Digital Stethoscope Research Articles

DIGITAL STETHOSCOPE – NEW ERA OF AUSCULTATION

This review is devoted to electronic and digital stethoscopes. We performed analysis of publications within last 10 years in databases e-LIBRARY, PubMed, Google Scholar. Key words for the search were «auscultation», «electronic stethoscope», «digital stethoscope», «telemedicine». Review contains an information about new possibilities in auscultation by using digital stethoscopes. We provided an information about brief characteristics of the products of the most popular manufacturers on the Market. Increasing of functionality and versatility (the ability to analyze heart, lungs and intestine sounds) of digital stethoscope and also increasing of noise reduction and sound filtration will make these devices more attractable for everyday use. When these tasks will be solved, the digital stethoscope will definitely become an indispensable tool in the diagnosis, monitoring and treatment of diseases, as well as patients’ self-monitoring. Contemporary models of digital stethoscopes can be used in telemonitoring of the patients with cardiovascular and respiratory diseases. In this case it is possible to estimate the results of auscultation in dynamics, during long term follow up. This can contribute to early evaluation of complications and decompensations in patients with chronic non-infectious diseases such as chronic obstructive pulmonary diseases, asthma, myocardial infarction, etc.

LightCardiacNet: light-weight deep ensemble network with attention mechanism for cardiac sound classification

Cardiovascular diseases (CVDs) account for about 32% of global deaths. While digital stethoscopes can record heart sounds, expert analysis is often lacking. To address this, we propose LightCardiacNet, an interpretable, lightweight ensemble neural network using Bi-Directional Gated Recurrent Units (Bi-GRU). It is trained on the PASCAL Heart Challenge and CirCor DigiScope datasets. Static network pruning enhances model sparsity for real-time deployment. We employ various data augmentation techniques to improve resilience to background noise. An ensemble of the two networks is constructed by employing a weighted average approach that combines the two light-weight attention Bi-GRU networks trained on different datasets, which outperforms several state-of-the-art networks achieving an accuracy of 99.8%, specificity of 99.6%, sensitivity of 95.2%, ROC-AUC of 0.974 and inference time of 17 ms on the PASCAL dataset, accuracy of 98.5%, specificity of 95.1%, sensitivity of 90.9%, ROC-AUC of 0.961 and inference time of 18 ms on the CirCor dataset, and an accuracy of 96.21%, sensitivity of 92.78%, specificity of 93.16%, ROC-AUC of 0.913 and inference time of 17.5 ms on real-world data. We adopt the SHAP algorithm to incorporate model interpretability and provide insights to make it clinically explainable and useful to healthcare professionals.

Enhancing digital health competencies: insights from european human resources for health

Abstract Background Mixed-skills for digital health transformation are critical for human resources for health (HRH). This study aimed to inform the design of new training programmes that address soft, hard and digital health skills. Methods Using a mixed-methods design science approach, focus groups were conducted by invitation and with informed consent, online or in-person. A script was prepared with key questions for orientation and facilitation, addressing the topics of current situation, desired situation, desired skills, practical and organisational needs to implement continuous training in healthcare. The collected data were analysed using Nvivo. Results Focus groups (14) had 87 participants (Norway, Latvia, Belgium, Italy and Portugal): 26 healthcare professionals (nurses, midwives, nutritionists, pharmacists, assistants and doctors); 27 managers or directors of hospitals and care centres; 34 experts (digital health specialists, researchers, technical officers, members of professional societies and national authorities). Real needs were identified, with 2 direct sub-themes that were best related to each other (Pearson coefficient, p > 0.40 - cluster analysis): 1. ‘Current situation’: Cybersecurity (eg. privacy, law and ethics); Time (work time versus private time, p = 0.69); Type (informal versus formal training, p = 0.32); Programmes (graduation, continuing education and post-graduation levels). 2. ‘Desired situation: Desired skills (eg. digital - basic ICT, data analysis, soft - communication, emotional intelligence, and hard skills - medication administration, catheters, ECG, vital signs, telehealth - digital stethoscope); Learning design and objectives (eg. collective learning, simulations, location - peer-to-peer and hybrid); Emergency care and the link between primary and secondary levels of care were considered important. Conclusions These findings of convergence among HRH inform Program design process to support the training programs and course syllabus design. Key messages • The identified needs and priorities inform Program design further to support Digital Health Transformation training programs and course syllabus design. • Real needs points to Current and Desired situation, where HRH give important insights that need to be considered to engage people to perform training courses.

