-
Sensors (Basel, Switzerland) Jun 2024The phonocardiogram (PCG) can be used as an affordable way to monitor heart conditions. This study proposes the training and testing of several classifiers based on SVMs...
The phonocardiogram (PCG) can be used as an affordable way to monitor heart conditions. This study proposes the training and testing of several classifiers based on SVMs (support vector machines), k-NN (k-Nearest Neighbor), and NNs (neural networks) to perform binary ("Normal"/"Pathologic") and multiclass ("Normal", "CAD" (coronary artery disease), "MVP" (mitral valve prolapse), and "Benign" (benign murmurs)) classification of PCG signals, without heart sound segmentation algorithms. Two datasets of 482 and 826 PCG signals from the Physionet/CinC 2016 dataset are used to train the binary and multiclass classifiers, respectively. Each PCG signal is pre-processed, with spike removal, denoising, filtering, and normalization; afterward, it is divided into 5 s frames with a 1 s shift. Subsequently, a feature set is extracted from each frame to train and test the binary and multiclass classifiers. Concerning the binary classification, the trained classifiers yielded accuracies ranging from 92.4 to 98.7% on the test set, with memory occupations from 92.7 kB to 11.1 MB. Regarding the multiclass classification, the trained classifiers achieved accuracies spanning from 95.3 to 98.6% on the test set, occupying a memory portion from 233 kB to 14.1 MB. The NNs trained and tested in this work offer the best trade-off between performance and memory occupation, whereas the trained k-NN models obtained the best performance at the cost of large memory occupation (up to 14.1 MB). The classifiers' performance slightly depends on the signal quality, since a denoising step is performed during pre-processing. To this end, the signal-to-noise ratio (SNR) was acquired before and after the denoising, indicating an improvement between 15 and 30 dB. The trained and tested models occupy relatively little memory, enabling their implementation in resource-limited systems.
Topics: Humans; Phonocardiography; Machine Learning; Signal Processing, Computer-Assisted; Algorithms; Neural Networks, Computer; Wearable Electronic Devices; Support Vector Machine
PubMed: 38931636
DOI: 10.3390/s24123853 -
Animals : An Open Access Journal From... Jun 2024Heart murmurs in puppies can be innocent or pathologic; the latter is almost always related to a congenital heart disease. Differentiating between these murmurs can be...
BACKGROUND
Heart murmurs in puppies can be innocent or pathologic; the latter is almost always related to a congenital heart disease. Differentiating between these murmurs can be challenging for practicing veterinarians, but this differentiation is essential to ensure the best prognosis for puppies having a congenital heart disease. Our study aimed to reveal how veterinarians manage puppies with a heart murmur.
METHODS
A web-based questionnaire was sent to Dutch and Belgian veterinary practices.
RESULTS
Data from 452 respondents were analyzed. Though 88% of the respondents find detecting a heart murmur easy, only 9% find differentiating innocent murmurs from pathologic murmurs in puppies easy. Of the respondents, only 80% recommend immediate additional examination when detecting a loud heart murmur during the first veterinary health check at 6 weeks of age. Most of the respondents are aware that normal growth and the absence of clinical signs do not exclude severe congenital heart disease. Of the respondents, 31% were uncertain whether early surgical intervention could lead to improved outcomes.
CONCLUSIONS
Veterinarians are aware of the importance of echocardiography for puppies with a loud heart murmur, and recognize their limitations when differentiating an innocent from a pathological heart murmur in a puppy.
PubMed: 38929440
DOI: 10.3390/ani14121821 -
Frontiers in Pediatrics 2024Atrial septal defect (ASD) is a congenital heart disease that often presents without symptoms or murmurs. If left untreated, children with ASD can develop comorbidities...
BACKGROUND
Atrial septal defect (ASD) is a congenital heart disease that often presents without symptoms or murmurs. If left untreated, children with ASD can develop comorbidities in adulthood. In Japan, school electrocardiography (ECG) screening has been implemented for all 1st, 7th, and 10th graders. However, the impact of this program in detecting children with ASD is unknown.
METHODS
This is a retrospective study that analyzed consecutive patients with ASD who underwent catheterization for surgical or catheter closure at ≤18 years of age during 2009-2019 at a tertiary referral center in Japan.
