Gated recurrent unit-based heart sound analysis for heart failure screening

PCGmix: A Data-Augmentation Method for Heart-Sound Classification

Cardiovascular diseases (CVDs) are a leading cause of mortality worldwide, responsible for 32% of all deaths, with the annual death toll projected to reach 23.3 million by 2030. The early identification of individuals at high risk of CVD is crucial for the effectiveness of preventive strategies. In the field of deep learning, automated CVD-detection methods have gained traction, with phonocardiogram (PCG) data emerging as a valuable resource. However, deep-learning models rely on large datasets, which are often challenging to obtain. In recent years, data augmentation has become a viable solution to the problem of scarce data. In this paper, we propose a novel data-augmentation technique named PCGmix, specifically engineered for the augmentation of PCG data. The PCGmix algorithm employs a process of segmenting and reassembling PCG recordings, incorporating meticulous interpolation to ensure the preservation of the cardinal diagnostic features pertinent to CVD detection. The empirical assessment of the PCGmix method was utilized on a publicly available database of normal and abnormal heart-sound recordings. To evaluate the impact of data augmentation across a range of dataset sizes, we conducted experiments encompassing both limited and extensive amounts of training data. The experimental results demonstrate that the novel method is superior to the compared state-of-the-art, time-series augmentation. Notably, on limited data, our method achieves comparable accuracy to the no-augmentation approach when trained on 31% to 69% larger datasets. This study suggests that PCGmix can enhance the accuracy of deep-learning models for CVD detection, especially in data-constrained environments.

Optimizing extubation success: a comparative analysis of time series algorithms and activation functions

Background

The success and failure of extubation of patients with acute respiratory failure is a very important issue for clinicians, and the failure of the ventilator often leads to possible complications, which in turn leads to a lot of doubts about the medical treatment in the minds of the people, so in order to increase the success of extubation success of the doctors to prevent the possible complications, the present study compared different time series algorithms and different activation functions for the training and prediction of extubation success or failure models.

Methods

This study compared different time series algorithms and different activation functions for training and predicting the success or failure of the extubation model.

Results

The results of this study using four validation methods show that the GRU model and Tanh's model have a better predictive model for predicting the success or failure of the extubation and better predictive result of 94.44% can be obtained using Holdout cross-validation validation method.

Conclusion

This study proposes a prediction method using GRU on the topic of extubation, and it can provide the doctors with the clinical application of extubation to give advice for reference.

A gated recurrent unit model based on ultrasound images of dynamic tongue movement for determining the severity of obstructive sleep apnea

Obstructive sleep apnea (OSA) presents as a respiratory disorder characterized by recurrent upper pharyngeal airway collapse during sleep. Dynamic tongue movement (DTM) analysis emerges as a promising avenue for elucidating the pathophysiological underpinnings of OSA, thereby facilitating its diagnosis. Recent endeavors have utilized artificial intelligence techniques to categorize OSA severity leveraging electrocardiography and blood oxygen saturation data. Nonetheless, the integration of ultrasound (US) imaging of the tongue remains largely untapped in the development of machine learning models aimed at determining the severity of OSA. This study endeavors to bridge this gap by capturing US images of DTM dynamics during wakefulness, encompassing transitions from normal breathing (NB) to the performance of the Müller maneuver (MM) in a cohort of 53 patients. Leveraging the modified optical flow method (MOFM), the trajectories of patients' DTM were tracked, facililtating the extraction of 27 parameters vital for model training. These parameters encompassed nine-point lateral movement, nine-point axial movement, and nine-point total displacement of the tongue, resulting in a dataset of 186,030 samples. The gated recurrent unit (GRU) method, renowned for its efficacy in motion tracking, was employed for model development in this study. Validation of the developed model was conducted via stratified k-fold cross-validation (SCV). The systems' overall performance in classifying OSA severity, as quantified by mean accuracy (MA), yielded a value of 43.49%. This pilot investigation marks an exploratory endeavor into the utilization of artificial intelligence for the classification of OSA severity based on US images and dynamic movement patterns. This novel model holds potential to assist clinicians in categorizing OSA severity and guiding the selection of pertinent treatment modalities tailored to the individual needs of patients afflicted with OSA.

