Identification of Congenital Valvular Murmurs in Young Patients Using Deep Learning-Based Attention Transformers and Phonocardiograms

One in every four newborns suffers from congenital heart disease (CHD) that causes defects in the heart structure. The current gold-standard assessment technique, echocardiography, causes delays in the diagnosis owing to the need for experts who vary markedly in their ability to detect and interpret pathological patterns. Moreover, echo is still causing cost difficulties for low- and middle-income countries. Here, we developed a deep learning-based attention transformer model to automate the detection of heart murmurs caused by CHD at an early stage of life using cost-effective and widely available phonocardiography (PCG). PCG recordings were obtained from 942 young patients at four major auscultation locations, including the aortic valve (AV), mitral valve (MV), pulmonary valve (PV), and tricuspid valve (TV), and they were annotated by experts as absent, present, or unknown murmurs. A transformation to wavelet features was performed to reduce the dimensionality before the deep learning stage for inferring the medical condition. The performance was validated through 10-fold cross-validation and yielded an average accuracy and sensitivity of 90.23 % and 72.41 %, respectively. The accuracy of discriminating between murmurs' absence and presence reached 76.10 % when evaluated on unseen data. The model had accuracies of 70 %, 88 %, and 86 % in predicting murmur presence in infants, children, and adolescents, respectively. The interpretation of the model revealed proper discrimination between the learned attributes, and AV channel was found important (score 0.75) for the murmur absence predictions while MV and TV were more important for murmur presence predictions. The findings potentiate deep learning as a powerful front-line tool for inferring CHD status in PCG recordings leveraging early detection of heart anomalies in young people. It is suggested as a tool that can be used independently from high-cost machinery or expert assessment.

Cardiac Multi-Frequency Vibration Signal Sensor Module and Feature Extraction Method Based on Vibration Modeling

Cardiovascular diseases pose a long-term risk to human health. This study focuses on the rich-spectrum mechanical vibrations generated during cardiac activity. By combining Fourier series theory, we propose a multi-frequency vibration model for the heart, decomposing cardiac vibration into frequency bands and establishing a systematic interpretation for detecting multi-frequency cardiac vibrations. Based on this, we develop a small multi-frequency vibration sensor module based on flexible polyvinylidene fluoride (PVDF) films, which is capable of synchronously collecting ultra-low-frequency seismocardiography (ULF-SCG), seismocardiography (SCG), and phonocardiography (PCG) signals with high sensitivity. Comparative experiments validate the sensor's performance and we further develop an algorithm framework for feature extraction based on 1D-CNN models, achieving continuous recognition of multiple vibration features. Testing shows that the recognition coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE) of the 8 features are 0.95, 2.18 ms, and 4.89 ms, respectively, with an average prediction speed of 60.18 us/point, meeting the re-quirements for online monitoring while ensuring accuracy in extracting multiple feature points. Finally, integrating the vibration model, sensor, and feature extraction algorithm, we propose a dynamic monitoring system for multi-frequency cardiac vibration, which can be applied to portable monitoring devices for daily dynamic cardiac monitoring, providing a new approach for the early diagnosis and prevention of cardiovascular diseases.

Study of Morpho-Functional Characteristics of the Cardiovascular System According to Electrocardiography, Phonocardiography, Echocardiography in Masters Athletics

Background

Many authors have noted the lack of knowledge on the causal relationship between the degree of physical activity, the dynamics, and outcomes of diseases, as well as the influence of sports history on the rehabilitation potential of former athletes.

Purpose

Assessment of the functional state of the cardiovascular system according to the indicators of electrocardiography, polycardiography, echocardiography and the level of physical performance in masters athletes.

Patients and Methods

The study included a main group consisting of 100 athletes, who had undergone electrocardiography, poly-electrocardiography, ultrasound echocardiography, heart rate and blood pressure measurement to determine their level of physical performance. The subjects were then divided into 2 groups. The first group included 75 people who continue to be active in regular sports activities. The second group consisted of 25 people who completely stopped training or had only occasional, unsystematic physical activities. A control group of 31 people, consisting of people of the same age who had not been involved in sports earlier, was examined according to the same program.

Results

The data obtained by us show that sports activities do contribute to the increasing stability of the body and maximize the deployment of the capabilities of the circulatory system, including their long-term preservation in masters athletic. Athletes who have stopped training have signs of age-related changes in the heart and blood vessels, which seem to be more frequent and earlier than those who continue training. A higher degree of myocardial contractility (in 90.67% of cases) can also be seen in the main group.

Conclusion

Masters athletes and those who stopped training after completing their sports career, should have notably thorough medical supervision and undergo regular annual in-depth examination.

Patient Self-Monitoring Using Intelligent Phonocardiography on a Mobile Platform

The paper presents the design and high-fidelity prototype of the remote patient self-monitoring system using a combination of intelligent phonocardiography, mobile and web-based platforms. The advantage of self-monitoring is patient awareness about potential changes, the convenience of performing the measurement often, and the saving of the findings. A mobile platform enables a physician to see the data, get a summary of patient recordings, and as well as saving the data. We have designed two user profiles to enable such functionality and to enable consultations. During the three development iterations, two main prototypes were developed. In the patient prototype, the main functionality is measuring PCG signals, but with the possibility of reading more details about the results. In the physician's prototype, the main functionality is the patient overview, with the possibility of querying through old patient data to consult newer patients. For physicians to monitor patients monitoring themselves, the solution needs to be properly clinically validated and regulatory demands satisfy before it could be utilized in the Norwegian health domain.

Novel phonocardiography system for heartbeat detection from various locations

The paper presents evaluation of the proposed phonocardiography (PCG) measurement system designed primarily for heartbeat detection to estimate heart rate (HR). Typically, HR estimation is performed using electrocardiography (ECG) or pulse wave as one of the fundamental diagnostic methodologies for assessing cardiac function. The system includes novel both sensory part and data processing procedure, which is based on signal preprocessing using Wavelet Transform (WT) and Shannon energy computation and heart sounds classification using K-means. Due to the lack of standardization in the placement of PCG sensors, the study focuses on evaluating the signal quality obtained from 7 different sensor locations on the subject's chest and investigates which locations are most suitable for recording heart sounds. The suitability of sensor localization was examined in 27 subjects by detecting the first two heart sounds (S1, S2). The HR detection sensitivity related to reference ECG from all sensor positions reached values over 88.9 and 77.4% in detection of S1 and S2, respectively. The placement in the middle of sternum showed the higher signal quality with median of the proper S1 and S2 detection sensitivity of 98.5 and 97.5%, respectively.