RESULTS
Of the overall 116 patients with ASD (median age: 3.0 years of age at diagnosis and 8.9 years at catheterization), 43 (37%) were prompted by the ECG screening (Screening group), while the remaining 73 (63%) were by other findings (Non-screening group). Of the 49 patients diagnosed at ≥6 years of age, 43 (88%) were prompted by the ECG screening, with the 3 corresponding peaks of the number of patients at diagnosis. Compared with the non-screening group, the screening group exhibited similar levels of hemodynamic parameters but had a lower proportion of audible heart murmur, which were mainly prompted by the health care and health checkups in infancy or preschool period. Patients positive for a composite parameter (rsR' type of iRBBB, inverted T in V4, or ST depression in the aVF lead) accounted for 79% of the screening group at catheterization, each of which was correlated with hemodynamic parameters in the overall patients.
CONCLUSIONS
The present study shows that school ECG screening detects otherwise unrecognized ASD, which prompted the diagnosis of the majority of patients at school age and >one-third of overall patients in Japan. These findings suggest that ECG screening program could be an effective strategy for detecting hemodynamically significant ASD in students, who are asymptomatic and murmurless.
PubMed: 38887565
DOI: 10.3389/fped.2024.1396853 -
International Journal of Cardiology Sep 2024Transthoracic echocardiography (TTE) is routinely required during pre-participation screening in the presence of symptoms, family history of sudden cardiac death or... (Review)
Review
Transthoracic echocardiography (TTE) is routinely required during pre-participation screening in the presence of symptoms, family history of sudden cardiac death or cardiomyopathies <40-year-old, murmurs, abnormal ECG findings or in the follow-up of athletes with a history of cardiovascular disease (CVD). TTE is a cost-effective first-line imaging modality to evaluate the cardiac remodeling due to long-term, intense training, previously known as the athlete's heart, and to rule out the presence of conditions at risk of sudden cardiac death, including cardiomyopathies, coronary artery anomalies, congenital, aortic and heart valve diseases. Moreover, TTE is useful for distinguishing physiological cardiac adaptations during intense exercise from pathological behavior due to an underlying CVD. In this expert opinion statement endorsed by the Italian Society of Sports Cardiology, we discussed common clinical scenarios where a TTE is required and conditions falling in the grey zone between the athlete's heart and underlying cardiomyopathies or other CVD. In addition, we propose a minimum dataset that should be included in the report for the most common indications of TTE in sports cardiology clinical practice.
Topics: Humans; Echocardiography; Sports Medicine; Italy; Societies, Medical; Cardiology; Death, Sudden, Cardiac; Athletes; Expert Testimony; Sports; Cardiovascular Diseases
PubMed: 38852859
DOI: 10.1016/j.ijcard.2024.132230 -
Animals : An Open Access Journal From... Apr 2024Auscultation of heart sounds is an important veterinary skill requiring an understanding of anatomy, physiology, pathophysiology and pattern recognition. This...
Auscultation of heart sounds is an important veterinary skill requiring an understanding of anatomy, physiology, pathophysiology and pattern recognition. This cross-sectional study was developed to evaluate a targeted, audio-visual training resource for veterinary students to improve their understanding and auscultation of common heart conditions in horses. Fourth- and fifth-year 2021 and 2022 Bachelor of Veterinary Science students at the University of Queensland (UQ) were provided the learning resource and surveyed via online pre- and post-intervention surveys. Results were quantitatively analyzed using descriptive statistics and Mann-Whitney U tests. Open-ended survey questions were qualitatively analyzed by thematic analysis and Leximancer™ Version 4 program software analysis. Over the two-year period, 231 fourth-year and 222 fifth-year veterinary students had access to the resource; 89 completed the pre-intervention survey and 57 completed the post-intervention survey. Quantitative results showed the resource helped students prepare for practicals and their perception of competency and confidence when auscultating equine cardiac sounds improved ( < 0.05). Compared to fifth-year students, fourth-year students felt less competent at identifying murmurs and arrythmias prior to accessing the learning resource ( < 0.05). Fourth-year and fifth-year students' familiarity with detection of murmurs improved after completing the learning resource ( < 0.001). Qualitative analysis demonstrated a limited number of opportunities to practice equine cardiac auscultation throughout the veterinary degree, especially during the COVID-19 pandemic, and that integrated audio-visual resources are an effective means of teaching auscultation.
