Electronic Stethoscope Filtering Mimics the Perceived Sound Characteristics of Acoustic Stethoscope

Exploring classical machine learning for identification of pathological lung auscultations

The use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to expand this body of knowledge by applying machine learning to pulmonary auscultation signals. Despite improvements in digital stethoscopes and attempts to find synergy between them and artificial intelligence, solutions for their use in clinical settings remain scarce. Physicians continue to infer initial diagnoses with less sophisticated means, resulting in low accuracy, leading to suboptimal patient care. To arrive at a correct preliminary diagnosis, the auscultation diagnostics need to be of high accuracy. Due to the large number of auscultations performed, data availability opens up opportunities for more effective sound analysis. In this study, digital 6-channel auscultations of 45 patients were used in various machine learning scenarios, with the aim of distinguishing between normal and abnormal pulmonary sounds. Audio features (such as fundamental frequencies F0-4, loudness, HNR, DFA, as well as descriptive statistics of log energy, RMS and MFCC) were extracted using the Python library Surfboard. Windowing, feature aggregation, and concatenation strategies were used to prepare data for machine learning algorithms in unsupervised (fair-cut forest, outlier forest) and supervised (random forest, regularized logistic regression) settings. The evaluation was carried out using 9-fold stratified cross-validation repeated 30 times. Decision fusion by averaging the outputs for a subject was also tested and found to be helpful. Supervised models showed a consistent advantage over unsupervised ones, with random forest achieving a mean AUC ROC of 0.691 (accuracy 71.11%, Kappa 0.416, F1-score 0.675) in side-based detection and a mean AUC ROC of 0.721 (accuracy 68.89%, Kappa 0.371, F1-score 0.650) in patient-based detection.

Deep learning-based lung sound analysis for intelligent stethoscope

Auscultation is crucial for the diagnosis of respiratory system diseases. However, traditional stethoscopes have inherent limitations, such as inter-listener variability and subjectivity, and they cannot record respiratory sounds for offline/retrospective diagnosis or remote prescriptions in telemedicine. The emergence of digital stethoscopes has overcome these limitations by allowing physicians to store and share respiratory sounds for consultation and education. On this basis, machine learning, particularly deep learning, enables the fully-automatic analysis of lung sounds that may pave the way for intelligent stethoscopes. This review thus aims to provide a comprehensive overview of deep learning algorithms used for lung sound analysis to emphasize the significance of artificial intelligence (AI) in this field. We focus on each component of deep learning-based lung sound analysis systems, including the task categories, public datasets, denoising methods, and, most importantly, existing deep learning methods, i.e., the state-of-the-art approaches to convert lung sounds into two-dimensional (2D) spectrograms and use convolutional neural networks for the end-to-end recognition of respiratory diseases or abnormal lung sounds. Additionally, this review highlights current challenges in this field, including the variety of devices, noise sensitivity, and poor interpretability of deep models. To address the poor reproducibility and variety of deep learning in this field, this review also provides a scalable and flexible open-source framework that aims to standardize the algorithmic workflow and provide a solid basis for replication and future extension: https://github.com/contactless-healthcare/Deep-Learning-for-Lung-Sound-Analysis .

A wearable nanoscale heart sound sensor based on P(VDF-TrFE)/ZnO/GR and its application in cardiac disease detection

This paper describes a method for preparing flexible composite piezoelectric nanofilms of P(VDF-TrFE)/ZnO/graphene using a high-voltage electrospinning method. Composition and β-phase content of the piezoelectric composite films were analyzed using X-ray diffraction. The morphology of the composite film fibers was observed through scanning electron microscopy. Finally, the P(VDF-TrFE)/ZnO/graphene composite film was encapsulated in a sandwich-structure heart sound sensor, and a visual heart sound acquisition and classification system was designed using LabVIEW. A heart sound classification model was trained based on a fine K-nearest neighbor classification algorithm to predict whether the collected heart sounds are normal or abnormal. The heart sound detection system designed in this paper can collect heart sound signals in real time and predict whether the heart sounds are normal or abnormal, providing a new solution for the diagnosis of heart diseases.