Recognition of Pediatric Congenital Heart Diseases by Using Phonocardiogram Signals and Transformer-Based Neural Networks

The phonocardiogram (PCG) or heart sound auscultation is a low-cost and non-invasive method to diagnose Congenital Heart Disease (CHD). However, recognizing CHD in the pediatric population based on heart sounds is difficult because it requires high medical training and skills. Also, the dependency of PCG signal quality on sensor location and developing heart in children are challenging. This study proposed a deep learning model that classifies unprocessed or raw PCG signals to diagnose CHD using a one-dimensional Convolution Neural Network (1D-CNN) with an attention transformer. The model was built on the raw PCG data of 484 patients. The results showed that the attention transformer model had a good balance of accuracy of 0.923, a sensitivity of 0.973, and a specificity of 0.833. The Receiver Operating Characteristic (ROC) plot generated an Area Under Curve (AUC) value of 0.964, and the F1-score was 0.939. The suggested model could provide quick and appropriate real-time remote diagnosis application in classifying PCG of CHD from non-CHD subjects.Clinical Relevance- The suggested methodology can be utilized to analyze PCG signals more quickly and affordably for rural doctors as a first screening tool before sending the cases to experts.

Time-Frequency Fragment Selection for Disease Detection from Imbalanced Phonocardiogram Data

Cardiovascular disease (CVD) has become the most concerning disease worldwide. A Phonocardiogram (PCG), the graphical representation of heart sound, is a non-invasive method that helps to detect CVD by analyzing its characteristics. Several machine learning (ML) approaches have been proposed in the last decade to assist practitioners in interpreting this disease accurately. However, the ML-based method requires a considerable amount of PCG data with a balance between data categories for unbiased performance. Moreover, PCG data in the literature is scarce, and the available database has a strong imbalance between the normal and abnormal categories. This data imbalance causes outcomes to be severely biased towards classes with greater samples. This work proposes a variable-hop fragment selection method with a pre-trained CNN model to counter the issues of data scarcity and imbalance. The proposed framework improves 7.12% of unweighted average recall (UAR) value for assessing an imbalanced PCG dataset compared to the state-of-the-art method and reports an overall UAR of 92.46% on the PhysioNet/CinC Challenge 2016 dataset. The improved performance signifies the clinical relevance of the work providing reliable assistance for heart auscultation and has the potential to screen for heart pathologies in data constraint applications.

On the Impact of Synchronous Electrocardiogram Signals for Heart Sounds Segmentation

In this paper we study the heart sound segmentation problem using Deep Neural Networks. The impact of available electrocardiogram (ECG) signals in addition to phonocardiogram (PCG) signals is evaluated. To incorporate ECG, two different models considered, which are built upon a 1D U-net - an early fusion one that fuses ECG in an early processing stage, and a late fusion one that averages the probabilities obtained by two networks applied independently on PCG and ECG data. Results show that, in contrast with traditional uses of ECG for PCG gating, early fusion of PCG and ECG information can provide more robust heart sound segmentation. As a proof of concept, we use the publicly available PhysioNet dataset. Validation results provide, on average, a sensitivity of 97.2%, 94.5%, and 95.6% and a Positive Predictive Value of 97.5%, 96.2%, and 96.1% for Early-fusion, Late-fusion, and unimodal (PCG only) models, respectively, showing the advantages of combining both signals at early stages to segment heart sounds.Clinical relevance- Cardiac auscultation is the first line of screening for cardiovascular diseases. Its low cost and simplicity are especially suitable for screening large populations in underprivileged countries. The proposed analysis and algorithm show the potential of effectively including electrocardiogram information to improve heart sound segmentation performance, thus enhancing the capacity of extracting useful information from heart sound recordings.

Deep Time Growing Neural Network vs Convolutional Neural Network for Intelligent Phonocardiography

This paper explores the capabilities of a sophisticated deep learning method, named Deep Time Growing Neural Network (DTGNN), and compares its possibilities against a generally well-known method, Convolutional Neural network (CNN). The comparison is performed by using time series of the heart sound signal, so-called Phonocardiography (PCG). The classification objective is to discriminate between healthy and patients with cardiac diseases by applying a deep machine learning method to PCGs. This approach which is called intelligent phonocardiography has received interest from the researchers toward the development of a smart stethoscope for decentralized diagnosis of heart disease. It is found that DTGNN associates further flexibility to the approach which enables the classifier to learn subtle contents of PCG, and meanwhile better copes with the complexities intrinsically that exist in the medical applications such as the imbalance training. The structural risk of the two methods is compared using the A-Test method.

Automatic segmentation for neonatal phonocardiogram

This work addresses the automatic segmentation of neonatal phonocardiogram (PCG) to be used in the artificial intelligence-assisted diagnosis of abnormal heart sounds. The proposed novel algorithm has a single free parameter - the maximum heart rate. The algorithm is compared with the baseline algorithm, which was developed for adult PCG segmentation. When evaluated on a large clinical dataset of neonatal PCG with a total duration of over 7h, an F1 score of 0.94 is achieved. The main features relevant for the segmentation of neonatal PCG are identified and discussed. The algorithm is able to increase the number of cardiac cycles by a factor of 5 compared to manual segmentation, potentially allowing to improve the performance of heart abnormality detection algorithms.

Can Heart Sound Denoising be Beneficial in Phonocardiogram Classification Tasksƒ

The purpose of computer-aided diagnosis (CAD) systems is to improve the detection of diseases in a shorter time and with reduced subjectivity. A robust system frequently requires a noise-free input signal. For CADs which use heart sounds, this problem is critical as heart sounds are often low amplitude and affected by some unavoidable sources of noise such as movement artifacts and physiological sounds. Removing noises by using denoising algorithms can be beneficial in improving the diagnostics accuracy of CADs. In this study, four denoising algorithms were investigated. Each algorithm has been carefully adapted to fit the requirements of the phonocardiograph signal. The effect of the denoising algorithms was objectively compared based on the improvement it introduces in the classification performance of the heart sound dataset. According to the findings, using denoising methods directly before classification decreased the algorithm's classification performance because a murmur was also treated as noise and suppressed by the denoising process. However, when denoising using Wiener estimation-based spectral subtraction was used as a preprocessing step to improve the segmentation algorithm, it increased the system's classification performance with a sensitivity of 96.0%, a specificity of 74.0%, and an overall score of 85.0%. As a result, to improve performance, denoising can be added as a preprocessing step into heart sound classifiers that are based on heart sound segmentation.