Recent advancements and applications of deep learning in heart failure: Α systematic review

BACKGROUND

Heart failure (HF), a global health challenge, requires innovative diagnostic and management approaches. The rapid evolution of deep learning (DL) in healthcare necessitates a comprehensive review to evaluate these developments and their potential to enhance HF evaluation, aligning clinical practices with technological advancements.

OBJECTIVE

This review aims to systematically explore the contributions of DL technologies in the assessment of HF, focusing on their potential to improve diagnostic accuracy, personalize treatment strategies, and address the impact of comorbidities.

METHODS

A thorough literature search was conducted across four major electronic databases: PubMed, Scopus, Web of Science and IEEE Xplore, yielding 137 articles that were subsequently categorized into five primary application areas: cardiovascular disease (CVD) classification, HF detection, image analysis, risk assessment, and other clinical analyses. The selection criteria focused on studies utilizing DL algorithms for HF assessment, not limited to HF detection but extending to any attempt in analyzing and interpreting HF-related data.

RESULTS

The analysis revealed a notable emphasis on CVD classification and HF detection, with DL algorithms showing significant promise in distinguishing between affected individuals and healthy subjects. Furthermore, the review highlights DL's capacity to identify underlying cardiomyopathies and other comorbidities, underscoring its utility in refining diagnostic processes and tailoring treatment plans to individual patient needs.

CONCLUSIONS

This review establishes DL as a key innovation in HF management, highlighting its role in advancing diagnostic accuracy and personalized care. The insights provided advocate for the integration of DL in clinical settings and suggest directions for future research to enhance patient outcomes in HF care.

[Research on bark-frequency spectral coefficients heart sound classification algorithm based on multiple window time-frequency reassignment]

The multi-window time-frequency reassignment helps to improve the time-frequency resolution of bark-frequency spectral coefficient (BFSC) analysis of heart sounds. For this purpose, a new heart sound classification algorithm combining feature extraction based on multi-window time-frequency reassignment BFSC with deep learning was proposed in this paper. Firstly, the randomly intercepted heart sound segments are preprocessed with amplitude normalization, the heart sounds were framed and time-frequency rearrangement based on short-time Fourier transforms were computed using multiple orthogonal windows. A smooth spectrum estimate is calculated by arithmetic averaging each of the obtained independent spectra. Finally, the BFSC of reassignment spectrum is extracted as a feature by the Bark filter bank. In this paper, convolutional network and recurrent neural network are used as classifiers for model comparison and performance evaluation of the extracted features. Eventually, the multi-window time-frequency rearrangement improved BFSC method extracts more discriminative features, with a binary classification accuracy of 0.936, a sensitivity of 0.946, and a specificity of 0.922. These results present that the algorithm proposed in this paper does not need to segment the heart sounds and randomly intercepts the heart sound segments, which greatly simplifies the computational process and is expected to be used for screening of congenital heart disease.

Applications of deep learning models in precision prediction of survival rates for heart failure patients

BACKGROUND

Heart failure poses a significant challenge in the global health domain, and accurate prediction of mortality is crucial for devising effective treatment plans. In this study, we employed a Seq2Seq model from deep learning, integrating 12 patient features. By finely modeling continuous medical records, we successfully enhanced the accuracy of mortality prediction.

OBJECTIVE

The objective of this research was to leverage the Seq2Seq model in conjunction with patient features for precise mortality prediction in heart failure cases, surpassing the performance of traditional machine learning methods.

METHODS

The study utilized a Seq2Seq model in deep learning, incorporating 12 patient features, to intricately model continuous medical records. The experimental design aimed to compare the performance of Seq2Seq with traditional machine learning methods in predicting mortality rates.

RESULTS

The experimental results demonstrated that the Seq2Seq model outperformed conventional machine learning methods in terms of predictive accuracy. Feature importance analysis provided critical patient risk factors, offering robust support for formulating personalized treatment plans.