Empowering Healthcare: TinyML for Precise Lung Disease Classification

Respiratory diseases such as asthma pose significant global health challenges, necessitating efficient and accessible diagnostic methods. The traditional stethoscope is widely used as a non-invasive and patient-friendly tool for diagnosing respiratory conditions through lung auscultation. However, it has limitations, such as a lack of recording functionality, dependence on the expertise and judgment of physicians, and the absence of noise-filtering capabilities. To overcome these limitations, digital stethoscopes have been developed to digitize and record lung sounds. Recently, there has been growing interest in the automated analysis of lung sounds using Deep Learning (DL). Nevertheless, the execution of large DL models in the cloud often leads to latency, dependency on internet connectivity, and potential privacy issues due to the transmission of sensitive health data. To address these challenges, we developed Tiny Machine Learning (TinyML) models for the real-time detection of respiratory conditions by using lung sound recordings, deployable on low-power, cost-effective devices like digital stethoscopes. We trained three machine learning models—a custom CNN, an Edge Impulse CNN, and a custom LSTM—on a publicly available lung sound dataset. Our data preprocessing included bandpass filtering and feature extraction through Mel-Frequency Cepstral Coefficients (MFCCs). We applied quantization techniques to ensure model efficiency. The custom CNN model achieved the highest performance, with 96% accuracy and 97% precision, recall, and F1-scores, while maintaining moderate resource usage. These findings highlight the potential of TinyML to provide accessible, reliable, and real-time diagnostic tools, particularly in remote and underserved areas, demonstrating the transformative impact of integrating advanced AI algorithms into portable medical devices. This advancement facilitates the prospect of automated respiratory health screening using lung sounds.

Foundation models for cardiovascular disease detection via biosignals from digital stethoscopes

Auscultation of the heart and the electrocardiogram (ECG) are two central components of the cardiac exam. Recent innovations of the stethoscope have enabled the simultaneous acquisition of a high-quality digital acoustic signal and ECG. We present foundation models trained on phonocardiogram (PCG) and ECG data collected from digital stethoscopes during routine clinical practice. We show that these foundation models that are pre-trained on large unlabeled datasets in a self-supervised manner can be fine-tuned for a variety of cardiovascular disease detection tasks. This is the first study that builds foundation models specifically for synchronously captured PCG and ECG data. Our approach is based on the recently developed masked autoencoder framework which we extend to handle multiple signals that are synchronously captured. This paradigm makes it possible to use large capacity models leading to superior performance even though the size of datasets with medical label annotations may be limited.

Development of an artificial intelligence-enabled non-invasive digital stethoscope for monitoring the heart condition of athletes in real-time

This study investigates the efficacy of AI-enabled digital stethoscopes in enhancing physical performance, increasing student engagement and motivation, and improving psychological well-being among physical culture students. The experimental design involved two groups of 40 students each: the experimental group used AI-enabled stethoscopes for real-time cardiovascular monitoring, while the control group relied on traditional heart rate monitoring methods. The results indicated significant improvements in physical performance, engagement, and psychological well-being for the experimental group. Real-time monitoring facilitated personalized training adjustments, optimizing training loads and preventing overexertion, leading to superior performance outcomes. Additionally, the use of innovative monitoring tools significantly increased student motivation and engagement in physical culture classes, as reflected in higher attendance rates and more enthusiastic participation. Psychological assessments revealed that continuous health monitoring reduced anxiety levels and enhanced overall mental well-being, providing students with a sense of security and proactive health management. These findings underscore the transformative potential of integrating advanced monitoring technologies into physical education and rehabilitation programs, offering precise, real-time data that supports individualized and responsive interventions. The study concludes with a call for further research to explore the long-term impacts and broader applications of AI-enabled health monitoring tools in diverse educational and clinical settings, aiming to maximize their benefits and improve overall student and patient outcomes. Keywords: Sports therapy, Physical culture education, Health monitoring technology, Personalized training, Student engagement, Real-time cardiovascular monitoring, AI-enabled stethoscope.