Unsupervised Heart Sound Decomposition and State Estimation with Generative Oscillation Models

This paper proposes a new generative probabilistic model for phonocardiograms (PCGs) that can simultaneously capture oscillatory factors and state transitions in cardiac cycles. Conventionally, PCGs have been modeled in two main aspects. One is a state space model that represents recurrent and frequently appearing state transitions. Another is a factor model that expresses the PCG as a non-stationary signal consisting of multiple oscillations. To model these perspectives in a unified framework, we combine an oscillation decomposition with a state space model. The proposed model can decompose the PCG into cardiac state dependent oscillations by reflecting the mechanism of cardiac sounds generation in an unsupervised manner. In the experiments, our model achieved better accuracy in the state estimation task compared to the empirical mode decomposition method. In addition, our model detected S2 onsets more accurately than the supervised segmentation method when distributions among PCG signals were different.

Automated Assessment of the Quality of Phonocardographic Recordings through Signal-to-Noise Ratio for Home Monitoring Applications

The signal quality limits the applicability of phonocardiography at the patients’ domicile. This work proposes the signal-to-noise ratio of the recorded signal as its main quality metrics. Moreover, we define the minimum acceptable values of the signal-to-noise ratio that warrantee an accuracy of the derived parameters acceptable in clinics. We considered 25 original heart sounds recordings, which we corrupted by adding noise to decrease their signal-to-noise ratio. We found that a signal-to-noise ratio equal to or higher than 14 dB warrants an uncertainty of the estimate of the valve closure latencies below 1 ms. This accuracy is higher than that required by most clinical applications. We validated the proposed method against a public database, obtaining results comparable to those obtained on our sample population. In conclusion, we defined (a) the signal-to-noise ratio of the phonocardiographic signal as the preferred metric to evaluate its quality and (b) the minimum values of the signal-to-noise ratio required to obtain an uncertainty of the latency of heart sound components compatible with clinical applications. We believe these results are crucial for the development of home monitoring systems aimed at preventing acute episodes of heart failure and that can be safely operated by naïve users.

A Robust Interpretable Deep Learning Classifier for Heart Anomaly Detection Without Segmentation

Traditionally, abnormal heart sound classification is framed as a three-stage process. The first stage involves segmenting the phonocardiogram to detect fundamental heart sounds; after which features are extracted and classification is performed. Some researchers in the field argue the segmentation step is an unwanted computational burden, whereas others embrace it as a prior step to feature extraction. When comparing accuracies achieved by studies that have segmented heart sounds before analysis with those who have overlooked that step, the question of whether to segment heart sounds before feature extraction is still open. In this study, we explicitly examine the importance of heart sound segmentation as a prior step for heart sound classification, and then seek to apply the obtained insights to propose a robust classifier for abnormal heart sound detection. Furthermore, recognizing the pressing need for explainable Artificial Intelligence (AI) models in the medical domain, we also unveil hidden representations learned by the classifier using model interpretation techniques. Experimental results demonstrate that the segmentation which can be learned by the model plays an essential role in abnormal heart sound classification. Our new classifier is also shown to be robust, stable and most importantly, explainable, with an accuracy of almost 100% on the widely used PhysioNet dataset.

Do you hear what you see? Utilizing phonocardiography to enhance proficiency in cardiac auscultation

INTRODUCTION

Cardiac auscultation skills have proven difficult to train and maintain. The authors investigated whether using phonocardiograms as visual adjuncts to audio cases improved first-year medical students' cardiac auscultation performance.

METHODS

The authors randomized 135 first-year medical students using an email referral link in 2018 and 2019 to train using audio-only cases (audio group) or audio with phonocardiogram tracings (combined group). Training included 7 cases with normal and abnormal auscultation findings. The assessment included feature identification and diagnostic accuracy using 14 audio-only cases, 7 presented during training, and 7 alternate versions of the same diagnoses. The assessment-administered immediately after training and repeated 7 days later-prompted participants to identify the key features and diagnoses for 14 audio-only cases. Key feature scores and diagnostic accuracy were compared between groups using repeated measures ANOVA.

RESULTS

Mean key feature scores were statistically significantly higher in the combined group (70%, 95% CI 67-75%) compared to the audio group (61%, 95% CI 56-66%) (F(1,116) = 6.144, p = 0.015, d_s = 0.45). Similarly, mean diagnostic accuracy in the combined group (68%, 95% CI 62-73%) was significantly higher than the audio group, although with small effect size (59%, 95% CI 54-65%) (F(1,116) = 4.548, p = 0.035, d_s = 0.40). Time on task for the assessment and prior auscultation experience did not significantly impact performance on either measure.

DISCUSSION

The addition of phonocardiograms to supplement cardiac auscultation training improves diagnostic accuracy and heart sound feature identification amongst novice students compared to training with audio alone.

Can empirical mode decomposition improve heartbeat detection in fetal phonocardiography signals?

BACKGROUND AND OBJECTIVE

A fetal phonocardiography signal can be hard to interpret and classify due to various sources of additive noise in the womb, spanning from fetal movement to maternal heart sounds. Nevertheless, the non-invasive nature of the method makes it potentially suitable for long-term monitoring of fetal health, especially since it can be implemented on ubiquitous devices such as smartphones. We have employed empirical mode decomposition for the extraction of intrinsic mode functions that would enable the utilization of additional characteristics from the signal.

METHODS

Fetal heart recordings from 7 pregnant women in the 3rd trimester or pregnancy were taken in parallel with a measurement microphone and a portable Doppler device. Signal peaks positions from the Doppler were taken as the locations of S1 heart sounds and subsequently used as classification labels for the microphone signal. After employing a moving window approach for segmentation, more than 7600 observations were stored in the final dataset. The 135 extracted features consisted of typical audio temporal and spectral characteristics, each taken from separate sets of audio signals and intrinsic mode functions. We have used a number of metrics and methods to validate the usability of features, including univariate analysis of feature ranking and importance. Furthermore, we have used machine learning to train a number of classifiers to validate the usability of features based on intrinsic mode functions, taking prediction accuracy as the comparison metric.

RESULTS

Features extracted from intrinsic mode functions combined with audio features significantly improve accuracy in comparison to using only audio features. The improvements of detection accuracy obtained with a selected set of combined features spanned from 3.8% to even 10.3% based on the employed classifier.

CONCLUSIONS

We have utilized empirical mode decomposition as a method of extracting features relevant for fetal heartbeat classification. The results show consistent improvements in detection accuracy when these characteristics are added to a set of conventional audio features. This implies substantial benefits of applying empirical mode decomposition and lays the groundwork for future research on fetal heartbeat detection.

