-
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 -
Acta Veterinaria Scandinavica Jun 2020The frequency that cardiac murmurs are identified and recorded in first opinion veterinary practices at the first health check in puppies is unknown. The aims of the...
BACKGROUND
The frequency that cardiac murmurs are identified and recorded in first opinion veterinary practices at the first health check in puppies is unknown. The aims of the study were to assess the agreement between first opinion veterinary practitioners, a veterinary student and a veterinary cardiology specialist on detecting murmurs, and to establish whether abnormal auscultation findings had been recorded in the health certificates of clinically healthy puppies. The study included prospective and retrospective investigations, where the prospectively collected auscultation findings from a veterinary cardiology specialist and a trained veterinary student were compared to auscultation findings recorded by first opinion veterinary practitioners.
RESULTS
Cardiac auscultation was performed on 331 client-owned, clinically healthy dogs at two time points: at age 34-69 days by a first opinion veterinary practitioner and at age 45-76 days, on average 9 days later, by a veterinary cardiology specialist and a trained veterinary student. Agreement among the three was compared for the presence of a murmur. The degree of inter-observer agreement was evaluated using Cohen's kappa. Auscultation findings, as noted in the pets' passports, from 331 puppies and 43 different first opinion veterinary practices, were retrospectively reviewed and prospectively compared with auscultation findings from a veterinary cardiology specialist. Agreement between the veterinary cardiology specialist and the first opinion veterinary practitioners was poor (ϰ = 0.01) and significantly different (P < 0.001). First opinion veterinary practitioners had recorded a cardiac murmur in only 1 of the 97 puppies in which the veterinary cardiology specialist detected a murmur. Two-hundred-and-fifty-two puppies were auscultated by both the veterinary cardiology specialist and the student. Their agreement was fair (ϰ = 0.40) and significantly different (P = 0.024). The agreement between the student and a first opinion veterinary practitioner on these 252 puppies was poor (ϰ = 0.03) and significantly different (P < 0.001).
CONCLUSIONS
This study shows that soft cardiac murmurs are rarely documented during the first veterinary health check in puppies by first opinion veterinary practitioners. Although soft murmurs may not be clinically relevant, finding and recording them is evidence of a carefully performed auscultation. Missing a non-pathological murmur is not of clinical importance; however, missing a pathological murmur could prove detrimental for the individual puppy.
Topics: Animals; Dog Diseases; Dogs; Heart Auscultation; Heart Murmurs; Prospective Studies; Retrospective Studies; Students; Veterinarians; Veterinary Medicine
PubMed: 32586343
DOI: 10.1186/s13028-020-00535-1 -
MedEdPORTAL : the Journal of Teaching... 2022Physicians need adequate physical exam skills. Unfortunately, interns have variable physical exam skills, and teaching is often limited to rounds, an inconsistent...
INTRODUCTION
Physicians need adequate physical exam skills. Unfortunately, interns have variable physical exam skills, and teaching is often limited to rounds, an inconsistent setting. Physical exam skills, particularly those involving auscultation, require practice. Our goal was to create a cardiac physical exam workshop for pediatric interns that would improve their performance on an interactive assessment of their ability and understanding in physical exam and murmur interpretation.
METHODS
We completed a targeted needs assessment and then developed a 2-hour workshop on the pediatric cardiac physical exam targeted to pediatrics residents. The workshop included didactics, group discussion, and practice interpreting common pediatric murmurs. Pediatrics residents completed the assessment as a pretest and then participated in the workshop. At the end of the workshop, the assessment was administered as a posttest, followed by a reassessment 3 months later. Nonparametric statistical analysis was conducted. Pre- and posttest scores were compared using the Wilcoxon signed rank test.
RESULTS
Twenty-five residents completed the workshop, including 22 pediatrics residents, one pediatrics/anesthesia combined resident, one pediatric neurology resident, and one resident completing a preliminary year in pediatrics prior to dermatology residency. There was a significant increase in the mean score on the assessment from pre- to posttest (pretest = 54%, posttest = 71%, < .001). This increase was sustained at the 3-month reassessment ( = 67%).
DISCUSSION
This cardiac physical exam workshop demonstrated improvement in physical exam knowledge and interpretation ability as measured by an online pre-/posttest.
Topics: Child; Humans; Internship and Residency; Clinical Competence; Physical Examination; Heart Murmurs; Auscultation
PubMed: 36605544
DOI: 10.15766/mep_2374-8265.11289 -
Micromachines Dec 2022In light of a need for low-frequency, high sensitivity and broadband cardiac murmur signal detection, the present work puts forward an integrated MEMS-based heart sound...