Use of a Digital Stethoscope to Evaluate Arteriovenous Fistulae before and after Intervention

Use of a Digital Stethoscope to Evaluate Arteriovenous Fistulae before and after Intervention

Artificial intelligence guided screening for cardiomyopathies in an obstetric population: a pragmatic randomized clinical trial.

Nigeria has the highest reported incidence of peripartum cardiomyopathy worldwide. This open-label, pragmatic clinical trial randomized pregnant and postpartum women to usual care or artificial intelligence (AI)-guided screening to assess its impact on the diagnosis left ventricular systolic dysfunction (LVSD) in the perinatal period. The study intervention included digital stethoscope recordings with point of-care AI predictions and a 12-lead electrocardiogram with asynchronous AI predictions for LVSD. The primary end point was identification of LVSD during the study period. In the intervention arm, the primary end point was defined as the number of identified participants with LVSD as determined by a positive AI screen, confirmed by echocardiography. In the control arm, this was the number of participants with clinical recognition and documentation of LVSD on echocardiography in keeping with current standard of care. Participants in the intervention arm had a confirmatory echocardiogram at baseline for AI model validation. A total of 1,232 (616 in each arm) participants were randomized and 1,195 participants (587 intervention arm and 608 control arm) completed the baseline visit at 6 hospitals in Nigeria between August 2022 and September 2023 with follow-up through May 2024. Using the AI-enabled digital stethoscope, the primary study end point was met with detection of 24 out of 587 (4.1%) versus 12 out of 608 (2.0%) patients with LVSD (intervention versus control odds ratio 2.12, 95% CI 1.05-4.27; P = 0.032). With the 12-lead AI-electrocardiogram model, the primary end point was detected in 20 out of 587 (3.4%) versus 12 out of 608 (2.0%) patients (odds ratio 1.75, 95% CI 0.85-3.62; P = 0.125). A similar direction of effect was observed in prespecified subgroup analysis. There were no serious adverse events related to study participation. In pregnant and postpartum women, AI-guided screening using a digital stethoscope improved the diagnosis of pregnancy-related cardiomyopathy. ClinicalTrials.gov registration: NCT05438576.

The Evolving Stethoscope: Insights Derived from Studying Phonocardiography in Trainees.

Phonocardiography (PCG) is used as an adjunct to teach cardiac auscultation and is now a function of PCG-capable stethoscopes (PCS). To evaluate the efficacy of PCG and PCS, the authors investigated the impact of providing PCG data and PCSs on how frequently murmurs, rubs, and gallops (MRGs) were correctly identified by third-year medical students. Following their internal medicine rotation, third-year medical students from the Georgetown University School of Medicine completed a standardized auscultation assessment. Sound files of 10 different MRGs with a corresponding clinical vignette and physical exam location were provided with and without PCG (with interchangeable question stems) as 10 paired questions (20 total questions). Some (32) students also received a PCS to use during their rotation. Discrimination/difficulty indexes, comparative chi-squared, and McNemar test p-values were calculated. The addition of phonocardiograms to audio data was associated with more frequent identification of mitral stenosis, S4, and cardiac friction rub, but less frequent identification of ventricular septal defect, S3, and tricuspid regurgitation. Students with a PCS had a higher frequency of identifying a cardiac friction rub. PCG may improve the identification of low-frequency, usually diastolic, heart sounds but appears to worsen or have little effect on the identification of higher-frequency, often systolic, heart sounds. As digital and phonocardiography-capable stethoscopes become more prevalent, insights regarding their strengths and weaknesses may be incorporated into medical school curricula, bedside rounds (to enhance teaching and diagnosis), and telemedicine/tele-auscultation efforts.

Remote pulmonary pathology diagnosis using a handheld device for acquiring lung sounds at the mouth: a proof of concept study