Cross-Domain Transfer Learning for PCG Diagnosis Algorithm

Cardiechema is a way to reflect cardiovascular disease where the doctor uses a stethoscope to help determine the heart condition with a sound map. In this paper, phonocardiogram (PCG) is used as a diagnostic signal, and a deep learning diagnostic framework is proposed. By improving the architecture and modules, a new transfer learning and boosting architecture is mainly employed. In addition, a segmentation method is designed to improve on the existing signal segmentation methods, such as R wave to R wave interval segmentation and fixed segmentation. For the evaluation, the final diagnostic architecture achieved a sustainable performance with a public PCG database.

Multifrequency Phased Tracking Method for Estimating Velocity in Heart Wall

Local high-accuracy velocity estimation is important for the ultrasound-based evaluation of regional myocardial function. The ultrasound phase difference at the center frequency of the transmitted signal has been conventionally used for velocity estimation. In the conventional method, spatial averaging is necessary owing to the frequency-dependent attenuation and interference of backscattered waves. Here, we propose a method for suppressing these effects using multifrequency phase differences. The resulting improvement in velocity estimation in the heart wall was validated by in vivo experiments. In the conventional method, the velocity waveform exhibits spike-like changes. The velocity waveform estimated using the proposed method did not exhibit such changes. Because the proposed method estimates myocardium velocity without spatial averaging, it can be used for measuring heart wall dynamics involving thickness changes.

Temporal-Framing Adaptive Network for Heart Sound Segmentation Without Prior Knowledge of State Duration

OBJECTIVE

This paper presents a novel heart sound segmentation algorithm based on Temporal-Framing Adaptive Network (TFAN), including state transition loss and dynamic inference.

METHODS

In contrast to previous state-of-the-art approaches, TFAN does not require any prior knowledge of the state duration of heart sounds and is therefore likely to generalize to non sinus rhythm. TFAN was trained on 50 recordings randomly chosen from Training set A of the 2016 PhysioNet/Computer in Cardiology Challenge and tested on the other 12 independent databases (2,099 recordings and 52,180 beats). And further testing of performance was conducted on databases with three levels of increasing difficulty (LEVEL-I, -II and -III).

RESULTS

TFAN achieved a superior F₁ score for all 12 databases except for 'Test-B,' with an average of 96.72%, compared to 94.56% for logistic regression hidden semi-Markov model (LR-HSMM) and 94.18% for bidirectional gated recurrent neural network (BiGRNN). Moreover, TFAN achieved an overall F₁ score of 99.21%, 94.17%, 91.31% on LEVEL-I, -II and -III databases respectively, compared to 98.37%, 87.56%, 78.46% for LR-HSMM and 99.01%, 92.63%, 88.45% for BiGRNN.

CONCLUSION

TFAN therefore provides a substantial improvement on heart sound segmentation while using less parameters compared to BiGRNN.

SIGNIFICANCE

The proposed method is highly flexible and likely to apply to other non-stationary time series. Further work is required to understand to what extent this approach will provide improved diagnostic performance, although it is logical to assume superior segmentation will lead to improved diagnostics.

Fetal heart rate estimation from a single phonocardiogram signal using non-negative matrix factorization

Fetal heart rate (FHR) is an important characteristic in fetal well-being follow-up. It is classically estimated using the cardiotocogram (CTG) non-invasive reference technique. However, this latter presents some significant drawbacks. An alternative non-invasive solution based on the fetal phonocardiogram (fetal PCG) can be used. But most of proposed methods based on the PCG signal need to detect and to label the fetal cardiac S₁ and S₂ sounds, which may be a difficult task in certain conditions. Therefore, in this paper, we propose a new methodology for FHR estimation from fetal PCG with one single cardio-microphone and without the distinction constraint of heart sounds. The method is based on the non-negative matrix factorization (NMF) applied on the spectrogram of fetal PCG considered as a source-filter model. The proposed method provides satisfactory results on a preliminary dataset of abdominal PCG signals. When compared to the reference CTG, correlation on FHR estimations between PCG and CTG is around 90%.

Enhancement of the heart sound envelope using the logistic function amplitude moderation method

This paper presents a new method to extract the envelope of the fundamental heart sound (S1 and S2) using the logistic function. The sigmoid characteristic of the logistic function is incorporated to segregate S1, and S2 signal intensities from silent or noise interfered systolic and diastolic intervals in a heart sound cycle. This signal intensity transformation brings uniformity to the envelope peak of S1 and S2 sound by inclining the transform intensity distribution towards the upper asymptote of the sigmoid curve. The proposed logistic function based amplitude moderation (LFAM) envelogram method involves finding the critical upper amplitude (x_uc) above which the signals will be categorized as loud sound and the critical lower amplitude (x_lc) below which the signal will be considered as noise. These critical values are regressively obtained from the signal itself by histogram analysis of intensity distribution. The performance is evaluated on noisy PCG dataset taken from PhysioNet/Computing in Cardiology Challenge 2016. The LFAM envelope yields better hill-valley discrimination of heart sounds from its silent/noisy signal intervals. The enhance heart sound envelope peaks are better than conventional methods. The proposed envelope feature is evaluated for heart sound segmentation using HSMM. There is a significant improvement in segmentation accuracy, especially at a low signal-to-noise ratio. The best average F1 score is 97.73%.

Improved Segmentation with Dynamic Threshold Adjustment for Phonocardiography Recordings

In this study with the intent to segment phonocardiography (PCG) recordings, an algorithm that processes a feature vector obtained by jointly using wavelet transform and mel scaled energy spectrum of the PCG signal is proposed. The feature vector is processed by a peak detection algorithm which results in a set of peaks that meet some certain criteria and will be exploited in the succeeding stages of the algorithm. Heart sounds are labeled by convolving circularly a template and a fragment of the feature vector which is picked up with the guidance of the peaks. At the final stage, the algorithm tries to detect and correct erroneous labels. The performance of the algorithm was tested on both normal heart sounds and abnormal heart sounds; 80 records in total. As a result of these tests, for normal heart sounds S1 and S2 sounds were detected with 99,51% recall and 97,28% precision, while with 97,59% recall and 92,53% precision for abnormal heart sounds.