Constrained Synthetic Sampling for Augmentation of Crackle Lung Sounds

Crackles are explosive breathing patterns caused by lung air sacs filling with fluid and act as an indicator for a plethora of pulmonary diseases. Clinical studies suggest a strong correlation between the presence of these adventitious auscultations and mortality rate, especially in pediatric patients, underscoring the importance of their pathological indication. While clinically important, crackles occur rarely in breathing signals relative to other phases and abnormalities of lung sounds, imposing a considerable class imbalance in developing learning methodologies for automated tracking and diagnosis of lung pathologies. The scarcity and clinical relevance of crackle sounds compel a need for exploring data augmentation techniques to enrich the space of crackle signals. Given their unique nature, the current study proposes a crackle-specific constrained synthetic sampling (CSS) augmentation that captures the geometric properties of crackles across different projected object spaces. We also outline a task-agnostic validation methodology that evaluates different augmentation techniques based on their goodness of fit relative to the space of original crackles. This evaluation considers both the separability of the manifold space generated by augmented data samples as well as a statistical distance space of the synthesized data relative to the original. Compared to a range of augmentation techniques, the proposed constrained-synthetic sampling of crackle sounds is shown to generate the most analogous samples relative to original crackle sounds, highlighting the importance of carefully considering the statistical constraints of the class under study.

Multi-Transduction-Mechanism Technology, an Emerging Approach to Enhance Sensor Performance

Conventional sensor systems employ single-transduction technology where they respond to an input stimulus and transduce the measured parameter into a readable output signal. As such, the technology can only provide limited corresponding data of the detected parameters due to relying on a single transformed output signal for information acquisition. This limitation commonly results in the need for utilizing sensor array technology to detect targeted parameters in complex environments. Multi-transduction-mechanism technology, on the other hand, may combine more than one transduction mechanism into a single structure. By employing this technology, sensors can be designed to simultaneously distinguish between different input signals from complex environments for greater degrees of freedom. This allows a multi-parameter response, which results in an increased range of detection and improved signal-to-noise ratio. In addition, utilizing a multi-transduction-mechanism approach can achieve miniaturization by reducing the number of required sensors in an array, providing further miniaturization and enhanced performance. This paper introduces the concept of multi-transduction-mechanism technology by exploring different candidate combinations of fundamental transduction mechanisms such as piezoresistive, piezoelectric, triboelectric, capacitive, and inductive mechanisms.

Review on the Advancements of Stethoscope Types in Chest Auscultation

Stethoscopes were originally designed for the auscultation of a patient's chest for the purpose of listening to lung and heart sounds. These aid medical professionals in their evaluation of the cardiovascular and respiratory systems, as well as in other applications, such as listening to bowel sounds in the gastrointestinal system or assessing for vascular bruits. Listening to internal sounds during chest auscultation aids healthcare professionals in their diagnosis of a patient's illness. We performed an extensive literature review on the currently available stethoscopes specifically for use in chest auscultation. By understanding the specificities of the different stethoscopes available, healthcare professionals can capitalize on their beneficial features, to serve both clinical and educational purposes. Additionally, the ongoing COVID-19 pandemic has also highlighted the unique application of digital stethoscopes for telemedicine. Thus, the advantages and limitations of digital stethoscopes are reviewed. Lastly, to determine the best available stethoscopes in the healthcare industry, this literature review explored various benchmarking methods that can be used to identify areas of improvement for existing stethoscopes, as well as to serve as a standard for the general comparison of stethoscope quality. The potential use of digital stethoscopes for telemedicine amidst ongoing technological advancements in wearable sensors and modern communication facilities such as 5G are also discussed. Based on the ongoing trend in advancements in wearable technology, telemedicine, and smart hospitals, understanding the benefits and limitations of the digital stethoscope is an essential consideration for potential equipment deployment, especially during the height of the current COVID-19 pandemic and, more importantly, for future healthcare crises when human and resource mobility is restricted.

Regularity and mechanism of fake crackle noise in an electronic stethoscope

Background: Electronic stethoscopes are widely used for cardiopulmonary auscultation; their audio recordings are used for the intelligent recognition of cardiopulmonary sounds. However, they generate noise similar to a crackle during use, significantly interfering with clinical diagnosis. This paper will discuss the causes, characteristics, and occurrence rules of the fake crackle and establish a reference for improving the reliability of the electronic stethoscope in lung auscultation. Methods: A total of 56 participants with healthy lungs (no underlying pulmonary disease, no recent respiratory symptoms, and no adventitious lung sound, as confirmed by an acoustic stethoscope) were enrolled in this study. A 30-s audio recording was recorded from each of the nine locations of the larynx and lungs of each participant with a 3M Littmann 3200 electronic stethoscope, and the audio was output in diaphragm mode and auscultated by the clinician. The doctor identified the fake crackles and analyzed their frequency spectrum. High-pass and low-pass filters were used to detect the frequency distribution of the fake crackles. Finally, the fake crackle was artificially regenerated to explore its causes. Results: A total of 500 audio recordings were included in the study, with 61 fake crackle audio recordings. Fake crackles were found predominantly in the lower lung. There were significant differences between lower lung and larynx (p < 0.001), lower lung and upper lung (p = 0.005), lower lung and middle lung (p = 0.005), and lower lung and infrascapular region (p = 0.027). Furthermore, more than 90% of fake crackles appeared in the inspiratory phase, similar to fine crackles, significantly interfering with clinical diagnosis. The spectral analysis revealed that the frequency range of fake crackles was approximately 250-1950 Hz. The fake crackle was generated when the diaphragm of the electronic stethoscope left the skin slightly but not completely. Conclusion: Fake crackles are most likely to be heard when using an electronic stethoscope to auscultate bilateral lower lungs, and the frequency of a fake crackle is close to that of a crackle, likely affecting the clinician's diagnosis.