IntroductionObtaining relevant information about respiratory conditions is a unique challenge in the rapidly growing field of telehealth. While auscultation using a stethoscope remains the first-line method in primary care, it is not a practical solution in a home setting, as it requires the presence of both a skilled caregiver and experienced interpreter online. We conducted a proofofconcept study of a simple selfcheck thermometer-like device (OmnySense®), which acquires auscultatory data through a microphone in the head of the device.ObjectivesTo have a concept of proof that home handled simplified device can asure a remote opion in telemedicine enhancing prompt and ease way to diagnose lung pathologies.MethodsWe assessed the agreement between subjective evaluations of lung sounds using the device and those using a digital stethoscope for the presence of crackles and/or wheezes. A total of 385 recordings from 13 patients admitted to the internal department were blindly, individually, and randomly assessed by three experienced physicians. The intra-modality agreement for crackles between evaluators was moderate for both the device and the stethoscope, with kappa statistics of 0.44 and 0.6 for the device and stethoscope, respectively, for the detection of wheezing and 0.46 and 0.4, respectively, for the crackles. The intermodality agreement was moderate for wheezes, with a kappa of 0.53, and was substantial for crackles, with a kappa of 0.71. Comparing the ability of crackles to diagnose pulmonary findings by imaging showed comparable sensitivity and specificity for both modalities.ConclusionsOur findings suggest that the diagnostic performance of OmnySense’s selfoperating device is similar to that of physician interpretation of digital stethoscope recordings; thus, OmnySense has the potential to become a useful tool in the remote assessment of respiratory conditions and pathologies.

Effectiveness of Bluetooth communication of digital stethoscope using quality of service method

Effectiveness of Bluetooth communication of digital stethoscope using quality of service method

Efficient Fetal Health Prediction using Machine Learning

The growth of technology in our day-to-day enterprise with advanced machines are outstanding through machine learning involving both machine learning and deep learning all over the world. Fetal monitoring during pregnancy time is the most important to save the life of the mother as well as the child. In this project, we present a ML technique that is used to measure the fetal heart rate during the time of pregnancy. The major component used for this detection is Fetal Digital stethoscope sensor which is to be placed on the abdomen of the pregnant and the signals are processed by the micro-controller used and the accurate fetal heart rate. This system is very flexible and low cost helps the patient to monitor the fetal heart rate in home. We will use ML method for our project. In this paper Fetal health is predicted by algorithms namely Decision Tree (DT) as existing and Recurrent Neural Network (RNN) as proposed and compared in terms of accuracy. From our work we can prove that our proposed RNN works better than other existing DT algorithm.

Digital Stethoscope Utility in NICU, SCN, and LDRP Patients

Introduction: To this day, abnormal auscultatory findings on acoustic examination of the cardiovascular system remains the most common reason for referral to a cardiologist. Three limitations exist with acoustic stethoscopes: 1) high selective sensitivity requirement is needed; 2) easy disruption by ambient environmental noise; 3) subjectivity of interpretation based on the provider’s experience, skills, and auditory proficiency. The introduction of digital stethoscopes offered a solution to the limitations of the traditional acoustic stethoscope while at the same time broadening the diagnostic potential of such devices: 1) improvement in sound quality; 2) amplification of the acoustic signal; 3) reduction of ambient noise. The objectives were: 1. To determine the accuracy of the digital stethoscope when used in neonatal intensive care unit (NICU), Special Care Nursery (SCN), and Labor & Delivery Recovery Postpartum (LDRP) patients; and 2. To determine if its use leads to improved detection rates of cardiac pathologies compared to the use of a classic acoustic stethoscope. Methods: This is a single center, prospective study of neonates in the NICU, SCN, and LDRP at Ascension St. John Children’s Hospital. After obtaining informed consent, infants were examined using both acoustic and electronic stethoscopes by trained residents. Data from chart review and echocardiography were also collected. Results from the two stethoscopes were compared to each other and to echocardiographic findings. Data were analyzed using Student’s t-test, the χ 2 test and the McNemar χ 2 test. Results: The study included 15 infants, mean of 33.3 ± 3.8 weeks’ gestation at birth, 46.7% female (7/15) and 66.7% (10/15) black. Of the 15 patients evaluated, for the differential diagnosis and the ECHO results, there was 56% (5/9) better agreement with the electronic stethoscope, 33% (3/9) equivocal agreement between the electronic and acoustic stethoscopes, and 11% (1/9) worse agreement between the electronic stethoscope differential diagnosis and the actual ECHO results. Conclusions: There is a trend towards better agreement between the electronic stethoscope differential diagnosis and the actual ECHO results. A larger sample size is needed to determine true statistical significance of the data and probability.