An Approach for Automatic Identification of Fundamental and Additional Sounds from Cardiac Sounds Recordings

This paper presents an approach for automatic segmentation of cardiac events from non-invasive sounds recordings, without the need of having an auxiliary signal reference. In addition, methods are proposed to subsequently differentiate cardiac events which correspond to normal cardiac cycles, from those which are due to abnormal activity of the heart. The detection of abnormal sounds is based on a model built with parameters which are obtained following feature extraction from those segments that were previously identified as normal fundamental heart sounds. The proposed algorithm achieved a sensitivity of 91.79% and 89.23% for the identification of normal fundamental, S₁ and S₂ sounds, and a true positive (TP) rate of 81.48% for abnormal additional sounds. These results were obtained using the PASCAL Classifying Heart Sounds challenge (CHSC) database.

Fully-Automated Diagnosis of Aortic Stenosis Using Phonocardiogram-Based Features

The irreversible damage and eventual heart failure caused by untreated aortic stenosis (AS) can be prevented by early detection and timely intervention. Prior work in the field of phonocardiogram (PCG) signal analysis has provided proof of concept for using heart-sound data in AS diagnosis. However, such systems either require operation by trained technicians, fail to address a diverse subject set, or involve unwieldy configuration procedures that challenge real-world application. This paper presents an end-to-end, fully-automated system that uses noise-subtraction, heartbeat-segmentation and quality-assurance algorithms to extract physiologically-motivated features from PCG signals to diagnose AS. When tested on n=96 patients showing a diverse set of cardiac and non-cardiac conditions, the system was able to diagnose AS with 92% sensitivity and 95% specificity.

Multi-source signal processing in phonocardiography: comparison among signal selection and signal enhancement techniques

Phonocardiography (PCG) is a promising tool for the diagnosis and follow-up of cardiovascular diseases. To date it is available only in clinical settings, because it relies on an experienced examiner for the positioning of the electronic stethoscope. Making it possible for an unexperienced user to obtain high quality PCG signals would allow for developing instruments suitable for homecare purposes. In this work, we test the usage of three standardly positioned microphone probes. The aim is to compare two different approaches for enhancing the PCG signal quality, namely a) selecting the single source with the highest Signal-to-Noise Ratio (SNR) and b) combining the three sources through array signal processing techniques. Both approaches were tested on a sample population counting 24 healthy subjects. We found that the two approaches above give statistically different results (two-tailed paired t-test, p = 0.037) in terms of SNR of the enhanced signal. Specifically, selecting the single source with highest SNR gives, on average, the best results. Moreover, this approach is also associated with the lowest computational cost. Finally, for every subject of our sample population, we obtained SNR values higher than 12.5 dB on the enhanced signal, which we consider as sufficient for the application of heart sound segmentation and classification algorithms. We believe that this methodology allows for obtaining PCG signals of sufficient quality for the analysis of heart sounds, thus opening to the applicability of PCG in a homecare context.

Electrocardiogram and Phonocardiogram Monitoring System for Cardiac Auscultation

Heart-sound auscultation is a rapid and fundamental technique used for examining the cardiovascular system. The main components of heart sounds are the first and second heart sounds. Discriminating these heart sounds under the presence of additional heart sounds and murmurs will be difficult. To recognize these signals efficiently, this study proposes a monitoring system with phonocardiogram and electrocardiogram. This system has two key points. The first is chip implementation, including capacitor coupled amplifier, transimpedance amplifier, high-pass sigma-delta modulator, and digital signal processing block. The chip in the system is fabricated in 0.18 μm standard complementary metal-oxide-semiconductor process. The second is a software application on smartphones for heart-related physiological signal recording, display, and identification. A wavelet-based QRS complex detection algorithm verified by MIT/BIH Arrhythmia Database is also proposed. The overall measured positive prediction, sensitivity, and error rate of the proposed algorithm are 99.90%, 99.82%, and 0.28%, respectively. During auscultation, doctors may refer to these physiological signals displayed on the smartphone and simultaneously listen to the heart sounds to diagnose the potential heart disease. By taking advantage of signal visualization and keeping the original diagnosis procedure, the uncertainty existing in heart sounds can be eliminated, and the training period to acquire auscultation skills can be reduced.

Ultimate Third Heart Sound

A 79-year-old man with dilated cardiomyopathy and severe functional mitral regurgitation presented with general fatigue and dyspnea. Auscultation revealed a systolic regurgitant murmur with a minimized second heart sound due to a low output. On the other hand, the third heart sound was ultimately enhanced, being visible and palpable as a pulsatile knock of the precordium. Phonocardiography and echocardiography successfully confirmed early-diastolic rapid distension of the left ventricle along with rapid ventricular filling and abrupt deceleration of the atrioventricular blood flow to be the precise etiology of the ultimate third heart sound, indicating critically deteriorated hemodynamics due to massive mitral regurgitation combined with a low output.

Comparison of multiple cardiac signal acquisition technologies for heart rate variability analysis

Heart rate variability analysis is a recognized non-invasive tool that is used to assess autonomic nervous system regulation in various clinical settings and medical conditions. A wide variety of HRV analysis methods have been proposed, but they all require a certain number of cardiac beats intervals. There are many ways to record cardiac activity: electrocardiography, phonocardiography, plethysmocardiography, seismocardiography. However, the feasibility of performing HRV analysis with these technologies and particularly their ability to detect autonomic nervous system changes still has to be studied. In this study, we developed a technology allowing the simultaneous monitoring of electrocardiography, phonocardiography, seismocardiography, photoplethysmocardiography and piezoplethysmocardiography and investigated whether these sensors could be used for HRV analysis. We therefore tested the evolution of several HRV parameters computed from several sensors before, during and after a postural change. The main findings of our study is that even if most sensors were suitable for mean HR computation, some of them demonstrated limited agreement for several HRV analyses methods. We also demonstrated that piezoplethysmocardiography showed better agreement with ECG than other sensors for most HRV indexes.

AcCorps: A low-cost 3D printed stethoscope for fetal phonocardiography

The analysis of fetal heart rate provides valuable information regarding the fetus wellbeing. Fetal phonocardiography is a low-cost and passive method allowing the acquisition of fetal heart rate by recording acoustic vibrations on the mother's abdomen. However, most of available stethoscopes are not optimized for a robust acquisition of fetal heart sound. In this publication, we investigated a new design of low-cost and 3D printed stethoscope. This device was optimized to provide an acoustic amplification especially in the low-frequency band which corresponds to the fetal heart sounds. This device was tested i) in silico, ii) on a test bench and iii) on 5 pregnant volunteers.

