Echocardiographic yield in children when innocent murmur seems likely but doubts linger

Identification of Congenital Valvular Murmurs in Young Patients Using Deep Learning-Based Attention Transformers and Phonocardiograms

One in every four newborns suffers from congenital heart disease (CHD) that causes defects in the heart structure. The current gold-standard assessment technique, echocardiography, causes delays in the diagnosis owing to the need for experts who vary markedly in their ability to detect and interpret pathological patterns. Moreover, echo is still causing cost difficulties for low- and middle-income countries. Here, we developed a deep learning-based attention transformer model to automate the detection of heart murmurs caused by CHD at an early stage of life using cost-effective and widely available phonocardiography (PCG). PCG recordings were obtained from 942 young patients at four major auscultation locations, including the aortic valve (AV), mitral valve (MV), pulmonary valve (PV), and tricuspid valve (TV), and they were annotated by experts as absent, present, or unknown murmurs. A transformation to wavelet features was performed to reduce the dimensionality before the deep learning stage for inferring the medical condition. The performance was validated through 10-fold cross-validation and yielded an average accuracy and sensitivity of 90.23 % and 72.41 %, respectively. The accuracy of discriminating between murmurs' absence and presence reached 76.10 % when evaluated on unseen data. The model had accuracies of 70 %, 88 %, and 86 % in predicting murmur presence in infants, children, and adolescents, respectively. The interpretation of the model revealed proper discrimination between the learned attributes, and AV channel was found important (score 0.75) for the murmur absence predictions while MV and TV were more important for murmur presence predictions. The findings potentiate deep learning as a powerful front-line tool for inferring CHD status in PCG recordings leveraging early detection of heart anomalies in young people. It is suggested as a tool that can be used independently from high-cost machinery or expert assessment.

Major congenital heart defects are rarely diagnosed after newborns' hospital discharge with modern screening

AIM

Our aim was to assess undiagnosed congenital heart defects (CHD) after newborns' hospital discharge in patients with a murmur or CHD suspicion, to find out the signs that predict CHDs and to estimate the costs of the examinations.

METHODS

We reviewed retrospective medical records of patients (n = 490) referred for the evaluation of CHD suspicion during 2017-2018.

RESULTS

The median age of the patients was 2.5 (IQR 0.5-7.4) years. Sixty-three (13%) patients had an abnormal echocardiography. Neither ductal-dependent nor cyanotic CHDs were found. Cardiac interventions were performed for 14 out of 63 (22%) patients. Clinical signs indicating CHDs were murmur grade ≥3 (10/11 [91%] vs. 53/479 [11%], p < 0.001) and harsh murmur (15/44 [34%] vs. 48/446 [11%], p < 0.001). Abnormal electrocardiography did not indicate CHD (8/40 [20%] vs. 55/447 [12%], p = 0.165). The total cost of the examinations was 259 700€. The share of the cost of studies assessed as benign was 59%.

CONCLUSION

Only a few CHDs were found after newborn hospital discharge among patients who received foetal and newborn screening and were examined due to CHD suspicion. The high number of benign murmurs in children leads to many referrals, resulting in unnecessary healthcare costs.

Diagnostic Accuracy of Physical Examination and Pulse Oximetry for Critical Congenital Cardiac Disease Screening in Newborns

BACKGROUND

Newborns with a critical congenital heart disease left undiagnosed and untreated have a substantial risk for serious complications and subsequent failure to thrive. Prenatal ultrasound screening is not widely available, nor is postnatal echocardiography. Physical examination is the standard for postnatal screening. Pulse oximetry has been proposed in numerous studies as an alternative screening method. This systematic review and meta-analysis aims to determine the diagnostic accuracies of both screening methods separately and combined.

METHODS

A systematic literature search of the Embase, PubMed, and Global Health databases up to 30 November 2023 was conducted with the following keywords: critical congenital heart disease, physical examination, clinical scores, pulse oximetry, and echocardiography. The search included all studies conducted in the newborn period using both physical examination and pulse oximetry as screening methods and excluded newborns admitted to the intensive care unit. All studies were assessed for risk of bias and applicability concerns using the QUADAS-2 score. The review adhered to the PRISMA 2020 statement guideline.