Back to the future: the novel art of digital auscultation applied in a prospective observational study of critically ill Covid-19 patients

BackgroundThe Covid-19 pandemic has caused immense pressure on Intensive Care Units (ICU). In patients with severe ARDS due to Covid-19, respiratory mechanics are important for determining the severity of lung damage. Lung auscultation could not be used during the pandemic despite its merit. The main objective of this study was to investigate associations between lung auscultatory sound features and lung mechanical properties, length of stay (LOS) and survival, in adults with severe Covid-19 ARDS.MethodsConsecutive patients admitted to a large ICU between 2020 and 2021 (n = 173) were included. Digital stethoscopes obtained auscultatory sounds and stored them in an on-line database for replay and further processing using advanced AI techniques. Correlation and regression analysis explored relationships between digital auscultation findings and lung mechanics or the ICU outcome. The resulting annotated lung sounds database is also publicly available as supplementary material.ResultsThe presence of squawks was associated with the ICU LOS, outcome and 90-day mortality. Other features (age, SOFA score & oxygenation index upon admission, minimum crackle entropy) had significant impact on outcome. Additional features affecting the 90-d survival were age and mean crackle entropy. Multivariate logistic regression showed that survival was affected by age, baseline SOFA, baseline oxygenation index and minimum crackle entropy.ConclusionsRespiratory mechanics were associated with various adventitious sounds, whereas the lung sound analytics and the presence of certain adventitious sounds correlated with the ICU outcome and the 90-d survival. Spectral features of crackles sounds can serve as prognostic factors for survival, highlighting the importance of digital auscultation.

The Digital Stethoscope with the Heart Rate Display: A Review and Its Implications for Learning

The Digital Stethoscope with the Heart Rate Display: A Review and Its Implications for Learning

Trends in the Use of Digital Stethoscopes in Healthcare: A Bibliometric Analysis

Trends in the Use of Digital Stethoscopes in Healthcare: A Bibliometric Analysis

Continual Monitoring of Respiratory Disorders to Enhance Therapy via Real-Time Lung Sound Imaging in Telemedicine

This work presents a configurable Internet of Things architecture for acoustical sensing and analysis for frequent remote respiratory assessments. The proposed system creates a foundation for enabling real-time therapy and patient feedback adjustment in a telemedicine setting. By allowing continuous remote respiratory monitoring, the system has the potential to give clinicians access to assessments from which they could make decisions about modifying therapy in real-time and communicate changes directly to patients. The system comprises a wearable wireless microphone array interfaced with a programmable microcontroller with embedded signal conditioning. Experiments on the phantom model were conducted to demonstrate the feasibility of reconstructing acoustic lung images for detecting obstructions in the airway and provided controlled validation of noise resilience and imaging capabilities. An optimized denoising technique and design innovations provided 7 dB more SNR and 7% more imaging accuracy for the proposed system, benchmarked against digital stethoscopes. While further clinical studies are warranted, initial results suggest potential benefits over single-point digital stethoscopes for internet-enabled remote lung monitoring needing noise immunity and regional specificity. The flexible architecture aims to bridge critical technical gaps in frequent and connected respiratory function at home or in busy clinical settings challenged by ambient noise interference.

Exploring the link between a novel approach for computer aided lung sound analysis and imaging biomarkers: a cross-sectional study

BackgroundComputer Aided Lung Sound Analysis (CALSA) aims to overcome limitations associated with standard lung auscultation by removing the subjective component and allowing quantification of sound characteristics. In this proof-of-concept study, a novel automated approach was evaluated in real patient data by comparing lung sound characteristics to structural and functional imaging biomarkers.MethodsPatients with cystic fibrosis (CF) aged > 5y were recruited in a prospective cross-sectional study. CT scans were analyzed by the CF-CT scoring method and Functional Respiratory Imaging (FRI). A digital stethoscope was used to record lung sounds at six chest locations. Following sound characteristics were determined: expiration-to-inspiration (E/I) signal power ratios within different frequency ranges, number of crackles per respiratory phase and wheeze parameters. Linear mixed-effects models were computed to relate CALSA parameters to imaging biomarkers on a lobar level.Results222 recordings from 25 CF patients were included. Significant associations were found between E/I ratios and structural abnormalities, of which the ratio between 200 and 400 Hz appeared to be most clinically relevant due to its relation with bronchiectasis, mucus plugging, bronchial wall thickening and air trapping on CT. The number of crackles was also associated with multiple structural abnormalities as well as regional airway resistance determined by FRI. Wheeze parameters were not considered in the statistical analysis, since wheezing was detected in only one recording.ConclusionsThe present study is the first to investigate associations between auscultatory findings and imaging biomarkers, which are considered the gold standard to evaluate the respiratory system. Despite the exploratory nature of this study, the results showed various meaningful associations that highlight the potential value of automated CALSA as a novel non-invasive outcome measure in future research and clinical practice.