Structural Risk Evaluation of a Deep Neural Network and a Markov Model in Extracting Medical Information from Phonocardiography

This paper presents a method for exploring structural risk of any artificial intelligence-based method in bioinformatics, the A-Test method. This method provides a way to not only quantitate the structural risk associated with a classification method, but provides a graphical representation to compare the learning capacity of different classification methods. Two different methods, Deep Time Growing Neural Network (DTGNN) and Hidden Markov Model (HMM), are selected as two classification methods for comparison. Time series of heart sound signals are employed as the case study where the classifiers are trained to learn the disease-related changes. Results showed that the DTGNN offers a superior performance both in terms of the capacity and the structural risk. The A-Test method can be especially employed in comparing the learning methods with small data size.

Cardiac cycle-synchronized electrical muscle stimulator for lower limb training with the potential to reduce the heart's pumping workload

Background

The lower limb muscle may play an important role in decreasing the heart’s pumping workload. Aging and inactivity cause atrophy and weakness of the muscle, leading to a loss of the heart-assisting role. An electrical lower limb muscle stimulator can prevent atrophy and weakness more effectively than conventional resistance training; however, it has been reported to increase the heart’s pumping workload in some situations. Therefore, more effective tools should be developed.

Methods

We newly developed a cardiac cycle-synchronized electrical lower limb muscle stimulator by combining a commercially available electrocardiogram monitor and belt electrode skeletal muscle electrical stimulator, making it possible to achieve strong and wide but not painful muscle contractions. Then, we tested the stimulator in 11 healthy volunteers to determine whether the special equipment enabled lower limb muscle training without harming the hemodynamics using plethysmography and a percutaneous cardiac output analyzer.

Results

In 9 of 11 subjects, the stimulator generated diastolic augmentation waves on the dicrotic notches and end-diastolic pressure reduction waves on the plethysmogram waveforms of the brachial artery, showing analogous waveforms in the intra-aortic balloon pumping heart-assisting therapy. The heart rate, stroke volume, and cardiac output significantly increased during the stimulation. There was no change in the systolic or diastolic blood pressure during the stimulation.

Conclusion

Cardiac cycle-synchronized electrical muscle stimulation for the lower limbs may enable muscle training without harmfully influencing the hemodynamics and with a potential to reduce the heart’s pumping workload, suggesting a promising tool for effectively treating both locomotor and cardiovascular disorders.

Novel features from autocorrelation and spectrum to classify Phonocardiogram quality

Phonocardiogram (PCG) or auscultation via a stethoscope forms the basis of preliminary medical screening. But PCG recorded in an uncontrolled environment is inherently noisy. In this paper we have derived novel features from the spectral domain and autocorrelation waveforms. These are used to identify the quality of a PCG recording and accepting only diagnosable quality recordings for further analysis. These features proved to be robust irrespective of variations in devices and in data collection protocols employed to ensure consistent data quality. A freely available, large, diverse, medical-grade PCG dataset was used for creating the training models. Results show that the proposed methodology yields an accuracy score of ~75% on our in-house PCG dataset, collected using a low-cost smartphone-based digital stethoscope.

Detecting fetal heart sounds by means of Fractal Dimension analysis in the Wavelet domain

Phonocardiography is a low-cost technique for the detection of fetal heart sounds (FHS) that can extend clinical auscultation in mobile and home care setups. The work presented here examines the transferability of a Wavelet Transform (WT)-based method that combines also Fractal Dimension (FD) analysis, previously proposed as WT-FD for the cases of lung and bowel sound analysis [4], to the extraction of FHSs. The WT-FD method has been evaluated with 12 simulated FHS signals and has shown promising results in terms of accuracy and performance (89%) in identifying the location of heartbeat, even in cases of signals with additive noise up to (6dB). This robustness paves the way for WT-FD testing in real FHSs, recorded under clinical setting, clearly contributing to better evaluation of the fetal heart functionality.

Pattern discovery and similarity assessment for robust heart sound segmentation

Heart Sound Segmentation plays a fundamental role in pathology detection in Phonocardiogram (PCG) signals. This matter of study has been widely studied in the past decades, however the majority of algorithms' results correspond only to small databases, composed by only quality signals or signals specific to one acquisition system. In this work we proposed a robust segmentation algorithm integrated with clinical information, based on a pattern recognition approach for segmentation of the fundamental heart sounds, which is validated in several databases from different countries and with different acquisition instrumentations. The database comprises a total of 3153 recordings from 764 patients with a variety of pathological conditions. The general results were 95% and 96% of sensitivity and positive predictivity, respectively. Based on the results the algorithm is able to perform with accuracy maintaining generalization capabilities.

Pattern discovery and similarity assessment for robust Heart Sound Segmentation

Heart Sound Segmentation plays a fundamental role in pathology detection in Phonocardiogram (PCG) signals. This matter of study has been widely studied in the past decades, however the majority of algorithms' results correspond only to small databases, composed by only quality signals or signals specific to one acquisition system. In this work we proposed a robust segmentation algorithm integrated with clinical information, based on a pattern recognition approach for segmentation of the fundamental heart sounds, which is validated in several databases from different countries and with different acquisition instrumentations. The database comprises a total of 3153 recordings from 764 patients with a variety of pathological conditions. The general results were 95% and 96% of sensitivity and positive predictivity, respectively. Based on the results the algorithm is able to perform with accuracy maintaining generalization capabilities.

Design and evaluation of a parametric model for cardiac sounds

Heart sound analysis plays an important role in the auscultative diagnosis process to detect the presence of cardiovascular diseases. In this paper we propose a novel parametric heart sound model that accurately represents normal and pathological cardiac audio signals, also known as phonocardiograms (PCG). The proposed model considers that the PCG signal is formed by the sum of two parts: one of them is deterministic and the other one is stochastic. The first part contains most of the acoustic energy. This part is modeled by the Matching Pursuit (MP) algorithm, which performs an analysis-synthesis procedure to represent the PCG signal as a linear combination of elementary waveforms. The second part, also called residual, is obtained after subtracting the deterministic signal from the original heart sound recording and can be accurately represented as an autoregressive process using the Linear Predictive Coding (LPC) technique. We evaluate the proposed heart sound model by performing subjective and objective tests using signals corresponding to different pathological cardiac sounds. The results of the objective evaluation show an average Percentage of Root-Mean-Square Difference of approximately 5% between the original heart sound and the reconstructed signal. For the subjective test we conducted a formal methodology for perceptual evaluation of audio quality with the assistance of medical experts. Statistical results of the subjective evaluation show that our model provides a highly accurate approximation of real heart sound signals. We are not aware of any previous heart sound model rigorously evaluated as our proposal.