In light of a need for low-frequency, high sensitivity and broadband cardiac murmur signal detection, the present work puts forward an integrated MEMS-based heart sound sensor with a hollow concave ciliary micro-structure. The advantages of a hollow MEMS structure, in contrast to planar ciliated micro-structures, are that it reduces the ciliated mass and enhances the operating bandwidth. Meanwhile, the area of acoustic-wave reception is enlarged by the concave architecture, thereby enhancing the sensitivity at low frequencies. By rationally designing the acoustic encapsulation, the loss of heart acoustic distortion and weak cardiac murmurs is reduced. As demonstrated by experimentation, the proposed hollow MEMS structure cardiac sound sensor has a sensitivity of up to -206.9 dB at 200 Hz, showing 6.5 dB and 170 Hz increases in the sensitivity and operating bandwidth, respectively, in contrast to the planar ciliated MEMS sensor. The SNR of the sensor is 26.471 dB, showing good detectability for cardiac sounds.
PubMed: 36557472
DOI: 10.3390/mi13122174 -
International Journal of Environmental... Oct 2021Assessment of heart sounds which are generated by the beating heart and the resultant blood flow through it provides a valuable tool for cardiovascular disease (CVD)...
Assessment of heart sounds which are generated by the beating heart and the resultant blood flow through it provides a valuable tool for cardiovascular disease (CVD) diagnostics. The cardiac auscultation using the classical stethoscope phonological cardiogram is known as the most famous exam method to detect heart anomalies. This exam requires a qualified cardiologist, who relies on the cardiac cycle vibration sound (heart muscle contractions and valves closure) to detect abnormalities in the heart during the pumping action. Phonocardiogram (PCG) signal represents the recording of sounds and murmurs resulting from the heart auscultation, typically with a stethoscope, as a part of medical diagnosis. For the sake of helping physicians in a clinical environment, a range of artificial intelligence methods was proposed to automatically analyze PCG signal to help in the preliminary diagnosis of different heart diseases. The aim of this research paper is providing an accurate CVD recognition model based on unsupervised and supervised machine learning methods relayed on convolutional neural network (CNN). The proposed approach is evaluated on heart sound signals from the well-known, publicly available PASCAL and PhysioNet datasets. Experimental results show that the heart cycle segmentation and segment selection processes have a direct impact on the validation accuracy, sensitivity (TPR), precision (PPV), and specificity (TNR). Based on PASCAL dataset, we obtained encouraging classification results with overall accuracy 0.87, overall precision 0.81, and overall sensitivity 0.83. Concerning Micro classification results, we obtained Micro accuracy 0.91, Micro sensitivity 0.83, Micro precision 0.84, and Micro specificity 0.92. Using PhysioNet dataset, we achieved very good results: 0.97 accuracy, 0.946 sensitivity, 0.944 precision, and 0.946 specificity.
Topics: Algorithms; Artificial Intelligence; Cardiovascular Diseases; Heart Rate; Heart Sounds; Humans; Neural Networks, Computer
PubMed: 34682696
DOI: 10.3390/ijerph182010952 -
Journal of Family Medicine and Primary... Jul 2023Cardiac diseases in the pediatric population can be congenital or acquired. If the diagnosis and treatment are early, the chance for survival increases. Thus, this study...
OBJECTIVES
Cardiac diseases in the pediatric population can be congenital or acquired. If the diagnosis and treatment are early, the chance for survival increases. Thus, this study aimed to determine the indications for pediatric cardiology consultations in a single tertiary hospital in Jeddah, Saudi Arabia.
MATERIALS AND METHODS
This study was conducted in 2020-2021 at a tertiary center in Jeddah, Saudi Arabia. Patients younger than 14 years of age who were referred by outpatient clinics or those who presented to the emergency department and needed outpatient cardiac evaluation were included in this study. Inpatient referrals were excluded. The Statistical Package for the Social Sciences version 21 was used for statistical analyses.
RESULTS
A total of 416 referred patients were included in this study. New patients accounted for 74% of the referrals, while known patients accounted for 26%. The median age was 2.728 years, with 56.3% being male participants. The three most common reasons for referral were: evaluation of cardiac function (21.6%), follow-up evaluation of fetal/neonatal diagnosis (19.5%), and heart murmurs (16.8%).
CONCLUSION
Most of the referrals were new patients. Of those who underwent echocardiography, 48.2% had abnormal results. We recommend further studies to help guide the direction of the residents' education and to provide better patient healthcare services.