PubMed: 38731348
DOI: 10.3390/ani14091341 -
Tropical Medicine and Infectious Disease Apr 2024Infective endocarditis (IE) is characterised by fever, heart murmurs, and emboli. Splenic emboli are frequent in left-sided IE. A systematic review of the literature... (Review)
Review
Infective endocarditis (IE) is characterised by fever, heart murmurs, and emboli. Splenic emboli are frequent in left-sided IE. A systematic review of the literature published on splenic embolism (SE) between 2000 and 2023 was conducted. Search strategies in electronic databases identified 2751 studies published between 1 January 2000 and 4 October 2023, of which 29 were finally included. The results showed that the imaging tests predominantly used to detect embolisms were computed tomography (CT), magnetic resonance imaging, positron emission tomography (PET)/CT, single-photon emission computed tomography/CT, ultrasound, and contrast-enhanced ultrasound. More recent studies typically used F-FDG PET-CT. The proportion of SE ranged from 1.4% to 71.7%. Only seven studies performed systematic conventional CT screening for intra-abdominal emboli, and the weighted mean frequency of SE was 22% (range: 8-34.8%). F-FDG PET-CT was performed systematically in seven studies, and splenic uptake was found in a weighted mean of 4.5%. There was a lack of uniformity in the published literature regarding the frequency and management of splenic embolisation. CT scans were the most frequently used method, until recently, when F-FDG PET-CT scans began to predominate. More data are necessary regarding the frequency of SE, especially focusing on their impact on IE management and prognosis.
PubMed: 38668544
DOI: 10.3390/tropicalmed9040083 -
Journal of Cardiothoracic Surgery Apr 2024In this case report, we present the unique and intriguing case of a 57-year-old man who experienced exertional palpitations and shortness of breath for 5 years. He was...
In this case report, we present the unique and intriguing case of a 57-year-old man who experienced exertional palpitations and shortness of breath for 5 years. He was diagnosed with idiopathic heart failure three years ago, leading to diuretic treatment. Physical examination revealed notable left lower extremity swelling, severe varicose veins, and cardiac murmurs. Echocardiography showed significant cardiac enlargement and severe functional mitral and tricuspid valve regurgitation. Computed tomography (CT) imaging uncovered a 10 mm left common iliac arteriovenous fistula, causing abnormal early filling of the inferior vena cava (IVC) and marked IVC dilation. Open surgical repair of the arteriovenous fistula resulted in symptom relief and improved cardiac function. This case underscores the importance of considering unusual causes in heart failure patients and highlights the value of early diagnosis and intervention in complex cardiac-vascular interactions.
Topics: Humans; Male; Middle Aged; Arteriovenous Fistula; Arteriovenous Shunt, Surgical; Echocardiography; Heart Failure; Tricuspid Valve Insufficiency; Vena Cava, Inferior
PubMed: 38594763
DOI: 10.1186/s13019-024-02664-4 -
Scientific Reports Mar 2024Traditionally, heart murmurs are diagnosed through cardiac auscultation, which requires specialized training and experience. The purpose of this study is to predict...
Traditionally, heart murmurs are diagnosed through cardiac auscultation, which requires specialized training and experience. The purpose of this study is to predict patients' clinical outcomes (normal or abnormal) and identify the presence or absence of heart murmurs using phonocardiograms (PCGs) obtained at different auscultation points. A semi-supervised model tailored to PCG classification is introduced in this study, with the goal of improving performance using time-frequency deep features. The study begins by investigating the behavior of PCGs in the time-frequency domain, utilizing the Stockwell transform to convert the PCG signal into two-dimensional time-frequency maps (TFMs). A deep network named AlexNet is then used to derive deep feature sets from these TFMs. In feature reduction, redundancy is eliminated and the number of deep features is reduced to streamline the feature set. The effectiveness of the extracted features is evaluated using three different classifiers using the CinC/Physionet challenge 2022 dataset. For Task I, which focuses on heart murmur detection, the proposed approach achieved an average accuracy of 93%, sensitivity of 91%, and F1-score of 91%. According to Task II of the CinC/Physionet challenge 2022, the approach showed a clinical outcome cost of 5290, exceeding the benchmark set by leading methods in the challenge.