A robust dataset-agnostic heart disease classifier from Phonocardiogram

Automatic classification of normal and abnormal heart sounds is a popular area of research. However, building a robust algorithm unaffected by signal quality and patient demography is a challenge. In this paper we have analysed a wide list of Phonocardiogram (PCG) features in time and frequency domain along with morphological and statistical features to construct a robust and discriminative feature set for dataset-agnostic classification of normal and cardiac patients. The large and open access database, made available in Physionet 2016 challenge was used for feature selection, internal validation and creation of training models. A second dataset of 41 PCG segments, collected using our in-house smart phone based digital stethoscope from an Indian hospital was used for performance evaluation. Our proposed methodology yielded sensitivity and specificity scores of 0.76 and 0.75 respectively on the test dataset in classifying cardiovascular diseases. The methodology also outperformed three popular prior art approaches, when applied on the same dataset.

Analysis of phonocardiogram signals through proactive denoising using novel self-discriminant learner

Phonocardiogram (PCG) records heart sound and murmurs, which contains significant information of cardiac health. Analysis of PCG signal has the potential to detect abnormal cardiac condition. However, the presence of noise and motion artifacts in PCG hinders the accuracy of clinical event detection. Thus, noise detection and elimination are crucial to ensure accurate clinical analysis. In this paper, we present a robust denoising technique, Proclean that precisely detects the noisy PCG signal through pattern recognition, and statistical learning. We propose a novel self-discriminant learner that ensures to obtain distinct feature set to distinguish clean and noisy PCG signals without human-in-loop. We demonstrate that our proposed denoising leads to higher accuracy in subsequent clinical analytics for medical investigation. Our extensive experimentations with publicly available MIT-Physionet datasets show that we achieve more than 85% accuracy for noisy PCG signal detection. Further, we establish that physiological abnormality detection improves by more than 20%, when our proposed denoising mechanism is applied.

Intelligent Phonocardiography for Screening Ventricular Septal Defect Using Time Growing Neural Network

This paper presents results of a study on the applicability of the intelligent phonocardiography in discriminating between Ventricular Spetal Defect (VSD) and regurgitation of the atrioventricular valves. An original machine learning method, based on the Time Growing Neural Network (TGNN), is employed for classifying the phonocardiographic recordings collected from the pediatric referrals to a children hospital. 90 individuals, 30 VSD, 30 with the valvular regurgitation, and 30 healthy subjects, participated in the study after obtaining the informed consents. The accuracy and sensitivity of the approach is estimated to be 86.7% and 83.3%, respectively, showing a good performance to be used as a decision support system.

An open access database for the evaluation of heart sound algorithms

In the past few decades, analysis of heart sound signals (i.e. the phonocardiogram or PCG), especially for automated heart sound segmentation and classification, has been widely studied and has been reported to have the potential value to detect pathology accurately in clinical applications. However, comparative analyses of algorithms in the literature have been hindered by the lack of high-quality, rigorously validated, and standardized open databases of heart sound recordings. This paper describes a public heart sound database, assembled for an international competition, the PhysioNet/Computing in Cardiology (CinC) Challenge 2016. The archive comprises nine different heart sound databases sourced from multiple research groups around the world. It includes 2435 heart sound recordings in total collected from 1297 healthy subjects and patients with a variety of conditions, including heart valve disease and coronary artery disease. The recordings were collected from a variety of clinical or nonclinical (such as in-home visits) environments and equipment. The length of recording varied from several seconds to several minutes. This article reports detailed information about the subjects/patients including demographics (number, age, gender), recordings (number, location, state and time length), associated synchronously recorded signals, sampling frequency and sensor type used. We also provide a brief summary of the commonly used heart sound segmentation and classification methods, including open source code provided concurrently for the Challenge. A description of the PhysioNet/CinC Challenge 2016, including the main aims, the training and test sets, the hand corrected annotations for different heart sound states, the scoring mechanism, and associated open source code are provided. In addition, several potential benefits from the public heart sound database are discussed.

Usefulness of the second heart sound for predicting pulmonary hypertension in patients with interstitial lung disease

CONTEXT AND OBJECTIVE

P2 hyperphonesis is considered to be a valuable finding in semiological diagnoses of pulmonary hypertension (PH). The aim here was to evaluate the accuracy of the pulmonary component of second heart sounds for predicting PH in patients with interstitial lung disease.

DESIGN AND SETTING

Cross-sectional study at the University of Brasilia and Hospital de Base do Distrito Federal.

METHODS

Heart sounds were acquired using an electronic stethoscope and were analyzed using phonocardiography. Clinical signs suggestive of PH, such as second heart sound (S2) in pulmonary area louder than in aortic area; P2 > A2 in pulmonary area and P2 present in mitral area, were compared with Doppler echocardiographic parameters suggestive of PH. Sensitivity (S), specificity (Sp) and positive (LR+) and negative (LR-) likelihood ratios were evaluated.

RESULTS

There was no significant correlation between S2 or P2 amplitude and PASP (pulmonary artery systolic pressure) (P = 0.185 and 0.115; P= 0.13 and 0.34, respectively). Higher S2 in pulmonary area than in aortic area, compared with all the criteria suggestive of PH, showed S = 60%, Sp= 22%; LR+ = 0.7; LR- = 1.7; while P2> A2 showed S= 57%, Sp = 39%; LR+ = 0.9; LR- = 1.1; and P2 in mitral area showed: S= 68%, Sp = 41%; LR+ = 1.1; LR- = 0.7. All these signals together showed: S= 50%, Sp = 56%.

CONCLUSIONS

The semiological signs indicative of PH presented low sensitivity and specificity levels for clinically diagnosing this comorbidity.

Exploring embedding matrices and the entropy gradient for the segmentation of heart sounds in real noisy environments

In this paper we explore a novel feature for the segmentation of heart sounds: the entropy gradient. We are motivated by the fact that auscultations in real environments are highly contaminated by noise and results reinforce our suspicions that the entropy gradient is not only robust to such noise but maintains a high sensitivity to the S1 and S2 components of the signal. Our whole approach consists of three stages, out of which the last two are novel contributions to this field. The first stage consists of typical pre-processing and wavelet reconstruction to obtain the Shannon energy envelogram. On the second stage we use an embedding matrix to track the dynamics of the system, which is formed by delay vectors with higher dimension than the corresponding attractor. On the third stage, we use the eigenvalues and eigenvectors of the embedding matrix to estimate the entropy of the envelogram. Finite differences are used to estimate entropy gradients, in which standard peak picking approaches are used for heart sound segmentation. Experiments are performed on a public dataset of pediatric auscultations obtained in real environments and results show the promising potential of this novel feature for such noisy scenarios.