Artificial intelligence–based screening for cardiomyopathy in an obstetric population: A pilot study

Cardiomyopathy is a leading cause of pregnancy-related mortality and the number one cause of death in the late postpartum period. Delay in diagnosis is associated with severe adverse outcomes. To evaluate the performance of an artificial intelligence-enhanced electrocardiogram (AI-ECG) and AI-enabled digital stethoscope to detect left ventricular systolic dysfunction in an obstetric population. We conducted a single-arm prospective study of pregnant and postpartum women enrolled at 3 sites between October 28, 2021, and October 27, 2022. Study participants completed a standard 12-lead ECG, digital stethoscope ECG and phonocardiogram recordings, and a transthoracic echocardiogram within 24 hours. Diagnostic performance was evaluated using the area under the curve (AUC). One hundred women were included in the final analysis. The median age was 31 years (Q1: 27, Q3: 34). Thirty-eight percent identified as non-Hispanic White, 32% as non-Hispanic Black, and 21% as Hispanic. Five percent and 6% had left ventricular ejection fraction (LVEF) <45% and <50%, respectively. The AI-ECG model had near-perfect classification performance (AUC: 1.0, 100% sensitivity; 99%-100% specificity) for detection of cardiomyopathy at both LVEF categories. The AI-enabled digital stethoscope had an AUC of 0.98 (95% CI: 0.95, 1.00) and 0.97 (95% CI: 0.93, 1.00), for detection of LVEF <45% and <50%, respectively, with 100% sensitivity and 90% specificity. We demonstrate an AI-ECG and AI-enabled digital stethoscope were effective for detecting cardiac dysfunction in an obstetric population. Larger studies, including an evaluation of the impact of screening on clinical outcomes, are essential next steps.

Identifying pediatric heart murmurs and distinguishing innocent from pathologic using deep learning

ObjectiveTo develop a deep learning algorithm to perform multi-class classification of normal pediatric heart sounds, innocent murmurs, and pathologic murmurs. MethodsWe prospectively enrolled children under age 18 being evaluated by the Division of Pediatric Cardiology. Parents provided consent for a deidentified recording of their child's heart sounds with a digital stethoscope. Innocent murmurs were validated by a pediatric cardiologist and pathologic murmurs were validated by echocardiogram. To augment our collection of normal heart sounds, we utilized a public database of pediatric heart sound recordings (Oliveira, 2022). We propose two novel approaches for this audio classification task. We train a vision transformer on either Markov transition field or Gramian angular field image representations of the frequency spectrum. We benchmark our results against a ResNet-50 CNN trained on spectrogram images. ResultsOur final dataset consisted of 366 normal heart sounds, 175 innocent murmurs, and 216 pathologic murmurs. Innocent murmurs collected include Still's murmur, venous hum, and flow murmurs. Pathologic murmurs included ventricular septal defect, tetralogy of Fallot, aortic regurgitation, aortic stenosis, pulmonary stenosis, mitral regurgitation and stenosis, and tricuspid regurgitation. We find that the Vision Transformer consistently outperforms the ResNet-50 on all three image representations, and that the Gramian angular field is the superior image representation for pediatric heart sounds. We calculated a one-vs-rest multi-class ROC curve for each of the three classes. Our best model achieves an area under the curve (AUC) value of 0.92 ± 0.05, 0.83 ± 0.04, and 0.88 ± 0.04 for identifying normal heart sounds, innocent murmurs, and pathologic murmurs, respectively. ConclusionWe present two novel methods for pediatric heart sound classification, which outperforms the current standard of using a convolutional neural network trained on spectrogram images. To our knowledge, we are the first to demonstrate multi-class classification of pediatric murmurs. Multiclass output affords a more explainable and interpretable model, which can facilitate further model improvement in the downstream model development cycle and enhance clinician trust and therefore adoption.