stenosis, it is difficult to make a human-made decision to judge the degree using a combination of those variances. The Burg autoregressive (AR) method is used to estimate the frequency spectra of a phonoangiographic signal and identify the characteristic frequencies. A rule-based decision-making method, FPNs, is designed as a decision-making system to evaluate the degree of stenosis (DOS) in routine examinations. For 42 long-term follow-up patients, the examination results show the proposed diagnosis system has greater efficiency in evaluating AVS stenosis.

Multiple-site hemodynamic analysis of Doppler ultrasound with an adaptive color relation classifier for arteriovenous access occlusion evaluation

This study proposes multiple-site hemodynamic analysis of Doppler ultrasound with an adaptive color relation classifier for arteriovenous access occlusion evaluation in routine examinations. The hemodynamic analysis is used to express the properties of blood flow through a vital access or a tube, using dimensionless numbers. An acoustic measurement is carried out to detect the peak-systolic and peak-diastolic velocities of blood flow from the arterial anastomosis sites (A) to the venous anastomosis sites (V). The ratio of the supracritical Reynolds (Re(supra)) number and the resistive (Res) index quantitates the degrees of stenosis (DOS) at multiple measurement sites. Then, an adaptive color relation classifier is designed as a nonlinear estimate model to survey the occlusion level in monthly examinations. For 30 long-term follow-up patients, the experimental results show the proposed screening model efficiently evaluates access occlusion.

Automatic heart sounds detection and systolic murmur characterization using wavelet transform and AR modeling

This paper describes a signal processing procedure that identifies the first and the second heart sounds (S1 and S2), extracts the systole from the diastole, detects and characterizes the systolic murmur found within. The identification of heart sounds was facilitated by discrete wavelet transform (DWT) approximation using the Coiflet wavelet and followed by using indicators that quantify signal activity and strength. The systole was isolated and divided into smaller short segments where the signal activity measure and absolute amplitude were computed. S1 and S2, and the onset and duration of a systolic murmur were marked. Using the indices derived from AR modeling, a systolic murmur can be characterized by its timing, duration, pitch, and shape either as crescendo, decrescendo, crescendo-decrescendo, or plateau. The performance of the proposed procedure was evaluated and proved with clinically recorded systolic murmur episodes.

Development of cardiac prescreening device for rural population using ultralow-power embedded system

The invention is inspired by the desire to understand the opportunities and expectations of developing economies in terms of healthcare. The designed system is a point-of-care (POC) device that can deliver heart-care services to the rural population and bridge the rural-urban divide in healthcare delivery. The product design incorporates several innovations including the effective use of adaptive and multiresolution signal-processing techniques for acquisition, denoising, segmentation, and characterization of the heart sounds (HS) and murmurs using an ultralow-power embedded Mixed Signal Processor. The device is able to provide indicative diagnosis of cardiac conditions and classify a subject into either normal, abnormal, ischemic, or valvular abnormalities category. Preliminary results demonstrated by the prototype confirm the applicability of the device as a prescreening tool that can be used by paramedics in rural outreach programs. Feedback from medical professionals also shows that such a device is helpful in early detection of common congenital heart diseases. This letter aims to determine a framework for utilization of automated HS analysis system for community healthcare and healthcare inclusion.

Time-frequency analysis of phonocardiogram signals using wavelet transform: a comparative study

Analysis of phonocardiogram (PCG) signals provides a non-invasive means to determine the abnormalities caused by cardiovascular system pathology. In general, time-frequency representation (TFR) methods are used to study the PCG signal because it is one of the non-stationary bio-signals. The continuous wavelet transform (CWT) is especially suitable for the analysis of non-stationary signals and to obtain the TFR, due to its high resolution, both in time and in frequency and has recently become a favourite tool. It decomposes a signal in terms of elementary contributions called wavelets, which are shifted and dilated copies of a fixed mother wavelet function, and yields a joint TFR. Although the basic characteristics of the wavelets are similar, each type of the wavelets produces a different TFR. In this study, eight real types of the most known wavelets are examined on typical PCG signals indicating heart abnormalities in order to determine the best wavelet to obtain a reliable TFR. For this purpose, the wavelet energy and frequency spectrum estimations based on the CWT and the spectra of the chosen wavelets were compared with the energy distribution and the autoregressive frequency spectra in order to determine the most suitable wavelet. The results show that Morlet wavelet is the most reliable wavelet for the time-frequency analysis of PCG signals.

Patient specific cardiovascular risk assessment and treatment decision support based on multiscale modelling and medical guidelines

In this work we present an enhanced medical workflow and a decision support system for atherosclerotic risk assessment and treatment, that is based both on existing medical guidelines and on patient specific multiscale data. The medical expert that uses the system is able to apply both existing medical guidelines as well as to take into account additional information for the patient by inspecting the 3D geometry of an arterial segment or the arterial tree, model the blood flow in the patient specific arterial model and predict the progression of the plaque. Moreover, the user is able to apply plaque characterization techniques in Intravascular Ultrasound images (IVUS) and Tomography Images (CT). The combination of the medical guidelines with the patient specific multiscale data provides a detailed view in the patient status for risk assessment and treatment suggestion.