[An Improved Empirical Mode Decomposition Algorithm for Phonocardiogram Signal De-noising and Its Application in S1/S2 Extraction]

In this paper, an improved empirical mode decomposition (EMD) algorithm for phonocardiogram (PCG) signal de-noising is proposed. Based on PCG signal processing theory, the S1/S2 components can be extracted by combining the improved EMD-Wavelet algorithm and Shannon energy envelope algorithm. Firstly, by applying EMD-Wavelet algorithm for pre-processing, the PCG signal was well filtered. Then, the filtered PCG signal was saved and applied in the following processing steps. Secondly, time domain features, frequency domain features and energy envelope of the each intrinsic mode function's (IMF) were computed. Based on the time frequency domain features of PCG's IMF components which were extracted from the EMD algorithm and energy envelope of the PCG, the S1/S2 components were pinpointed accurately. Meanwhile, a detecting fixed method, which was based on the time domain processing, was proposed to amend the detection results. Finally, to test the performance of the algorithm proposed in this paper, a series of experiments was contrived. The experiments with thirty samples were tested for validating the effectiveness of the new method. Results of test experiments revealed that the accuracy for recognizing S1/S2 components was as high as 99.75%. Comparing the results of the method proposed in this paper with those of traditional algorithm, the detection accuracy was increased by 5.56%. The detection results showed that the algorithm described in this paper was effective and accurate. The work described in this paper will be utilized in the further studying on identity recognition.

De-noising the abdominal phonogram for foetal heart rate extraction: blind source separation versus empirical filtering

This work explored the suitability of using the foetal phonocardiogram (FPCG) blindly separated from the abdominal phonogram as a source for foetal heart rate (FHR) measuring in antenatal surveillance. To this end, and working on a dataset of 15 abdominal phonograms, the FPCG was estimated by using two de-noising approaches (1) single-channel independent component analysis (SCICA) to produce FPCG(e) and (2) empirical filtering to produce FPCG(g). Next, the FPCGs were further processed to collect the beat-to-beat FHR and the resulting time-series (FCTG(e) and FCTG(g) were compared to the reference signal given by the abdominal ECG (FCTG(r)). Results are promising, the FPCG(e) gives rise to a FCTG(e) that resembles FCTG(r) and, most importantly, whose mean FHR value is statistically equivalent to that given by FCTG(r) (p > 0.05). Thus, the mean FHR value obtained from the FPCG(e), is likely to be equivalent to the value given by the abdominal ECG, which is especially significant since the FPCG(e) is retrieved from the noisy abdominal phonogram. Hence, as far as this study has gone, it can be said that, when using SCICA to de-noise the abdominal phonogram, the resulting FPCG is likely to become a useful source for FHR collection in antenatal surveillance.

No influence of lower leg heating on central arterial pulse pressure in young men

Central arterial pulse pressure (PP), a strong predictor of cardiovascular disease, mainly consists of an incident wave generated by left ventricular ejection and a late-arriving reflected wave emanating from the lower body. We have tested the hypothesis that a reduction in leg vascular tone by heat treatment of the lower leg attenuates the central arterial PP. Pressure and wave properties of the peripheral and central arteries were measured in eight young men before and after heat treatment of the lower leg (temperature approx. 43 °C) for 30 and 60 min, respectively. Following the lower leg heat trial, leg (femoral-ankle) pulse wave velocity (PWV) was significantly decreased, but aortic (carotid-femoral) PWV and parameters of wave reflection and carotid arterial PP did not change significantly. No significant changes were observed in these parameters in the control trial. These results suggest that the reduction in leg vascular tone induced by heat treatment of the lower leg may not affect wave reflection and central arterial PP in young men.

Assessment of left ventricular function by noninvasive methods

The possibility of evaluating left ventricular function by noninvasive methods is discussed in detail. The methods that are considered are electrocardiograph, phonocardiography, apex cardiography, sphygmography, impedance cardiography, electrokymography, and echocardiography. Following a brief section of 'definitions', each method is described in detail including technical problems, difficulties, and results. The systolic time intervals and the stress tests are briefly discussed. Based on modern experimental studies, the stress test should include both an electro- and a phonocardiogram. In the latter, one would measure the amplitude of the first heart sound as an index of contractility. The conclusion is that combined methods give the best results. They are electrocardiography, phonocardiography, impedance cardiography, and echocardiography. An alternative, dictated by technical problems, is to use at first phonocardiography and impedance plus electrocardiography; then echocardiography plus electrocardiography; and then, if indicated, a stress test might complete the study; the latter should include both an electrocardiogram and a phonocardiogram.

Nonalcoholic fatty liver disease as a risk factor of arterial stiffness measured by the cardioankle vascular index

Nonalcoholic fatty liver disease (NAFLD) is associated with risk factors for cardiovascular disease. The cardioankle vascular index (CAVI), a new measure of arterial stiffness, was recently developed and is independent of blood pressure. We investigated whether NAFLD is associated with arterial stiffness as measured using the CAVI in an apparently healthy population.A total of 2954 subjects without any known liver diseases were enrolled. NAFLD was diagnosed via typical ultrasonography. The clinical characteristics examined included age, sex, body mass index (BMI), waist circumference (WC), and the levels of aspartate aminotransferase, alanine aminotransferase, total cholesterol, high-density lipoprotein-cholesterol, low-density lipoprotein-cholesterol triglycerides, and glucose. Arterial stiffness was defined using an age- and sex-specific threshold of the upper quartile of the CAVI.NAFLD was found in 1249 (42.3%) of the analyzed subjects. Using an age-, sex-, and BMI-adjusted model, NAFLD was associated with a 42% increase in the risk for arterial stiffness (highest quartile of the CAVI). The risk for arterial stiffness increased according to the severity of NAFLD (adjusted odds ratio [95% confidence interval], 1.27 [1.02 - 1.57] vs 1.78 [1.37 - 2.31], mild vs moderate-to-severe, respectively). When adjusted for other risk factors, including BMI, WC, smoking status, diabetes, and hypertension, these relationships remained statistically significant.Patients with NAFLD are at a high risk for arterial stiffness regardless of classical risk factors. The presence of cardiometabolic risk factors may attenuate the prediction of arterial stiffness by means of NAFLD presence. Thus, physicians should carefully assess subjects with NAFLD for atherosclerosis and associated comorbidities.