CONCLUSIONS

This research sheds light on the significant applications of deep learning, specifically the Seq2Seq model, in enhancing the precision of mortality prediction in heart failure cases. The findings present a valuable direction for the application of deep learning in the medical field and provide crucial insights for future research and clinical practices.

[Heart sound classification based on improved mel frequency cepstrum coefficient and integrated decision network method]

Heart sound analysis is significant for early diagnosis of congenital heart disease. A novel method of heart sound classification was proposed in this paper, in which the traditional mel frequency cepstral coefficient (MFCC) method was improved by using the Fisher discriminant half raised-sine function (F-HRSF) and an integrated decision network was used as classifier. It does not rely on segmentation of the cardiac cycle. Firstly, the heart sound signals were framed and windowed. Then, the features of heart sounds were extracted by using improved MFCC, in which the F-HRSF was used to weight sub-band components of MFCC according to the Fisher discriminant ratio of each sub-band component and the raised half sine function. Three classification networks, convolutional neural network (CNN), long and short-term memory network (LSTM), and gated recurrent unit (GRU) were combined as integrated decision network. Finally, the two-category classification results were obtained through the majority voting algorithm. An accuracy of 92.15%, sensitivity of 91.43%, specificity of 92.83%, corrected accuracy of 92.01%, and F score of 92.13% were achieved using the novel signal processing techniques. It shows that the algorithm has great potential in early diagnosis of congenital heart disease.

Development and Validation of a Dynamic Prediction Model for Massive Hemorrhage in Trauma

Objectives

Early warning prediction of massive hemorrhages can greatly reduce mortality in trauma patients. This study aimed to develop and validate dynamic prediction models for massive hemorrhage in trauma patients.

Methods

Based on vital signs (e.g., heart rate, respiratory rate, pulse pressure, and peripheral oxygen saturation) time-series data and the gated recurrent unit algorithm, we characterized a group of models to flexibly and dynamically predict the occurrence of massive hemorrhages in the subsequent T hours (where T = 1, 2, and 3). Models were evaluated in terms of accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 score, and the area under the curve (AUC).

Results

Results show that of the 2205 trauma patients selected for model development, a total of 265 (12.02%) had a massive hemorrhage. The AUCs of the model in the 1-h-group, 2-h-group, and 3-h-group were 0.763 (95% CI: 0.708-0.820), 0.775 (95% CI: 0.728-0.823), and 0.756 (95% CI: 0.715-0.797), respectively. Finally, the models were used in a web calculator and information system for the hospital emergency department.

Conclusions

This study developed and validated a group of dynamic prediction models based on vital sign time-series data and a deep-learning algorithm to assist medical staff in the early diagnosis and dynamic prediction of a future massive hemorrhage in trauma.

Association between phonocardiography and echocardiography in heart failure patients with preserved ejection fraction

Aims

Heart failure with preserved ejection fraction (HFpEF) is associated with stiffened myocardium and elevated filling pressure that may be captured by heart sound (HS). We investigated the relationship between phonocardiography (PCG) and echocardiography in symptomatic patients suspected of HFpEF.

Methods and results

Consecutive symptomatic patients with sinus rhythm and left ventricular ejection fraction >45% were enrolled. Echocardiography was performed to evaluate the patients' diastolic function, accompanied by PCG measurements. Phonocardiography features including HS amplitude, frequency, and timing intervals were calculated, and their abilities to differentiate the ratio between early mitral inflow velocity and early diastolic mitral annular velocity (E/e') were investigated. Of 45 patients, variable ratio matching was applied to obtain two groups of patients with similar characteristics but different E/e'. Patients with a higher E/e' showed higher first and second HS frequencies and more fourth HS and longer systolic time intervals. The interval from QRS onset to first HS was the best feature for the prediction of E/e' > 9 [area under the curve (AUC): 0.72 (0.51-0.88)] in the matched patients. In comparison, N-terminal pro-brain natriuretic peptide (NT-proBNP) showed an AUC of 0.67 (0.46-0.85), a value not better than any PCG feature (P > 0.05).