RESULTS

Out of 2711 articles, 20 articles were selected as eligible for meta-analysis. Cumulatively, the sample included 872,549 screened newborns. The pooled sensitivity of the physical examination screening method was found to be 0.69 (0.66-0.73 (95% CI)) and specificity was found to be 0.98 (0.98-0.98). For the pulse oximetry screening method, the pooled sensitivity and specificity yielded 0.78 (0.75-0.82) and 0.99 (0.99-0.99), respectively. The combined method of screening yielded improved diagnostic characteristics at a sensitivity and specificity of 0.93 (0.91-0.95) and 0.98 (0.98-0.98, respectively.

CONCLUSIONS

The evidence indicates that combining both physical examination and pulse oximetry to screen for critical congenital heart disease exceeds the accuracy of either separate method. The main limitation is that solely newborns with suspected critical congenital heart disease were subjected to the reference standard. We recommend adapting both methods to screen for critical congenital heart diseases, especially in settings lacking standard fetal ultrasound screening. To increase the sensitivity further, we recommend increasing the screening time window and employing the peripheral perfusion index.

The discerning ear: cardiac auscultation in the era of artificial intelligence and telemedicine

Heart murmur, a thoracic auscultatory finding of cardiovascular origin, is extremely common in childhood and can appear at any age from premature newborn to late adolescence. The objective of this review is to provide a modern examination and update of cardiac murmur auscultation in this new era of artificial intelligence (AI) and telemedicine. First, we provide a comprehensive review of the causes and differential diagnosis, clinical features, evaluation, and long-term management of paediatric heart murmurs. Next, we provide a brief history of computer-assisted auscultation and murmur analysis, along with insight into the engineering design of the digital stethoscope. We conclude with a discussion of the paradigm shifting impact of deep learning on murmur analysis, AI-assisted auscultation, and the implications of these technologies on telemedicine in paediatric cardiology. It is our hope that this article provides an updated perspective on the impact of AI on cardiac auscultation for the modern paediatric cardiologist.

Automatic recognition of murmurs of ventricular septal defect using convolutional recurrent neural networks with temporal attentive pooling

Recognizing specific heart sound patterns is important for the diagnosis of structural heart diseases. However, the correct recognition of heart murmur depends largely on clinical experience. Accurately identifying abnormal heart sound patterns is challenging for young and inexperienced clinicians. This study is aimed at the development of a novel algorithm that can automatically recognize systolic murmurs in patients with ventricular septal defects (VSDs). Heart sounds from 51 subjects with VSDs and 25 subjects without a significant heart malformation were obtained in this study. Subsequently, the soundtracks were divided into different training and testing sets to establish the recognition system and evaluate the performance. The automatic murmur recognition system was based on a novel temporal attentive pooling-convolutional recurrent neural network (TAP-CRNN) model. On analyzing the performance using the test data that comprised 178 VSD heart sounds and 60 normal heart sounds, a sensitivity rate of 96.0% was obtained along with a specificity of 96.7%. When analyzing the heart sounds recorded in the second aortic and tricuspid areas, both the sensitivity and specificity were 100%. We demonstrated that the proposed TAP-CRNN system can accurately recognize the systolic murmurs of VSD patients, showing promising potential for the development of software for classifying the heart murmurs of several other structural heart diseases.

Teratogen update: Malaria in pregnancy and the use of antimalarial drugs in the first trimester

Malaria is a particular problem in pregnancy because of enhanced sensitivity, the possibility of placental malaria, and adverse effects on pregnancy outcome. Artemisinin-containing combination therapies (ACTs) are the most effective antimalarials known. WHO recommends 7-day quinine therapy for uncomplicated Plasmodium falciparum malaria in the first trimester despite the superior tolerability and efficacy of 3-day ACT regimens because artemisinins caused embryolethality and/or cardiovascular malformations at relatively low doses in rats, rabbits, and monkeys. The developmental toxicity of artesunate, artemether, and DHA were similar in rats but artesunate was embryotoxic at lower doses in rabbits (5 mg/kg/day) than artemether (no effect level = 25 mg/kg/day). In clinical studies in Africa, treatment with artemether-lumefantrine in the first trimester was observed to be highly efficacious and the miscarriage rate (≤3.1%) was similar to no antimalarial treatment (2.6%). When data from the first-trimester use of largely artesunate-based therapies in Thailand were pooled together, there was no difference in miscarriage rate compared to quinine. However, individually, artesunate-mefloquine was associated with a higher miscarriage rate (15/71 = 21%) compared to other artemisinin-based therapies including 7-day artesunate + clindamycin (2/50 = 4%) and quinine (92/842 = 11%). Thus, appropriate statistical comparisons of individual ACT groups are needed prior to assuming that they all have the same risk for developmental toxicity. Current limitations in the assessment of the safety of ACTs in the first trimester are a lack of exposures early in gestation (gestational weeks 6-7), limited postnatal evaluation for cardiovascular malformations, and the pooling of all ACTs for the assessment of risk.