PubMed: 37649738
DOI: 10.4103/jfmpc.jfmpc_65_23 -
Journal of Cardiology Nov 2022The effectiveness of cardiac auscultation training with a cardiology patient simulator for medical students is still unclear. Starting such training earlier may help...
BACKGROUND
The effectiveness of cardiac auscultation training with a cardiology patient simulator for medical students is still unclear. Starting such training earlier may help students improve their proficiency. We investigated whether cardiac auscultation training using a simulator for first-year students is feasible and effective.
METHODS
A total of 43 first-year medical students (5-12 in each year, 2015-2019) participated in three 1.5-hour extra-curricular classes comprising mini-lectures, facilitated training, two different auscultation tests (the second test closer to clinical setting than the first), and a questionnaire. The test results were compared with those of 556 fourth-year medical students who participated in a compulsory 3-hour cardiac auscultation class in 2016-2019.
RESULTS
The accuracy rate of all heart sounds and murmurs was higher in the first-year students than in the fourth-year students in both the first (85.8 vs. 79.4 %, p = 0.001) and second (71.3 vs. 61.2 %, p = 0.02) tests. That of second/third/fourth sounds was also higher in the first-year students than in the fourth-year students in both the first (86.0 vs. 79.7 %, p = 0.01) and second (70.9 vs. 53.9 %, p = 0.002) tests. The accuracy rate of murmurs was higher in the first-year students than in the fourth-year students in the first test (85.5 vs. 78.9 %, p = 0.04), but not in the second test (72.1 vs. 75.7 %, p = 0.58). All the first-year students and 65 % of them agreed that they had received sufficient knowledge and built sufficient skills, respectively. All the first-year students and 93 % of them agreed that they were satisfied with the program, and that the program was suitable for first-year students, respectively.
CONCLUSIONS
Although training time was different between the two groups and it is possible that only motivated first-year students participated in the program, these results suggest that our cardiac auscultation training is feasible and effective for first-year medical students.
Topics: Cardiology; Clinical Competence; Feasibility Studies; Heart Auscultation; Heart Murmurs; Humans; Students, Medical
PubMed: 35750554
DOI: 10.1016/j.jjcc.2022.06.007 -
BMC Medical Education Jul 2022Well performed clinical communication is a cornerstone of collaborative care in medicine but may be confounded by inconsistent intentions of the messenger and biased...
BACKGROUND
Well performed clinical communication is a cornerstone of collaborative care in medicine but may be confounded by inconsistent intentions of the messenger and biased interpretation by the recipient. A comparison of the findings of electronic echocardiography reports with clinician-completed standardised request forms provided an opportunity to assess communication quality.
AIM
The study aimed to determine clinician aptitude to complete written echocardiography referral forms by assessing the completeness, appropriateness, accuracy, and coherency of the reported clinical findings, conclusions and requests made on the referral forms. The study explored factors that may influence the quality of communication through this referral medium.
METHODS
A retrospective cohort study was conducted on patients who underwent trans-thoracic echocardiography imaging at Cecilia Makiwane Hospital in East London over 26 months. Paper echocardiography request forms that recorded the requesting clinician's findings on examination, the provisional clinical diagnosis, and the specific echocardiographic information sought, were compared with the actual findings on echocardiography.
RESULTS
Of 613 request forms reviewed, 97 cases were excluded due to illegibility or because they lacked analysable information or requester details, leaving 516 forms suitable for study. No pathology was found on echocardiography in 31%. Of the murmurs expected from the echocardiography findings, only half were recorded on the request form (sensitivity and positive predictive value both 52%.). Only 35% of request forms that mentioned a mitral systolic murmur gave a working diagnosis of mitral regurgitation and only 38% of request forms that mentioned an aortic systolic murmur considered aortic stenosis. Clinically suspected cardiomyopathy (CMO) had a PPV of 43% and echocardiographic CMO was missed clinically in 41%. Apex beat displacement reported clinically was not associated with echocardiographic LV dilatation in 65% of cases. One-third (34%) of forms reporting murmurs did not request valve function assessment and 17% considering cardiomyopathy did not request left ventricular function assessment.
CONCLUSION
Echocardiography request forms highlight vulnerabilities in clinical communication. Specifically, important clinical features were missing and more concerningly, included when unlikely to be present. There was a lack of concordance between recorded clinical findings and postulated diagnoses. Clinicians sometimes appeared unclear about the value or appropriateness of the requested assistance. Greater emphasis on teaching examination and communication skills may foster safer and more efficient use of scarce resources.