Conclusion

Phonocardiography features stratify E/e' in symptomatic patients suspected of HFpEF with a diagnostic performance similar to NT-proBNP. Heart sound may serve as a simple non-invasive tool for evaluating HFpEF patients.

Identification of decompensation episodes in chronic heart failure patients based solely on heart sounds

Decompensation episodes in chronic heart failure patients frequently result in unplanned outpatient or emergency room visits or even hospitalizations. Early detection of these episodes in their pre-symptomatic phase would likely enable the clinicians to manage this patient cohort with the appropriate modification of medical therapy which would in turn prevent the development of more severe heart failure decompensation thus avoiding the need for heart failure-related hospitalizations. Currently, heart failure worsening is recognized by the clinicians through characteristic changes of heart failure-related symptoms and signs, including the changes in heart sounds. The latter has proven to be largely unreliable as its interpretation is highly subjective and dependent on the clinicians’ skills and preferences. Previous studies have indicated that the algorithms of artificial intelligence are promising in distinguishing the heart sounds of heart failure patients from those of healthy individuals. In this manuscript, we focus on the analysis of heart sounds of chronic heart failure patients in their decompensated and recompensated phase. The data was recorded on 37 patients using two types of electronic stethoscopes. Using a combination of machine learning approaches, we obtained up to 72% classification accuracy between the two phases, which is better than the accuracy of the interpretation by cardiologists, which reached 50%. Our results demonstrate that machine learning algorithms are promising in improving early detection of heart failure decompensation episodes.

Effective features extraction by analyzing heart sound for identifying cardiovascular diseases related to COVID-19: A diagnostic model

Incidence and exacerbation of some of the cardiovascular diseases in the presence of the coronavirus will lead to an increase in the mortality rate among patients. Therefore, early diagnosis of such diseases is critical, especially during the COVID-19 pandemic (mild COVID-19 infection). Thus, for diagnosing the heart diseases related to the COVID-19, an automatic, non-invasive, and inexpensive method based on the heart sound processing approach is proposed. In the present study, a set of features related to the nature of heart signals is defined and extracted. The investigated features included morphological and statistical features in the heart sound frequencies. By extracting and selecting a set of effective features related to the mentioned diseases, and avoiding to use different segmentation and filtering techniques, dependence on a limited dataset and specific sampling procedures has been eliminated. Different classifiers with various kernels are applied for diagnosis in data unbalanced and balanced conditions. The results showed 93.15% accuracy and 93.72% F1-score using 60 effective features in data balanced conditions. The identification system using the extracted features from Azad dataset is able to achieve the desired results in a generalized dataset. In this way, in the shortest possible sampling time, the present system provided an effective and generalizable method and a practical model for diagnosing important cardiovascular diseases in the presence of coronavirus in the COVID-19 pandemic.

Korotkoff sounds dynamically reflect changes in cardiac function based on deep learning methods

Korotkoff sounds (K-sounds) have been around for over 100 years and are considered the gold standard for blood pressure (BP) measurement. K-sounds are also unique for the diagnosis and treatment of cardiovascular diseases; however, their efficacy is limited. The incidences of heart failure (HF) are increasing, which necessitate the development of a rapid and convenient pre-hospital screening method. In this review, we propose a deep learning (DL) method and the possibility of using K-methods to predict cardiac function changes for the detection of cardiac dysfunctions.

A multimodal parallel method for left ventricular dysfunction identification based on phonocardiogram and electrocardiogram signals synchronous analysis

