Heart Sound Classification Using Wavelet Analysis Approaches and Ensemble of Deep Learning Models

Analysis of PCG signals using quality assessment and homomorphic filters for localization and classification of heart sounds

Bowing gesture while playing violin refers to the motion of the violinist's arm.Violinists use different types of bow strokes to express musical phrases, played by the movement of the right arm holding the fiddle bow.Although the sound produced by each bow stroke is distinct, it can be difficult for new fiddlers to distinguish and recognize these bowing techniques.So, this paper presents a novel approach of an ensemble of multimodal deep learning models consisting of one Convolution Neural Network (CNN) and two Long Short-Term Memory (LSTM) models to classify into one of the five bowing classes: detaché , legato, martelé , spiccato and staccato.The dataset used consists of audio samples performed by 8 violinists along with the motion of their forearms measured using a Myo sensor device, to acquire 8-channels of Electromyogram (EMG) data and 13-channels of Inertial Measurement Unit (IMU) data.The audio features are extracted from audio excerpts and time domain features are extracted from EMG and IMU motion signals.These features are passed into an ensemble of deep learning models to make the final prediction using weighted voting.The proposed ensemble classifier was able to deliver optimal results with an overall accuracy of 99.5%, which is better than the previous studies that took only either audio or motion data into consideration.

Radiologists often face challenges in differentiating benign from malignant sacral bone lesions due to their similar imaging characteristics. This study aimed to develop an ensemble deep learning (DL) model that can preoperatively distinguish between benign and malignant sacral tumors using noncontrast computed tomography images. Preoperative sacral CT scans from 569 patients with confirmed sacral lesions were analyzed. Data from Center 1 were utilized in model development and internal test via fivefold cross-validation, and those from Centers 2 and 3 were employed in external test. Various ensemble models combining human-readable interpretation and DL were developed. The diagnostic performance of the models and radiologists was assessed using metrics such as precision, recall, accuracy, area under the curve (AUC), F1 score, and confusion matrix. Furthermore, the clinical benefits derived from radiologists' interpretations and supported by the DL model were evaluated. The ensemble model, which integrates 3D-DenseNet121 with human interpretation, exhibited the most robust performance. The ensemble model demonstrated high performance on the internal and external test sets and achieved AUCs of 0.9139 and 0.8713, F1 scores of 0.9054 and 0.8571, precision of 0.9041 and 0.8824, recall of 0.9136 and 0.8333, and accuracy of 0.8630 and 0.8182, respectively. Across the external test cohort, all radiologists experienced improvements in AUC, accuracy, sensitivity, and specificity. Notably, junior radiologists demonstrated significant improvements compared with senior radiologists. The potential clinical application of the DL model lies in its capacity to considerably enhance the diagnostic efficiency of radiologists. This study presents the first ensemble deep learning model integrating 3D-DenseNet121 with radiologists' interpretation for preoperative differentiation of sacral tumors on noncontrast CT that improved diagnostic performance across all experience levels, particularly for junior radiologists. First artificial intelligence-radiologist ensemble for noncontrast computed tomography (NCCT)-based sacral tumor classification. Boosts all radiologists' performance, with the greatest gains for juniors, potentially reducing referrals. Enables reliable NCCT diagnosis, overcoming contrast/magnetic resonance imaging dependency in musculoskeletal oncology.

Heart sounds convey important information regarding potential heart diseases. Currently, heart sound classification attracts many researchers from the fields of telemedicine, digital signal processing, and machine learning—among others—mainly to identify cardiac pathology as quickly as possible. This article proposes chaogram as a new transform to convert heart sound signals to colour images. In the proposed approach, the output image is, therefore, the projection of the reconstructed phase space representation of the phonocardiogram (PCG) signal on three coordinate planes. This has two major benefits: (1) it makes possible to apply deep convolutional neural networks to heart sounds and (2) it is also possible to employ a transfer learning scheme by converting a heart sound signal to an image. The performance of the proposed approach was verified on the PhysioNet dataset. Due to the imbalanced data on this dataset, it is common to assess the results quality using the average of sensitivity and specificity, which is known as score, instead of accuracy. In this study, the best results were achieved using the model, which achieved a score of 88.06%.

