Evaluation of cardiac auscultation skills in pediatric residents

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

OBJECTIVE

To develop a deep learning algorithm to perform multi-class classification of normal pediatric heart sounds, innocent murmurs, and pathologic murmurs.

METHODS

We 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.

RESULTS

Our 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.

CONCLUSION

We 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.

Paediatric resident identification of cardiac emergencies

OBJECTIVES

Critical CHD is associated with morbidity and mortality, worsened by delayed diagnosis. Paediatric residents are front-line clinicians, yet identification of congenital CHD remains challenging. Current exposure to cardiology is limited in paediatric resident education. We evaluated the impact of rapid cycle deliberate practice simulation on paediatric residents' skills, knowledge, and perceived competence to recognise and manage infants with congenital CHD.

METHODS

We conducted a 6-month pilot study. Interns rotating in paediatric cardiology completed a case scenario assessment during weeks 1 and 4 and participated in paired simulations (traditional debrief and rapid cycle deliberate practice) in weeks 2-4. We assessed interns' skills during the simulation using a checklist of "cannot miss" tasks. In week 4, they completed a retrospective pre-post knowledge-based survey. We analysed the data using summary statistics and mixed effect linear regression.

RESULTS

A total of 26 interns participated. There was a significant increase in case scenario assessment scores between weeks 1 and 4 (4, interquartile range 3-6 versus 8, interquartile range 6-10; p-value < 0.0001). The percentage of "cannot miss" tasks on the simulation checklist increased from weeks 2 to 3 (73% versus 83%, p-value 0.0263) and from weeks 2-4 (73% versus 92%, p-value 0.0025). The retrospective pre-post survey scores also increased (1.67, interquartile range 1.33-2.17 versus 3.83, interquartile range 3.17-4; p-value < 0.0001).

CONCLUSION

Rapid cycle deliberate practice simulations resulted in improved recognition and initiation of treatment of simulated infants with congenital CHD among paediatric interns. Future studies will include full implementation of the curriculum and knowledge retention work.

Breath Measurement Method for Synchronized Reproduction of Biological Tones in an Augmented Reality Auscultation Training System

An educational augmented reality auscultation system (EARS) is proposed to enhance the reality of auscultation training using a simulated patient. The conventional EARS cannot accurately reproduce breath sounds according to the breathing of a simulated patient because the system instructs the breathing rhythm. In this study, we propose breath measurement methods that can be integrated into the chest piece of a stethoscope. We investigate methods using the thoracic variations and frequency characteristics of breath sounds. An accelerometer, a magnetic sensor, a gyro sensor, a pressure sensor, and a microphone were selected as the sensors. For measurement with the magnetic sensor, we proposed a method by detecting the breathing waveform in terms of changes in the magnetic field accompanying the surface deformation of the stethoscope based on thoracic variations using a magnet. During breath sound measurement, the frequency spectra of the breath sounds acquired by the built-in microphone were calculated. The breathing waveforms were obtained from the difference in characteristics between the breath sounds during exhalation and inhalation. The result showed the average value of the correlation coefficient with the reference value reached 0.45, indicating the effectiveness of this method as a breath measurement method. And the evaluations suggest more accurate breathing waveforms can be obtained by selecting the measurement method according to breathing method and measurement point.

A randomized, controlled trial of an innovative, multimedia instructional program for acquiring auditory skill in identifying pediatric heart murmurs

Objective

To create a brief, acceptable, innovative method for self-paced learning to enhance recognition of pediatric heart murmurs by medical students, and to demonstrate this method's effectiveness in a randomized, controlled trial.

Materials and methods

A curriculum of six 10-min online learning modules was designed to enable deliberate practice of pediatric cardiac auscultation, using recordings of patients' heart murmurs. Principles of andragogy and multimedia learning were applied to optimize acquisition of this skill. A pretest and posttest, given 4 weeks apart, were created using additional recordings and administered to 87 3rd-year medical students during their pediatric clerkship. They were randomized to have access to the modules after the pretest or after the posttest, and asked to use at least the first 2 of the modules.