Heart failure (HF) is widely acknowledged as the terminal stage of cardiac disease and represents a global clinical and public health problem. Left ventricular ejection fraction (LVEF) measured by echocardiography is an important indicator of HF diagnosis and treatment. Early identification of LVEF reduction and early treatment is of great significance to improve LVEF and the prognosis of HF. This research aims to introduce a new method for left ventricular dysfunction (LVD) identification based on phonocardiogram (ECG) and electrocardiogram (PCG) signals synchronous analysis. In the present study, we established a database called Synchronized ECG and PCG Database for Patients with Left Ventricular Dysfunction (SEP-LVDb) consisting of 1046 synchronous ECG and PCG recordings from patients with reduced (n = 107) and normal (n = 699) LVEF. 173 and 873 recordings were available from the reduced and normal LVEF group, respectively. Then, we proposed a parallel multimodal method for LVD identification based on synchronous analysis of PCG and ECG signals. Two-layer bidirectional gate recurrent unit (Bi-GRU) was used to extract features in the time domain, and the data were classified using residual network 18 (ResNet-18). This research confirmed that fused ECG and PCG signals yielded better performance than ECG or PCG signals alone, with an accuracy of 93.27%, precision of 93.34%, recall of 93.27%, and F1-score of 93.27%. Verification of the model's performance with an independent dataset achieved an accuracy of 80.00%, precision of 79.38%, recall of 80.00% and F1-score of 78.67%. The Bi-GRU model outperformed Bi-directional long short-term memory (Bi-LSTM) and recurrent neural network (RNN) models with a best selection frame length of 3.2 s. The Saliency Maps showed that SEP-LVDPN could effectively learn features from the data.

A multi-scale and multi-domain heart sound feature-based machine learning model for ACC/AHA heart failure stage classification

OBJECTIVE

Heart sounds can reflect detrimental changes in cardiac mechanical activity that are common pathological characteristics of chronic heart failure (CHF). The ACC/AHA heart failure (HF) stage classification is essential for clinical decision-making and the management of CHF. Herein, a machine learning model that makes use of multi-scale and multi-domain heart sound features was proposed to provide an objective aid for ACC/AHA HF stage classification.

APPROACH

A dataset containing phonocardiogram (PCG) signals from 275 subjects was obtained from two medical institutions and used in this study. Complementary ensemble empirical mode decomposition and tunable-Q wavelet transform were used to construct self-adaptive sub-sequences and multi-level sub-band signals for PCG signals. Time-domain, frequency-domain and nonlinear feature extraction were then applied to the original PCG signal, heart sound sub-sequences and sub-band signals to construct multi-scale and multi-domain heart sound features. The features selected via the least absolute shrinkage and selection operator were fed into a machine learning classifier for ACC/AHA HF stage classification. Finally, mainstream machine learning classifiers, including least-squares support vector machine (LS-SVM), deep belief network (DBN) and random forest (RF), were compared to determine the optimal model.

MAIN RESULTS

The results showed that the LS-SVM, which utilized a combination of multi-scale and multi-domain features, achieved better classification performance than the DBN and RF using multi-scale or multi-domain features alone or together, with average sensitivity, specificity, and accuracy of 0.821, 0.955 and 0.820 on the testing set, respectively.

SIGNIFICANCE

PCG signal analysis provides efficient measurement information regarding CHF severity and is a promising noninvasive method for ACC/AHA HF stage classification.

An automatic approach for heart failure typing based on heart sounds and convolutional recurrent neural networks

Heart failure (HF) is a complex clinical syndrome that poses a major hazard to human health. Patients with different types of HF have great differences in pathogenesis and treatment options. Therefore, HF typing is of great significance for timely treatment of patients. In this paper, we proposed an automatic approach for HF typing based on heart sounds (HS) and convolutional recurrent neural networks, which provides a new non-invasive and convenient way for HF typing. Firstly, the collected HS signals were preprocessed with adaptive wavelet denoising. Then, the logistic regression based hidden semi-Markov model was utilized to segment HS frames. For the distinction between normal subjects and the HF patients with preserved ejection fraction or reduced ejection fraction, a model based on convolutional neural network and recurrent neural network was built. The model can automatically learn the spatial and temporal characteristics of HS signals. The results show that the proposed model achieved a superior performance with an accuracy of 97.64%. This study suggests the proposed method could be a useful tool for HF recognition and as a supplement for HF typing.

Decision Support Systems in HF based on Deep Learning Technologies

Purpose of Review

Application of deep learning (DL) is growing in the last years, especially in the healthcare domain. This review presents the current state of DL techniques applied to electronic health record structured data, physiological signals, and imaging modalities for the management of heart failure (HF), focusing in particular on diagnosis, prognosis, and re-hospitalization risk, to explore the level of maturity of DL in this field.