A Phonocardiogram (PCG) signal represents murmurs and sounds signals made by vibrations caused for the period of a cardiac cycle. Acoustic wave generated through the beat of the cardiac cycle propagates through the chest wall. It can be easily recorded by a low-cost small handheld digital device called a stethoscope. It provides information like heart rate, intensity, tone, quality, frequency, and location of various components of cardiac sound. Due to these characteristics, phonocardiogram signals can be used to detect heart status at an early stage in a non-invasive manner. In previous studies, the Convolutional Neural Network (ConvNet) is the most studied architecture, which was fed by features, namely Mel Frequency Cepstral (MFC), Chroma Energy Normalized Statistics (CENS), and Constant-Q Transform (CQT). This work has proposed a ConvNet model trained by Hybrid Constant-Q Transform (HCQT) for heart sound beat classification. CQT, Variable-Q Transform (VQT), and HCQT are extracted from each phonocardiogram signal as the acoustic features, including the dominant MFCC features, feed into five-layer regularized ConvNets. After analyzing the literature in the same domain, it can be stated that this is the first time HCQT is being utilized for PCG signals. The findings of the experiments demonstrate that HCQT is more effective than standard CQT and other variants. Also, the accuracies of the system proposed in this work on the validation datasets are 96% in multi-class classification, which outperforms the proposed work relative to other models significantly. The source code is available on the Github repository https://github.com/shamiktiwari/ PCG-signal-Classification-using-Hybrid-Constant-Q-Transform to support the research community.

The accuracy of shear wave elastography for non-invasive assessment of renal fibrosis (RF) in chronic kidney disease (CKD) needs further improvement. We developed a tool using an ensemble deep learning model (EDLM) that can accurately assess RF in CKD patients based solely on two-dimensional shear wave elastography (2D-SWE) images. Retrospective data were collected from CKD patients between April 2019 and October 2024, along with renal 2D-SWE images obtained before biopsy. Pathological evaluation was the reference standard of RF. All patients were randomly divided into training, validation, and test sets in a 7:1:2 ratio. An EDLM integrating three convolutional neural networks (ResNet18, DenseNet121, and EfficientNet-b7) through a voting strategy at the output level was developed and validated using 2D-SWE images. The diagnostic performance of the EDLM was compared with that of radiologists. A total of 286 CKD patients (mean age ± standard deviation: 41.86 ± 14.94, males: 162) and 858 2D-SWE images (mild RF: 405, moderate-severe RF: 453) were included. In the test set, EDLM achieved an accuracy of 93.0% (95% CI: 88.1, 95.9), negative predictive value of 89.6% (95% CI: 81.5, 94.5), positive predictive value of 96.4% (95% CI: 90.0, 98.8), specificity of 96.3% (95% CI: 89.7, 98.7), and sensitivity of 90.0% (95% CI: 82.1, 94.7). The area under the receiver operating characteristic curves of the EDLM was 0.989, surpassing experienced radiologist by 0.186 (P < 0.001) and less experienced radiologist by 0.279 (P < 0.001). EDLM based on 2D-SWE images significantly improved the diagnostic performance of RF in CKD. The EDLM was expected to be a potential tool for accurately non-invasive assessment of RF in CKD.

This paper is concerned with the analysis of the first (S1) and second (S2) heart sound of the Phonocardiogram signal (PCG) using Discrete Wavelet Transform (DWT) and Continuous Wavelet Transform (CWT). The second heart sound S2 consists of two major components A2 and P2. The time delay between them plays very vital role in medical diagnosis. DWT is used for denoising and finding the best split of A2 and P2 components of S2, where as, CWT is used to determine the number of frequency components of S1 and S2. Experiments are performed on normal and pathological PCG signals. Denoising and finding split between A2 and P2 is carried out using DWT. The frequency components of S1 and S2 of PCG are determined using CWT. Also split between A2 and P2 have been measured using CWT.

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/and 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.

This paper presents an automatic normal and abnormal heart sound classification model developed based on deep learning algorithm. MITHSDB heart sounds datasets obtained from the 2016 PhysioNet/Computing in Cardiology Challenge database were used in this research with the assumption that the electrocardiograms (ECG) were recorded simultaneously with the heart sounds (phonocardiogram, PCG). The PCG time series are segmented per heart beat, and each sub-segment is converted to form a square intensity matrix, and classified using convolutional neural network (CNN) models. This approach removes the need to provide classification features for the supervised machine learning algorithm. Instead, the features are determined automatically through training, from the time series provided. The result proves that the prediction model is able to provide reasonable and comparable classification accuracy despite simple implementation. This approach can be used for real-time classification of heart sounds in Internet of Medical Things (IoMT), e.g. remote monitoring applications of PCG signal.

Cardiovascular diseases (CVDs) are the leading cause of death, resulting in approximately 17.9 million deaths every year. Treatment of CVDs is most effective when detected early, creating a need for accurate and inexpensive pre-screening methods. Recently, deep learning has been explored to classify abnormal heart sounds indicative of CVDs using phonocardiogram (PCG) and electrocardiogram (ECG) signals. However, due to limited synchronised PCG and ECG data, state-of-the-art (SOTA) architectures, such as transformers, have not seen much use within this domain. This work explores the use of traditional signal processing, along with denoising diffusion models WaveGrad and DiffWave, to create an augmented dataset that is used to fine-tune a Wav2Vec 2.0-based classifier. The proposed methods achieve greater than state-of-the-art accuracy, unweighted average recall, sensitivity, specificity and Matthew's correlation coefficient of 93.14% and 92.21%, 93.35%, 90.10% and 0.838, respectively, in the Computing in Cardiology (CinC) 2016 training-a data which consists of synchronised PCG and ECG signals. These methods also achieved 92.98%, 92.48%, 93.63%, 92.48%, and 0.8238 when trained on all CinC databases utilising only PCG signals, which is also greater performance than SOTA methods. These results demonstrate the performance of fine-tuning self-supervised transformer-based models when trained on larger amounts of data, which an augmented dataset can supplement.