Results

47 subjects comprised the Intervention group, and 40 subjects the Control group. On our primary outcome, distinguishing innocent from pathological with at least moderate confidence, the posttest scores were significantly higher for the Intervention group (60.5%) than for the Control group (20.0%). For our secondary outcomes, the 2 groups also differed significantly in the ability to distinguish innocent from pathological murmurs, and in identifying the actual diagnosis. On all 3 outcomes, those Intervention group subjects who accessed 4-6 modules scored higher than those who accessed 0-3 modules, who in turn scored higher than the Control group.

Summary

Applying current principles of adult learning, we have created a teaching program for medical students to learn to recognize common pediatric murmurs. Its effectiveness was demonstrated in a randomized, controlled trial. The program results in a meaningful gain in this skill from 1 h of self-paced training with high acceptance to learners.

Evaluating the baseline auscultation abilities of second-year chiropractic students using simulated patients and high-fidelity manikin simulators: A pilot study

OBJECTIVE

To assess the ability of 2nd-year students to identify normal and abnormal findings during cardiac and lung auscultation using high-fidelity manikin simulators and standardized patients. A secondary objective was to assess students' perceived competence and confidence in their abilities.

METHODS

This was a descriptive pilot study of randomly selected 2nd-year students at 1 chiropractic training program. Participants were asked to perform cardiac and lung auscultation on high-fidelity manikins (2 stations) and standardized human patients (2 stations) with normal and abnormal auscultation sounds. Participants described the auscultated sound as "abnormal" or "normal" and were also asked to score their confidence in describing the sound and competence in performing auscultation on a 100-mm visual analog scale. Descriptive statistics were calculated for all study variables.

RESULTS

Thirty-two students (23 women and 9 men) were included. For lung auscultation, 15.6% were incorrect on the human subject and 6.2% were incorrect on the manikin. For cardiac auscultation, 62.5% were incorrect on the human subject and 40.6% were incorrect on the manikin. Confidence mean scores ranged from 34.8 to 60. Competence mean scores ranged from 34.8 to 50.

CONCLUSION

Results identified that 2nd-year students from 1 institution were correct in identifying an abnormal sound during lung auscultation but reported low levels of perceived competence or confidence in their responses. They performed poorly on cardiac auscultation and reported low perceived confidence and competence in their abilities to perform cardiac auscultation and identify sounds.

Accuracy of physical examination of cardiovascular system in the diagnosis of common congenital heart diseases in children

BACKGROUND

It is widely perceived that the value of physical examination in paediatric cardiology has diminished with the increasing availability of echocardiography. The accuracy of physical examination of cardiovascular system in children has not been systematically tested.

METHODS

This is a cross-sectional, diagnostic accuracy study from the paediatric cardiology clinic of a tertiary referral hospital in South India. A total of 545 children with 5 common cardiac conditions were included-normal heart, atrial septal defect, patent ductus arteriosus, ventricular septal defect (VSD) and VSD with pulmonic stenosis. Physical examination was documented by a paediatric cardiology fellow and a consultant who were blinded to previous investigations and to each other. The accuracy of physical examination of the fellow and the consultant was determined for each patient group by comparing with echocardiography. Interobserver agreement was calculated using kappa statistics.

RESULTS

Physical examination differentiated normal hearts from abnormal with an accuracy of 95.0% for fellows and 96.3% for consultants. For all abnormal hearts, the results for fellows and consultants, respectively, were as follows: sensitivity: 94.3%, 94.9%, specificity: 96.2%, 98.6%, accuracy: 95.0%, 96.3%, positive likelihood ratio: 24.8, 66.4 and negative likelihood ratio: 0.06, 0.05. There was good agreement between fellows and consultant for all patient groups (kappa: 0.72-1), except for large VSD (kappa: 0.232). Younger age and haemodynamically insignificant lesions were associated with incorrect diagnosis.