Topics: Cardiomyopathies; Communication; Echocardiography; Heart Murmurs; Humans; Referral and Consultation; Retrospective Studies; Systolic Murmurs
PubMed: 35831886
DOI: 10.1186/s12909-022-03602-5 -
Journal of Feline Medicine and Surgery Apr 2021Assessment of heart size in kittens is important, and there is a need for reference intervals (RIs) to prevent misinterpretation of cardiomegaly in this patient...
OBJECTIVES
Assessment of heart size in kittens is important, and there is a need for reference intervals (RIs) to prevent misinterpretation of cardiomegaly in this patient population. The purpose of this study was to generate RIs for echocardiographic and radiographic quantification of cardiac size in healthy kittens.
METHODS
In total, 88 kittens aged 6-16 weeks were enrolled in this study. Physical examination, and radiographic and echocardiographic evaluations were performed without sedation. Thoracic radiographs and echocardiographic images were measured to establish RIs for vertebral heart score (VHS), cardiac thoracic ratio (CTR) and multiple echocardiographic variables. N-terminal pro B-type natriuretic peptide (NT-proBNP) was measured. Statistical correlations between echocardiographic parameters and age, body weight and sex were all evaluated and RIs were generated.
RESULTS
Low-grade heart murmurs were appreciated in 26/88 kittens (29.5%). Kittens had a median VHS of 9.5 vertebrae (95% RI 8.0-10.9) and a median CTR of 67.2% (95% RI 54.4-79.8%). Measured NT-proBNP levels were comparable to healthy adult cats with a median of 31 pmol/l (upper reference limit 75 pmol/l). Multiple moderate-to-strong correlations between body weight and age with various echocardiographic parameters were observed and allometric scaling was performed for body weight. RIs for echocardiographic parameters were generated based on patient weight using allometric scaling formulas. Tricuspid valve regurgitation was a common finding and was present in 37.5% (n = 33) of the kittens.
CONCLUSIONS AND RELEVANCE
This study establishes RIs for thoracic radiograph assessment, echocardiography and cardiac biomarkers in kittens, which fills a critical gap in the veterinary literature. The VHS reported in this study is higher than previously reported for adult cats.
Topics: Animals; Biomarkers; Cats; Echocardiography; Female; Heart Murmurs; Natriuretic Peptide, Brain; Peptide Fragments; Reference Values
PubMed: 32812464
DOI: 10.1177/1098612X20946461 -
Journal of Veterinary Internal Medicine May 2021The origin of cough in dogs with heart murmurs is controversial, because the cough could be primary cardiac (eg, pulmonary edema, bronchi compression by left-sided...
BACKGROUND
The origin of cough in dogs with heart murmurs is controversial, because the cough could be primary cardiac (eg, pulmonary edema, bronchi compression by left-sided cardiomegaly) or respiratory (eg, bronchomalacia, other bronchial or bronchiolar disease, interstitial lung disease) in origin.
HYPOTHESIS/OBJECTIVES
To study the association between left atrium (LA) dilatation and cardiomegaly and bronchial narrowing in coughing dogs with heart murmurs using computed tomography (CT).
ANIMALS
Twenty-one client-owned coughing dogs with heart murmurs and 14 historical control dogs.
METHODS
Dogs with cough and murmur were prospectively recruited over 4 months. Cervical and thoracic radiography, echocardiography, and thoracic CT were performed in enrolled dogs. Control dogs, with no disease on thoracic CT and no records of heart murmur and coughing, were gathered from the institution's computerized database. Degree of bronchial narrowing was assessed using the bronchial-to-aorta (Ao) ratio, measured by 3 radiologists blinded to the clinical findings. After identifying bronchi that were significantly narrowed in dogs with murmur compared to controls, the relationship between degree of narrowing and LA/Ao ratio (measured echocardiographically) and vertebral heart scale (VHS) measured radiographically was studied in dogs with murmur using mixed-effects regression.
RESULT
Significant narrowing was identified for all left-sided bronchi and the right principal, middle, and caudal bronchi in the coughing dogs, compared with controls. Increasing LA size and VHS were significantly inversely associated with diameter for all left-sided and right-sided bronchi indicated above.
CONCLUSION AND CLINICAL IMPORTANCE
Results indicate an association between LA enlargement and cardiomegaly and bronchial narrowing and support heart size-associated exacerbation of cough in dogs with murmurs.
Topics: Animals; Bronchi; Cough; Dog Diseases; Dogs; Heart Murmurs; Tomography, X-Ray Computed
PubMed: 33811698
DOI: 10.1111/jvim.16115