Computer-aided auscultation to diagnose Renal Artery Stenosis

Renal Artery Stenosis (RAS) is the most common cause of secondary hypertension, and early diagnosis is important since correct and timely treatment may cure hypertension and prevent loss of renal function. This study investigates a new approach to diagnosing renal artery stenosis by computer analysis of the phonogram recorded with an electronic stethoscope. Phonograms recorded from five positions over the renal arteries were obtained, three from patients with confirmed RAS and 15 from healthy subjects. Two features describing the power ratios between the systolic and diastolic periods in two different frequency bands were extracted. It was possible to discriminate all three RAS subjects from the healthy subjects in the frequency band 0.4-1.1 kHz. However, the number of subjects is insufficient to draw statistically significant conclusions about the performance of the system.

Characterisation of arteriovenous fistula's sound recordings using principal component analysis

In this study, a signal analysis framework based on the Karhunen-Loève expansion and k-means clustering algorithm is proposed for the characterisation of arteriovenous (AV) fistula's sound recordings. The Karhunen-Loève (KL) coefficients corresponding to the directions of maximum variance were used as classification features, which were clustered applying k-means algorithm. The results showed that one natural cluster was found for similar AV fistula's state recordings. On the other hand, when stenotic and non-stenotic AV fistula's recordings were processed together, the two most significant KL coefficients contain important information that can be used for classification or discrimination between these AV fistula's states.

Arteriovenous fistula stenosis detection using wavelets and support vector machines

The objective of this exploratory study was to develop signal processing methods for assisting in the diagnosis of arteriovenous fistula stenosis on patients suffering from endstage renal disease and undergoing haemodialysis treatments. The proposed method is based on the classification of vessels sounds utilizing parameter extraction from wavelets transform coefficients. The coefficients energy of selected scales (frequency bands) were fed to a support vector machine based system for classification. Results suggested that this technique can be useful for diagnosis purposes to physicians during the auscultation procedure.

Quantitative analysis of heart sounds and systolic heart murmurs using wavelet transform and AR modeling

A quantitative approach integrating AR modeling and wavelet transform is presented in this paper to analyze the digitized phonocardiogram. The recognition of the first and the second heart sounds (S(1) and S(2)) were facilitated with wavelet transform without referring to the QRS waveform. We found that the Daubechies wavelet is most effective in identifying S(1) and S(2). In addition, the boundaries of S(1), S(2), and the onset and duration of the systolic murmur thus identified within the systole could be marked using the wavelet-filtered signal's strength. Furthermore, quantitative measures derived from a 2(nd) order AR model were used to delineate the configuration and pitch of the systolic murmur found within through piecewise segmentation. The proposed approach was tested and proved effective in delineating a set of clinically diagnosed systolic murmurs. The suggested AR and wavelet transform combined approach can be generalized with minor adjustments to delineate diastolic murmurs as well.

Ultrasonic Doppler Vibrometry: Novel Method for Detection of Left Ventricular Wall Vibrations Caused by Poststenotic Coronary Flow

BACKGROUND

A diastolic coronary flow murmur has been reported for patients with coronary stenoses, yet is rarely appreciated during routine auscultation. We hypothesized that an ultrasonic Doppler method can detect the epicardial vibrations associated with this murmur. Ultrasonic Doppler vibrometry is a pulsed wave echocardiography phase demodulation technique designed for detecting vibrations. We correlated the vibration characteristics measured using vibrometry with the angiographic severity of coronary artery stenosis.

METHODS

In a prospective pilot study, 49 patients were recruited for an ultrasound examination before coronary arteriography. An ultrasound instrument was customized to acquire the raw pulsed wave Doppler echocardiographic data from a range gate placed on the left ventricular myocardium near the path of the epicardial coronary arteries.

RESULTS

Patients with angiographically minor stenosis (tightest stenosis < 50% by quantitative coronary angiography, N = 25) had lower diastolic vibration energy (computed as the median spectral energy of myocardial wall velocity in the 100 approximately 1000-Hz frequency band normalized by a baseline diastolic value) compared with patients with moderate or severe stenosis (any stenosis > 50%, N = 24) (P < .001, area under the receiver operating characteristics curve = 0.84). The vibration energy increased with increasing stenosis severity for less severe narrowing (<70%) but decreased for severe narrowing (>70%) (R(2) = 0.21, P < .0002).

CONCLUSIONS

Preliminary evidence indicates that diastolic left ventricular wall vibrations measured using ultrasonic Doppler vibrometry are related to the severity of coronary artery stenoses. With further refinement and validation, this noninvasive and low-cost method could lead to an early screening and monitoring test for coronary artery stenosis.