Cardiac anomaly detection considering an additive noise and convolutional distortion model of heart sound recordings

Cardiac auscultation is an essential point-of-care method used for the early diagnosis of heart diseases. Automatic analysis of heart sounds for abnormality detection is faced with the challenges of additive noise and sensor-dependent degradation. This paper aims to develop methods to address the cardiac abnormality detection problem when both of these components are present in the cardiac auscultation sound. We first mathematically analyze the effect of additive noise and convolutional distortion on short-term mel-filterbank energy-based features and a Convolutional Neural Network (CNN) layer. Based on the analysis, we propose a combination of linear and logarithmic spectrogram-image features. These 2D features are provided as input to a residual CNN network (ResNet) for heart sound abnormality detection. Experimental validation is performed first on an open-access, multiclass heart sound dataset where we analyzed the effect of additive noise by mixing lung sound noise with the recordings. In noisy conditions, the proposed method outperforms one of the best-performing methods in the literature achieving an Macc (mean of sensitivity and specificity) of 89.55% and an average F-1 score of 82.96%, respectively, when averaged over all noise levels. Next, we perform heart sound abnormality detection (binary classification) experiments on the 2016 Physionet/CinC Challenge dataset that involves noisy recordings obtained from multiple stethoscope sensors. The proposed method achieves significantly improved results compared to the conventional approaches on this dataset, in the presence of both additive noise and channel distortion, with an area under the ROC (receiver operating characteristics) curve (AUC) of 91.36%, F-1 score of 84.09%, and Macc of 85.08%. We also show that the proposed method shows the best mean accuracy across different source domains, including stethoscope and noise variability, demonstrating its effectiveness in different recording conditions. The proposed combination of linear and logarithmic features along with the ResNet classifier effectively minimizes the impact of background noise and sensor variability for classifying phonocardiogram (PCG) signals. The method thus paves the way toward developing computer-aided cardiac auscultation systems in noisy environments using low-cost stethoscopes.

Digital auscultation as a novel childhood pneumonia diagnostic tool for community clinics in Sylhet, Bangladesh: protocol for a cross-sectional study

INTRODUCTION

The WHO's Integrated Management of Childhood Illnesses (IMCI) algorithm for diagnosis of child pneumonia relies on counting respiratory rate and observing respiratory distress to diagnose childhood pneumonia. IMCI case defination for pneumonia performs with high sensitivity but low specificity, leading to overdiagnosis of child pneumonia and unnecessary antibiotic use. Including lung auscultation in IMCI could improve specificity of pneumonia diagnosis. Our objectives are: (1) assess lung sound recording quality by primary healthcare workers (HCWs) from under-5 children with the Feelix Smart Stethoscope and (2) determine the reliability and performance of recorded lung sound interpretations by an automated algorithm compared with reference paediatrician interpretations.

METHODS AND ANALYSIS

In a cross-sectional design, community HCWs will record lung sounds of ~1000 under-5-year-old children with suspected pneumonia at first-level facilities in Zakiganj subdistrict, Sylhet, Bangladesh. Enrolled children will be evaluated for pneumonia, including oxygen saturation, and have their lung sounds recorded by the Feelix Smart stethoscope at four sequential chest locations: two back and two front positions. A novel sound-filtering algorithm will be applied to recordings to address ambient noise and optimise recording quality. Recorded sounds will be assessed against a predefined quality threshold. A trained paediatric listening panel will classify recordings into one of the following categories: normal, crackles, wheeze, crackles and wheeze or uninterpretable. All sound files will be classified into the same categories by the automated algorithm and compared with panel classifications. Sensitivity, specificity and predictive values, of the automated algorithm will be assessed considering the panel's final interpretation as gold standard.

ETHICS AND DISSEMINATION

The study protocol was approved by the National Research Ethics Committee of Bangladesh Medical Research Council, Bangladesh (registration number: 09630012018) and Academic and Clinical Central Office for Research and Development Medical Research Ethics Committee, Edinburgh, UK (REC Reference: 18-HV-051). Dissemination will be through conference presentations, peer-reviewed journals and stakeholder engagement meetings in Bangladesh.

TRIAL REGISTRATION NUMBER

NCT03959956.