Evaluation and diagnostic approach for heart murmurs in children

Heart murmurs are common in children. Most of them are innocent murmurs with normal heart anatomy and function, and only a few are pathologic murmurs with congenital heart anomaly or abnormal heart function. However, a heart murmur may be the sole symptom of serious heart disease. Therefore, careful evaluation of heart murmurs for distinguishing pathologic murmurs from innocent murmurs is important. Heart murmurs are described by their intensity, timing in the cardiac cycle, location, transmission, and quality. Murmurs, such as a holosystolic or diastolic murmur, of grade 3 or higher intensity, harsh quality, an abnormal S2, a systolic click, or increased intensity when the patient stands are more likely to be pathologic murmurs. Innocent murmurs are more likely to be systolic murmurs, with soft sounds, short duration, low pitch, and varying intensity with phases of respiration and posture (disappears with standing). Not only auscultation but also physical examination findings are important to evaluate heart murmurs. The gold standard test for the evaluation of any potentially pathologic murmur is echocardiography. For the appropriate use of echocardiography, close physical examination, including auscultation, is essential and requires considerable practice.

Echocardiographic Evaluation in Neonates with Heart Murmurs

Auscultation of the heart is one of the most important tools of physical examination in neonates, which is very helpful in the diagnosis or rejection of congenital heart diseases (CHDs). The aim of this study is to investigate the causes of heart murmur in neonates hospitalized in neonatal unit in Imam Reza Hospital, Kermanshah, Iran. This cross-sectional study was conducted within the period of 18 months on neonates hospitalized in neonatal unit whose heart murmur, diagnosed through examination, and echocardiography was conducted to investigate the existence of CHD. In 62.1% of the cases, murmuring was auscultated within the first week after birth. Among 172 neonates with heart murmur, 25 subjects (14.5%) had normal echocardiogram, and others had abnormal echocardiogram in which ventricular septal defect (31.4%) was the most common CHD. Patent ductus arteriosus (23.3%) was the second common CHD found. Other defects were atrial septal defect, persistent foramen ovale, pulmonary stenosis, and tricuspid regurgitation. Among the neonates with CHD, 55 subjects were females and 92 cases were males. There was CHD history in previous siblings in 10 cases. In 73 neonates with CHD, the mother had not taken folic acid in the first trimester of pregnancy. A total of 14.5% of the hospitalized neonates suffered from innocent murmur, and the rest with heart murmur had abnormal echocardiography and suffered from CHD (85.5%). Heart murmur in neonates could be a symptom of CHD, and timely echocardiography is very important in diagnosing the type of disease.

Does Echocardiography Have a Role in the Cardiologist's Diagnosis of Innocent Murmurs in Childhood?

BACKGROUND

Innocent murmurs are common in childhood. Echocardiography may diagnose almost all congenital cardiac abnormalities. Earlier studies have suggested that it may be unnecessary when a clinical diagnosis of an innocent murmur is made by an experienced cardiologist. Yet, echocardiography is commonly performed despite such a diagnosis. Is that justifiable?

METHODS

Patients referred to a paediatric cardiologist for evaluation of a murmur were assessed. If an innocent murmur was clinically diagnosed, an echocardiogram and an electrocardiogram were ordered when requested. The cardiologist completed a questionnaire documenting the reasons for the investigations and his degree of confidence in the clinical diagnosis. The parents and patients were informed of the diagnosis and the results of the investigations.