Acoustic detection of coronary artery disease

Coronary artery disease (CAD) occurs when the arteries to the heart (the coronary arteries) become blocked by deposition of plaque, depriving the heart of oxygen-bearing blood. This disease is arguably the most important fatal disease in industrialized countries, causing one-third to one-half of all deaths in persons between the ages of 35 and 64 in the United States. Despite the fact that early detection of CAD allows for successful and cost-effective treatment of the disease, only 20% of CAD cases are diagnosed prior to a heart attack. The development of a definitive, noninvasive test for detection of coronary blockages is one of the holy grails of diagnostic cardiology. One promising approach to detecting coronary blockages noninvasively is based on identifying acoustic signatures generated by turbulent blood flow through partially occluded coronary arteries. In fact, no other approach to the detection of CAD promises to be as inexpensive, simple to perform, and risk free as the acoustic-based approach. Although sounds associated with partially blocked arteries are easy to identify in more superficial vessels such as the carotids, sounds from coronary arteries are very faint and surrounded by noise such as the very loud valve sounds. To detect these very weak signals requires sophisticated signal processing techniques. This review describes the work that has been done in this area since the 1980s and discusses future directions that may fulfill the promise of the acoustic approach to detecting coronary artery disease.

Ultrasonic imaging of myocardial vibrations associated with coronary artery disease

Coronary artery disease (CAD) is a major cause of mortality in the western world. Although progress has been made in recent years for the noninvasive diagnosis of CAD, a widely available, inexpensive and effective diagnostic solution remains elusive. We have developed a novel ultrasound-based technology to detect and analyze the myocardial vibrations associated with diastolic murmurs produced by CAD. Conventional ultrasound imaging systems suppress these vibrations. We have developed algorithms to process the raw ultrasound data and isolate these vibrations and integrated them into a programmable ultrasound system for real-time vibration imaging. In preliminary results from clinical studies of patients with CAD, we have observed localized areas of vibrations in the neighborhood of the stenosed coronary artery. The vibrations are narrowband with frequency >200 Hz, and appear to have harmonic components, thus indicating reasonance phenomena potentially with nonlinear mechanisms involved. No such vibrations were observed in normal subjects. Analysis of myocardial vibrations could provide a noninvasive diagnostic test for CAD that overcomes many of the limitations of conventional noninvasive tests. Potentially, this technology could provide a new way of evaluating CAD and cardiac function.

Ultrasonic Doppler vibrometry: measurement of left ventricular wall vibrations associated with coronary artery disease

We have developed a new method of detecting coronary artery stenoses that uses Doppler ultrasound to measure minute local vibrations in the cardiac wall associated with post-stenotic flow turbulence. In this paper, we present the results of a preliminary clinical study to evaluate the efficacy of this method for detecting coronary artery disease (CAD) using coronary angiography as the gold standard. The study population consisted of 34 patients clinically-indicated for coronary angiography. Based on the catheterization reports, the patients were divided into three categories: severe (obstructive CAD, typically with >70% diameter reduction), moderate (non-obstructive CAD, typically with <50% diameter reduction or diffuse atherosclerosis), and normal (no angiographic evidence of CAD). A diastolic myocardial vibration index (DMVI) was calculated as the ratio of the normalized periodogram spectral energy in the 100~800-Hz frequency band of the instantaneous wall velocity in early diastole to a baseline value during diastasis. The DMVI was significantly higher in severe CAD patients (21.2 +/- 3.2 dB) compared to moderate CAD (17.5 +/- 3.5 dB) and normal (11.2 +/- 4.8 dB). The differences between each of the categories were statistically significant (p<0.05). Severe CAD patients could be distinguished from normal with a sensitivity of 91.7% and specificity of 83.3%. We believe that this method could potentially be developed into a low-cost and accurate test for diagnosis and screening for coronary artery stenosis.

Ultrasonic technique for imaging tissue vibrations: preliminary results

We propose an ultrasound (US)-based technique for imaging vibrations in the blood vessel walls and surrounding tissue caused by eddies produced during flow through narrowed or punctured arteries. Our approach is to utilize the clutter signal, normally suppressed in conventional color flow imaging, to detect and characterize local tissue vibrations. We demonstrate the feasibility of visualizing the origin and extent of vibrations relative to the underlying anatomy and blood flow in real-time and their quantitative assessment, including measurements of the amplitude, frequency and spatial distribution. We present two signal-processing algorithms, one based on phase decomposition and the other based on spectral estimation using eigen decomposition for isolating vibrations from clutter, blood flow and noise using an ensemble of US echoes. In simulation studies, the computationally efficient phase-decomposition method achieved 96% sensitivity and 98% specificity for vibration detection and was robust to broadband vibrations. Somewhat higher sensitivity (98%) and specificity (99%) could be achieved using the more computationally intensive eigen decomposition-based algorithm. Vibration amplitudes as low as 1 mum were measured accurately in phantom experiments. Real-time tissue vibration imaging at typical color-flow frame rates was implemented on a software-programmable US system. Vibrations were studied in vivo in a stenosed femoral bypass vein graft in a human subject and in a punctured femoral artery and incised spleen in an animal model.