Topics: Humans; Phonocardiography; Algorithms; Signal Processing, Computer-Assisted; Heart Murmurs; Heart Auscultation
PubMed: 38555390
DOI: 10.1038/s41598-024-58274-6 -
PLOS Digital Health Mar 2024Cardiovascular diseases (CVDs) account for a high fatality rate worldwide. Heart murmurs can be detected from phonocardiograms (PCGs) and may indicate CVDs. Still, they...
OBJECTIVE
Cardiovascular diseases (CVDs) account for a high fatality rate worldwide. Heart murmurs can be detected from phonocardiograms (PCGs) and may indicate CVDs. Still, they are often overlooked as their detection and correct clinical interpretation require expert skills. In this work, we aim to predict the presence of murmurs and clinical outcomes from multiple PCG recordings employing an explainable multitask model.
APPROACH
Our approach consists of a two-stage multitask model. In the first stage, we predict the murmur presence in single PCGs using a multiple instance learning (MIL) framework. MIL also allows us to derive sample-wise classifications (i.e. murmur locations) while only needing one annotation per recording ("weak label") during training. In the second stage, we fuse explainable hand-crafted features with features from a pooling-based artificial neural network (PANN) derived from the MIL framework. Finally, we predict the presence of murmurs and the clinical outcome for a single patient based on multiple recordings using a simple feed-forward neural network.
MAIN RESULTS
We show qualitatively and quantitatively that the MIL approach yields useful features and can be used to detect murmurs on multiple time instances and may thus guide a practitioner through PCGs. We analyze the second stage of the model in terms of murmur classification and clinical outcome. We achieved a weighted accuracy of 0.714 and an outcome cost of 13612 when using the PANN model and demographic features on the CirCor dataset (hidden test set of the George B. Moody PhysioNet challenge 2022, team "Heart2Beat", rank 12 / 40).
SIGNIFICANCE
To the best of our knowledge, we are the first to demonstrate the usefulness of MIL in PCG classification. Also, we showcase how the explainability of the model can be analyzed quantitatively, thus avoiding confirmation bias inherent to many post-hoc methods. Finally, our overall results demonstrate the merit of employing MIL combined with handcrafted features for the generation of explainable features as well as for a competitive classification performance.
PubMed: 38502666
DOI: 10.1371/journal.pdig.0000461 -
International Journal of Cardiology.... Apr 2024Insufficient clinicians' auscultation ability delays the diagnosis and treatment of valvular heart disease (VHD); artificial intelligence provides a solution to...
BACKGROUND
Insufficient clinicians' auscultation ability delays the diagnosis and treatment of valvular heart disease (VHD); artificial intelligence provides a solution to compensate for the insufficiency in auscultation ability by distinguishing between heart murmurs and normal heart sounds. However, whether artificial intelligence can automatically diagnose VHD remains unknown. Our objective was to use deep learning to process and compare raw heart sound data to identify patients with VHD requiring intervention.
METHODS
Heart sounds from patients with VHD and healthy controls were collected using an electronic stethoscope. Echocardiographic findings were used as the gold standard for this study. According to the chronological order of enrollment, the early-enrolled samples were used to train the deep learning model, and the late-enrollment samples were used to validate the results.
RESULTS
The final study population comprised 499 patients (354 in the algorithm training group and 145 in the result validation group). The sensitivity, specificity, and accuracy of the deep-learning model for identifying various VHDs ranged from 71.4 to 100.0%, 83.5-100.0%, and 84.1-100.0%, respectively; the best diagnostic performance was observed for mitral stenosis, with a sensitivity of 100.0% (31.0-100.0%), a specificity of 100% (96.7-100.0%), and an accuracy of 100% (97.5-100.0%).
CONCLUSIONS
Based on raw heart sound data, the deep learning model effectively identifies patients with various types of VHD who require intervention and assists in the screening, diagnosis, and follow-up of VHD.
PubMed: 38482387
DOI: 10.1016/j.ijcha.2024.101368