RESULTS

In almost all 62 cases whose murmurs were clinically considered to be innocent, the referring doctor expected an echocardiogram to be performed. Following echocardiography, one patient was found to have a small muscular ventricular septal defect. On review, the murmur was consistent with that diagnosis. Three (3) others had abnormal echocardiograms namely congenitally corrected transposition of great arteries, partial anomalous right upper lobe pulmonary vein, and left ventricular non-compaction. All on review were still considered clinically to have innocent murmurs.

CONCLUSIONS

Despite the competency of the cardiologist, echocardiography diagnosed important but relatively uncommon cardiac abnormalities with prognostic implications that would have been missed if only the clinical examination was performed. Over and above the referring doctor's expectations for an echocardiogram to be performed is the need for the cardiologist to provide a complete and definitive diagnosis.

Yield of Echocardiogram and Predictors of Positive Yield in Pediatric Patients: A Study in an Urban, Community-Based Outpatient Pediatric Cardiology Clinic

The yield of outpatient echocardiograms varies based on the indication for the echocardiogram and the age of the patient. The purpose of this study was to determine the cumulative yield of outpatient echocardiograms by age group and reason for the test. A secondary aim was to determine the predictors of a positive echocardiogram in an outpatient cardiology clinic at a large community teaching hospital. We retrospectively reviewed the charts of 891 patients who had a first-time echocardiogram between 2011 and 2015. Positive yield was defined as echocardiographic findings that explained the reason for the echocardiogram. The overall positive yield was 8.2%. Children between birth and 3 months of age had the highest yield (34.2%), and children between 12 and 18 years of age had the lowest yield (1%). Patients with murmurs (18.1%) had the highest yield compared with patients with other signs or symptoms. By age group and reason, the highest yields were as follows: 0 to 3 months of age, murmur (39.2%); 4 to 11 months of age, >1 symptom (50%); and 1 to 5 years of age, shortness of breath (66.7%). Based on our study, the overall yield of echocardiograms in the outpatient pediatric setting is low. Age and symptoms should be considered before ordering an echocardiogram.

Factors Influencing Pediatric Outpatient Transthoracic Echocardiography Utilization Before Appropriate Use Criteria Release: A Multicenter Study

BACKGROUND

Although pediatric appropriate use criteria (AUC) for outpatient transthoracic echocardiography (TTE) are available, little is known about TTE utilization patterns before their release. The aims of this study were to determine the relation between AUC and TTE utilization and to identify patient and physician factors associated with discordance between the AUC and clinical practice.

METHODS

A retrospective review of 3,000 initial outpatient pediatric cardiology encounters at six centers was performed. Investigator-determined indications were classified using AUC definitions. Concordance between AUC and TTE utilization was determined. Multivariate analysis was performed to identify patient and physician factors associated with TTE's being performed for rarely appropriate and TTE's not being performed for appropriate indications.

RESULTS

Concordance between AUC and TTE utilization was 88%. TTE was performed for rarely appropriate indications in 9% and was associated with patient age < 3 months, indications of murmur, noninvasive imaging physician subspecialty, and physician volume. No TTE was ordered for appropriate indications in 3% and was associated with indications including prior test result (primarily abnormal electrocardiographic findings), older patients, and physician subspecialty other than generalist or imaging. There was high variability in TTE utilization among centers.

CONCLUSIONS

There was a reasonable degree of concordance between AUC and clinical practice before AUC publication. Several patient and physician factors were associated with discordance with the AUC. These findings should be considered in efforts to disseminate the AUC and in the development of future iterations. The causes for variation among centers deserve further exploration.

Prevalence and diagnostic accuracy of heart disease in children with asymptomatic murmurs

This study was performed to determine the prevalence of CHD among children referred with asymptomatic murmurs and to determine the diagnostic accuracy of the assessment of asymptomatic heart murmurs by general paediatricians. We reviewed the records of children who had been referred by general paediatricians to a cardiology clinic for further evaluation of a heart murmur. The referring paediatricians' clinical assessment of the murmur was compared with the cardiologist's echocardiographic diagnosis. A total of 150 children were referred by paediatricians to a paediatric cardiologist for further assessment of a heart murmur. Out of 150 children, 72 had a paediatrician's diagnosis of innocent murmur; of these 72 patients, two (3%) had heart disease on echocardiography. In all, after echocardiography, a range of congenital heart lesions was found in 28 (19%) of the 150 children. CHD is not rare among children with asymptomatic heart murmurs. In this series of children with asymptomatic murmurs, 19% had heart lesions on echocardiography. Most, but not all, of the children with heart lesions were identified on clinical examination by general paediatricians.