CONCLUSION

This study underscores the utility of clinical examination in initial screening for commonly encountered congenital cardiac conditions even in the current era of echocardiography.

Virtual auscultation course via video chat in times of COVID-19 improves cardiac auscultation skills compared to literature self-study in third-year medical students: a prospective randomized controlled cross-over study

BACKGROUND

Cardiac auscultation is a core clinical skill taught in medical school. Due to contact restrictions during the SARS-CoV-2 pandemic, interaction with patients was very limited. Therefore, a peer-to-peer virtual case-based auscultation course via video conference was established.

METHODS

A randomized controlled cross-over study was conducted to evaluate whether participation in a virtual auscultation course could improve heart auscultation skills in 3^rd-year medical students. A total of sixty medical students were randomly assigned to either the experimental or control group after informed consent was obtained. Due to no-shows, 55 students participated. Depending on allocation, students attended three ninety-minute courses in intervals of one week in a different order: a virtual case-based auscultation course held via video chat, literature self-study, and an on-site course using a high-fidelity auscultation simulator (SAM II). The study's primary endpoint was the performance of the two groups at the simulator after participating in the virtual auscultation course or literature self-study. To evaluate their auscultation skills, students participated in five assessments using the same six pathologies: stenosis and regurgitation of the aortic and mitral valve, ventricular septal defect, and patent ductus arteriosus. Moreover, participants rated their satisfaction with each course and provided a self-assessment of competence.

RESULTS

Compared to literature self-study, participation in the virtual auscultation course led to a significantly improved description of heart murmurs at the auscultation simulator with regard to the presence in systole and diastole, low- and high-pitched sounds, and volume dynamics. There was no significant difference between the groups in diagnostic accuracy and identification of the point of maximal intensity. After the virtual course, students showed higher satisfaction rates and a higher increase in self-assessed competence compared to participants who engaged in literature self-study.

CONCLUSIONS

For the first time, this study demonstrates that a case-based virtual auscultation course can improve aspects of cardiac auscultation skills on a simulator. This may facilitate the further acquisition of an essential clinical skill, even when contact restrictions will be lifted.

The Effect of Signal Duration on the Classification of Heart Sounds: A Deep Learning Approach

Deep learning techniques are the future trend for designing heart sound classification methods, making conventional heart sound segmentation dispensable. However, despite using fixed signal duration for training, no study has assessed its effect on the final performance in detail. Therefore, this study aims at analysing the duration effect on the commonly used deep learning methods to provide insight for future studies in data processing, classifier, and feature selection. The results of this study revealed that (1) very short heart sound signal duration (1 s) weakens the performance of Recurrent Neural Networks (RNNs), whereas no apparent decrease in the tested Convolutional Neural Network (CNN) model was found. (2) RNN outperformed CNN using Mel-frequency cepstrum coefficients (MFCCs) as features. There was no difference between RNN models (LSTM, BiLSTM, GRU, or BiGRU). (3) Adding dynamic information (∆ and ∆²MFCCs) of the heart sound as a feature did not improve the RNNs' performance, and the improvement on CNN was also minimal (≤2.5% in MAcc). The findings provided a theoretical basis for further heart sound classification using deep learning techniques when selecting the input length.

Dysphagia management: Does structured training improve the validity and reliability of cervical auscultation?