CardioPHON: Quality assessment and self-supervised pretraining for screening of cardiac function based on phonocardiogram recordings

Accurate interpretation of heart sounds remains a fundamental yet challenging task in the early diagnosis of cardiovascular diseases. Traditional auscultation relies heavily on clinical expertise, whereas automated approaches often struggle with signal variability, background noise, and overlapping murmurs that obscure vital diagnostic cues. Conventional machine learning methods rely on handcrafted features and fail to capture the intricate temporal–spectral dependencies inherent in phonocardiogram (PCG) signals. Deep learning models, though powerful, frequently lack interpretability and require large datasets, limiting their adoption in real-world clinical settings.To address these challenges, this paper presents MCAF-TabNet, an interpretable deep learning framework for heart sound classification. The model integrates a Multiscale Convolutional Encoder for hierarchical temporal–spectral feature extraction, a Channel Attention Module for adaptive channel reweighting, and a Feature Fusion Layer that combines deep representations with handcrafted acoustic descriptors. The fused features are processed by a TabNet Classifier, enabling sequential, attention-based feature selection and transparent decision-making. Experimental results on a benchmark PCG dataset demonstrate that the proposed framework achieves an accuracy of 98.42% and an AUC of 0.991, outperforming state-of-the-art CNN, CRNN, and attention-based architectures.The findings show that MCAF-TabNet effectively balances accuracy, interpretability, and robustness, overcoming the limitations of traditional models in noisy and data-limited conditions. Its transparent architecture not only enhances trust in automated diagnosis but also aligns closely with clinical decision-making principles. This work establishes MCAF-TabNet as a reliable foundation for intelligent, interpretable, and scalable cardiac auscultation systems, paving the way for practical deployment in telehealth and point-of-care diagnostics.

Most of the causes of death are related to cardiovascular disease. Heart sound classification plays a key role in the early detection of cardiovascular disease. The distinction between normal and abnormal heart sounds is not obvious, making heart sound classification a challenging task. This paper proposes a method based on statistical analysis and feature engineering to analyze the features extracted from heart sound signals. The discriminative features are selected and input into the classifier to classify the heart sound. While ensuring accuracy, the method reduces the scale of the input data and computational time for classification. The selected distinguishable features achieved an accuracy of 96.5 % for the classification of abnormal and normal heart sounds. The experimental results show that the selected features can achieve a high accuracy rate in the classification of heart sound, which is suitable for real-time applications.

An ensemble deep learning model for exhaust emissions prediction of heavy oil-fired boiler combustion

The potential of generalized deep learning models developed for crop water estimation was examined in the current study. This study was conducted in a semiarid region of India, i.e., Karnataka, with daily climatic data (maximum and minimum air temperatures, maximum and minimum relative humidity, wind speed, sunshine hours, and rainfall) of 44 years (1976–2020) for twelve locations. The Extreme Gradient Boosting (XGBoost), Gradient Boosting (GB), and Random Forest (RF) are three ensemble deep learning models that were developed using all of the climatic data from a single location (Bengaluru) from January 1976 to December 2017 and then immediately applied at eleven different locations (Ballari, Chikmaglur, Chitradurga, Devnagiri, Dharwad, Gadag, Haveri, Koppal, Mandya, Shivmoga, and Tumkuru) without the need for any local calibration. For the test period of January 2018–June 2020, the model’s capacity to estimate the numerical values of crop water requirement (Penman-Monteith (P-M) ETo values) was assessed. The developed ensemble deep learning models were evaluated using the performance criteria of mean absolute error (MAE), average absolute relative error (AARE), coefficient of correlation (r), noise to signal ratio (NS), Nash–Sutcliffe efficiency (ɳ), and weighted standard error of estimate (WSEE). The results indicated that the WSEE values of RF, GB, and XGBoost models for each location were smaller than 1 mm per day, and the model’s effectiveness varied from 96% to 99% across various locations. While all of the deep learning models performed better with respect to the P-M ETo approach, the XGBoost model was able to estimate ETo with greater accuracy than the GB and RF models. The XGBoost model’s strong performance was also indicated by the decreased noise-to-signal ratio. Thus, in this study, a generalized mathematical model for short-term ETo estimates is developed using ensemble deep learning techniques. Because of this type of model’s accuracy in calculating crop water requirements and its ability for generalization, it can be effortlessly integrated with a real-time water management system or an autonomous weather station at the regional level.