Serum troponin-I as an indicator of clinically significant myocardial injury in paediatric trauma patients

Myocardial injury is a cause of mortality in paediatric trauma, but it is often difficult to diagnose. The objectives of this pilot study were to (1) determine the prevalence of elevated cardiac troponin I (TnI) in paediatric trauma patients and (2) to determine whether elevated TnI correlates with clinically significant myocardial injury, defined as abnormalities on echocardiogram (ECHO) and/or electrocardiograms (ECG). To this end, we investigated a convenient sample size of 59 paediatric trauma patients with an Injury Severity Score (ISS)>12. TnI and creatine kinase-MB (CK-MB) were measured on admission, at then at regular intervals until TnI had normalized. Patients with elevated TnI levels had an ECHO performed within 24h of admission and underwent daily ECGs until TnI normalized. Elevated serum TnI was found in n=16/59 (27%; 95% CI: 18-40%) patients and was associated with elevated CK-MB in all cases. Abnormal ECHOs were seen in 4/16 patients with elevated TnI, but peak TnI values did not correlate with abnormalities on ECHO (p=0.23). Only 1 patient had a clinically significant, albeit mild, decrease in cardiac function. All ECGs were normal. Patients with elevated TnI were more likely to be intubated (p=0.04), to have higher Injury Severity Scores (p=0.02), required more resuscitation fluid (p=0.001), and to have thoracic injuries (p<0.001). Our data indicates that the prevalence of elevated TnI in paediatric trauma patients is 27%; and whilst elevated TnI reflects overall trauma severity, it is frequently elevated without a clinically significance myocardial injury. Hence, large scale studies are required to determine if an elevated threshold TnI value can be identified to accurately diagnose severe myocardial injury in paediatric trauma.

Prevalence of undiagnosed congenital cardiac defects in older children

BACKGROUND

Certain congenital cardiac defects may go undetected for several years due to lack of symptoms and signs. Our purpose was to determine the prevalence of such defects among children greater than one year of age.

METHODS

The study was performed on subjects diagnosed with systemic hypertension, aged from 1 to 19 years, with a mean of 12.4 years, in whom we performed echocardiography, using a standard protocol, to establish any end-organ damage or to reveal any congenital cardiac defects.

RESULTS

We found a congenital cardiac defect in 5 (3.5%) of the 143 children evaluated. Of these, 4 had not previously been detected, specifically Ebsteins malformation of the tricuspid valve, with moderate regurgitation, a coronary arterial anomaly, a bicuspid aortic valve, and prolapse of the mitral valve permitting regurgitation. In the other patient, we found a non-significant tiny muscular ventricular septal defect.

CONCLUSIONS

Our transthoracic echocardiographic investigation revealed previously unsuspected congenital cardiac defects in 4 of 143 older children, with 3 of these requiring further management by a paediatric cardiologist. A similar prevalence has also been reported in older children evaluated echocardiographically for other diseases such as insulin-resistance and leukemia. Hence, it is possible that the prevalence of congenitally malformed hearts is higher than previously reported. When clinically indicated, clinicians should more readily consider obtaining an echocardiogram to help in the identification of such malformations.

Digital phonocardiography as a screening tool for heart disease in childhood

AIM

To evaluate the performance of experienced cardiologists by use of digital phonocardiography for the correct identification of heart disease and innocent murmurs in children.

METHODS

Two independent paediatric cardiologists blindly evaluated 83 digital phonocardiograms obtained from consecutive paediatric cardiology outpatients. Each observer had to document the presence and characteristics of murmurs (intensity, quality, location), the presence of additional abnormal auscultatory findings (systolic click, second heart tone abnormalities) and whether he would recommend echocardiography (ECHO). The accuracy of their diagnoses was tested against the ECG diagnosis within two severity levels of heart disease.