Recent Findings

DL allows a better integration of different data sources to distillate more accurate outcomes in HF patients, thus resulting in better performance when compared to conventional evaluation methods. While applications in image and signal processing for HF diagnosis have reached very high performance, the application of DL to electronic health records and its multisource data for prediction could still be improved, despite the already promising results.

Summary

Embracing the current big data era, DL can improve performance compared to conventional techniques and machine learning approaches. DL algorithms have potential to provide more efficient care and improve outcomes of HF patients, although further investigations are needed to overcome current limitations, including results generalizability and transparency and explicability of the evidences supporting the process.

Deep Learning-Based Heart Sound Analysis for Left Ventricular Diastolic Dysfunction Diagnosis

The aggravation of left ventricular diastolic dysfunction (LVDD) could lead to ventricular remodeling, wall stiffness, reduced compliance, and progression to heart failure with a preserved ejection fraction. A non-invasive method based on convolutional neural networks (CNN) and heart sounds (HS) is presented for the early diagnosis of LVDD in this paper. A deep convolutional generative adversarial networks (DCGAN) model-based data augmentation (DA) method was proposed to expand a HS database of LVDD for model training. Firstly, the preprocessing of HS signals was performed using the improved wavelet denoising method. Secondly, the logistic regression based hidden semi-Markov model was utilized to segment HS signals, which were subsequently converted into spectrograms for DA using the short-time Fourier transform (STFT). Finally, the proposed method was compared with VGG-16, VGG-19, ResNet-18, ResNet-50, DenseNet-121, and AlexNet in terms of performance for LVDD diagnosis. The result shows that the proposed method has a reasonable performance with an accuracy of 0.987, a sensitivity of 0.986, and a specificity of 0.988, which proves the effectiveness of HS analysis for the early diagnosis of LVDD and demonstrates that the DCGAN-based DA method could effectively augment HS data.

Prediction of exercise sudden death in rabbit exhaustive swimming using deep neural network

Background and objective

Moderate exercise contributes to good health. However, excessive exercise may lead to cardiac fatigue, myocardial damage and even exercise sudden death. Monitoring the heart health has important implication to prevent exercise sudden death. Diagnosis methods such as electrocardiogram, echocardiogram, blood pressure and histological analysis have shown that arrhythmia and left ventricular fibrosis are early warning symptoms of exercise sudden death. Heart sounds (HS) can reflect the changes of cardiac valve, cardiac blood flow and myocardial function. Deep learning has drawn wide attention because of its ability to recognize disease. Therefore, a deep learning method combined with HS was proposed to predict exercise sudden death in New Zealand rabbits. The objective is to develop a method to predict exercise sudden death in New Zealand rabbits.

Methods

This paper proposed a method to predict exercise sudden death in New Zealand rabbits based on convolutional neural network (CNN) and gated recurrent unit (GRU). The weight-bearing exhaustive swimming experiment was conducted to obtain the HS of exercise sudden death and surviving New Zealand rabbits (n = 11/10) at four different time points. Then, the improved Viola integral method and double threshold method were employed to segment HS signals. The segmented HS frames at different time points were taken as the input of a combined CNN and GRU called CNN–GRU network to complete the prediction of exercise sudden death.

Results

In order to evaluate the performance of proposed network, CNN and GRU were used for comparison. When the fourth time point segmented HS frames were taken as input, the result shows that the proposed network has better performance with an accuracy of 89.57%, a sensitivity of 89.38% and a specificity of 92.20%. In addition, the segmented HS frames at different time points were input into CNN–GRU network, and the result shows that with the progress of the experiment, the prediction accuracy of exercise sudden death in New Zealand rabbits increased from 50.98 to 89.57%.

Conclusion

The proposed network shows good performance in classifying HS, which proves the feasibility of deep learning in exploring exercise sudden death. Further, it may have important implications in helping humans explore exercise sudden death.