Purpose: Cervical auscultation (CA) uses a stethoscope or microphone to complement the clinical swallow examination by interpreting swallowing sounds and swallow-respiratory coordination. This study investigated the effects of structured CA training on CA-rating agreement with Flexible Endoscopic Evaluation of Swallowing (FEES) and CA rater reliability.Method: Thirty-nine speech-language pathologists participated in a structured CA training course at Gothenburg University. They rated nine swallow-respiratory sound recordings which were simultaneously recorded during FEES. Swallow sounds were rated six weeks prior to the CA-workshop using two binary yes/no questions, (1) Safe, (2) Dysphagia, and a third Dysphagia Severity rating. Swallow sounds were rated again (re-randomised) one month post CA-workshop.Result: Agreement with FEES (validity) improved significantly (p < 0.05) pre-post training for the Safe and Dysphagia questions, with post training sensitivities >90% and specificities at 76% and 85% respectively. Dysphagia severity rating improved non-significantly. Intra-rater reliability improved significantly with kappa statistics >0.90 post training. Improvements for inter-rater reliability were noted, though non-significant.Conclusion: Results demonstrate that with structured training, the validity of CA (to detect a Safe/Dysphagic swallow) significantly improves, as does intra-rater reliability. This is congruent with literature identifying the positive effects of structured training improving instrumental dysphagia assessment.

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.

The Simulated Cardiology Clinic: A Standardized Patient Exercise Supporting Medical Students' Biomedical Knowledge and Clinical Skills Integration

INTRODUCTION

Development of cardiac disease-related diagnostic skills-including hypothesis-driven data gathering, heart sound interpretation, and ECG interpretation-is an important component of medical student training. Prior studies indicate trainees' performance of these skills is limited. Simulation provides students with opportunities to practice integrating their developing knowledge in a relevant clinical context. We developed a simulated clinic activity for second-year medical students consisting of standardized patient (SP) cases representing cardiovascular (CV) diseases.

METHODS

Student small groups rotated through four SP encounters. For each case, one student performed the history, after which the whole small group listened to audio files of heart sounds, interpreted an ECG, and collaboratively developed a prioritized differential diagnosis. The CV course director met with students for a large-group debrief, highlighting key learning points. We collected learners' evaluations of the event through an online survey.

RESULTS

Of students, 276 participated in this activity over the course of 2 years. Nearly all students assessed the activity as extremely or quite effective for applying learning content from the CV course (97%, 2018; 93%, 2019), and for practicing how to approach chest pain, shortness of breath, palpitations, and fatigue (100%, 2018; 95%, 2019). The most helpful aspects were reinforcement of CV disease illness scripts, hypothesis-driven data gathering practice, ECG interpretation, and applying knowledge and skills in a realistic context.

DISCUSSION

SP encounters representing CV conditions can effectively provide opportunities for students to integrate basic science knowledge and clinical skills. Students assessed the activity as helpful and engaging.

Artificial intelligence-aided decision support in paediatrics clinical diagnosis: development and future prospects

Artificial intelligence (AI)-aided decision support has developed rapidly to meet the needs for effective analysis of substantial data sets from electronic medical records and medical images generated daily, and computer-assisted intelligent drug design. In clinical practice, paediatricians make medical decisions after obtaining a large amount of information about symptoms, physical examinations, laboratory test indicators, special examinations and treatments. This information is used in combination with paediatricians' knowledge and experience to form the basis of clinical decisions. This diagnosis and therapeutic strategy development based on large amounts of information storage can be applied to both large clinical databases and data for individual patients. To date, AI applications have been of great value in intelligent diagnosis and treatment, intelligent image recognition, research and development of intelligent drugs and intelligent health management. This review aims to summarize recent advances in the research and clinical use of AI in paediatrics.

Developing Physical Exam Skills in Residency: Comparing the Perspectives of Residents and Faculty About Values, Barriers, and Teaching Methods

BACKGROUND

The physical examination (PE) skills of residents are often not improved since medical school. Unfortunately, how residents learn PE is not well understood. There is a paucity of research on the factors involved and the differences between resident and faculty perspectives. The authors sought to determine resident and faculty perceptions about the value of PE, the major barriers to learning PE, and the most effective teaching methods.

METHODS

Based on a rigorous process of literature review and semi-structured interviews, the authors developed an online survey which was sent to 406 internal medicine residents and 93 faculty at 3 institutions. Residents and faculty answered questions about both their own opinions and about their perception of the other group's opinions.