RESULTS

Twenty-three out of 24 cases (95.8%) with moderate-to-severe heart defects and 12 to 13 out of 19 cases (63.2%-68.4%) with trivial-to-mild heart defects were correctly identified by phonocardiography. Additionally, 37 to 38 out of 40 cases (92.5%-95.0%) without ECHO evidence of heart disease were correctly interpreted as having innocent murmurs. The level of agreement between the two observers was substantial regarding their recommendations for ECHO (kappa, kappa=0.83) and in identifying abnormal murmurs (kappa=0.78).

CONCLUSION

Evaluation of digital phonocardiography by experienced cardiologists could allow for correct identification of moderate-to-severe forms of heart disease while preventing the majority of children with innocent murmurs from unnecessary referral.

Phono-spectrographic analysis of heart murmur in children

BACKGROUND

More than 90% of heart murmurs in children are innocent. Frequently the skills of the first examiner are not adequate to differentiate between innocent and pathological murmurs. Our goal was to evaluate the value of a simple and low-cost phonocardiographic recording and analysis system in determining the characteristic features of heart murmurs in children and in distinguishing innocent systolic murmurs from pathological.

METHODS

The system consisting of an electronic stethoscope and a multimedia laptop computer was used for the recording, monitoring and analysis of auscultation findings. The recorded sounds were examined graphically and numerically using combined phono-spectrograms. The data consisted of heart sound recordings from 807 pediatric patients, including 88 normal cases without any murmur, 447 innocent murmurs and 272 pathological murmurs. The phono-spectrographic features of heart murmurs were examined visually and numerically. From this database, 50 innocent vibratory murmurs, 25 innocent ejection murmurs and 50 easily confusable, mildly pathological systolic murmurs were selected to test whether quantitative phono-spectrographic analysis could be used as an accurate screening tool for systolic heart murmurs in children.

RESULTS

The phono-spectrograms of the most common innocent and pathological murmurs were presented as examples of the whole data set. Typically, innocent murmurs had lower frequencies (below 200 Hz) and a frequency spectrum with a more harmonic structure than pathological cases. Quantitative analysis revealed no significant differences in the duration of S1 and S2 or loudness of systolic murmurs between the pathological and physiological systolic murmurs. However, the pathological murmurs included both lower and higher frequencies than the physiological ones (p < 0.001 for both low and high frequency limits). If the systolic murmur contained intensive frequency components of over 200 Hz, or its length accounted for over 80 % of the whole systolic duration, it was considered pathological. Using these criteria, 90 % specificity and 91 % sensitivity in screening were achieved.

CONCLUSION

Phono-spectrographic analysis improves the accuracy of primary heart murmur evaluation and educates inexperienced listener. Using simple quantitative criterias a level of pediatric cardiologist is easily achieved in screening heart murmurs in children.

Accuracy of the initial evaluation of heart murmurs in neonates: do we need an echocardiogram?

The objective of this study was to determine the differences between neonatologists and pediatric cardiologists with regards to the initial assessment of neonatal heart murmur and to evaluate the role of echocardiography in this group of patients. During a period of 1 year, all neonates with heart murmur seen in pediatric cardiology consultation from neonatal intensive care units at the Children Hospital of Eastern Ontario and Ottawa General Hospital were included in this study. Neonates with heart murmur were initially evaluated clinically by a neonatologist and the most likely clinical diagnosis was recorded. This was followed by similar evaluation and assessment by the pediatric cardiologist, who did not know the result of the previous assessment. Echocardiography diagnosis was considered the gold standard for the accurate diagnosis in the two groups, and it was done for all patients. For the neonatologists, the sensitivity to detect a pathological murmur was 78% and the specificity was 33%; the positive predictive value was 77% and the negative predictive value was 37%. For the pediatric cardiologists, the accuracy of the clinical examination showed a sensitivity of 83% in detecting a pathological murmur and a specificity of 25%; the positive predictive value was 80% and the negative predictive value was 29%. There was no significant difference between the two groups. Certified neonatologists are able to assess the significance of neonatal heart murmurs well as pediatric cardiologists, although echocardiogram is still needed to reach the accurate diagnosis of congenital heart disease in neonates even if a pediatric cardiologist is consulted.