RESULTS

About 283 residents (70%) and 61 faculty (66%) completed the survey. Both residents and faculty rated the importance of PE similarly. Residents rated being too busy, followed by a lack of feedback, as the most significant barriers to learning PE. Faculty rated a lack of feedback, followed by a lack of resident accountability, as the most significant barriers. Both groups rated the availability of abnormal findings as the least significant barrier. Both groups agreed that faculty demonstration at the bedside was the most effective teaching method.

CONCLUSION

This survey can serve as a needs assessment for educational interventions to improve the PE skills of residents by focusing on areas of agreement between residents and faculty, specifically faculty demonstration at the bedside combined with feedback about residents' skills.

Cardiac Auscultation Lab Using a Heart Sounds Auscultation Simulation Manikin

INTRODUCTION

Cardiac auscultation skills are essential to the development of a competent physician. We created a hypothesis-driven cardiac auscultation laboratory session utilizing a high-fidelity simulator to teach these skills to second-year medical students at our institution. This program was grounded in deliberate practice opportunities to aid in the acquisition of cardiac auscultation skills.

METHODS

This session aimed to help students identify and discriminate between normal and pathologic heart sounds in the context of a clinical vignette. Faculty facilitators guided students through unknown patient cases and utilized the auscultation manikin to simulate corresponding heart sounds. Time was also allotted for students to auscultate the manikins and practice their cardiac physical examination skills.

RESULTS

This program has been in place at our institution since 2016 and has been well received by students and facilitators. Since its initial introduction in 2016, 183 second-year medical students have completed the cardiac auscultation lab session each year, for a total of 549 students. Evaluations of the session have improved as faculty have become more familiar with the mechanics of operating the auscultation manikin.

DISCUSSION

The cardiac exam and heart sounds lab can be adapted to any simulator model that is capable of producing heart sounds and can be done in a large- or small-group format. Enough time should be allotted to adequately work through all components of the laboratory. Student and faculty feedback has helped us further refine the session since its initial introduction to the curriculum.

Artificial Intelligence-Assisted Auscultation of Heart Murmurs: Validation by Virtual Clinical Trial

Artificial intelligence (AI) has potential to improve the accuracy of screening for valvular and congenital heart disease by auscultation. However, despite recent advances in signal processing and classification algorithms focused on heart sounds, clinical acceptance of this technology has been limited, in part due to lack of objective performance data. We hypothesized that a heart murmur detection algorithm could be quantitatively and objectively evaluated by virtual clinical trial. All cases from the Johns Hopkins Cardiac Auscultatory Recording Database (CARD) with either a pathologic murmur, an innocent murmur or no murmur were selected. The test algorithm, developed independently of CARD, analyzed each recording using an automated batch processing protocol. 3180 heart sound recordings from 603 outpatient visits were selected from CARD. Algorithm estimation of heart rate was similar to gold standard. Sensitivity and specificity for detection of pathologic cases were 93% (CI 90-95%) and 81% (CI 75-85%), respectively, with accuracy 88% (CI 85-91%). Performance varied according to algorithm certainty measure, age of patient, heart rate, murmur intensity, location of recording on the chest and pathologic diagnosis. This is the first reported comprehensive and objective evaluation of an AI-based murmur detection algorithm to our knowledge. The test algorithm performed well in this virtual clinical trial. This strategy can be used to efficiently compare performance of other algorithms against the same dataset and improve understanding of the potential clinical usefulness of AI-assisted auscultation.

Cardiac auscultation poorly predicts the presence of valvular heart disease in asymptomatic primary care patients

Objective

Cardiac auscultation is a key clinical skill, particularly for the diagnosis of valvular heart disease (VHD). However, its utility has declined due to the widespread availability of echocardiography and diminishing emphasis on the importance of clinical examination. We aim to determine the contemporary accuracy of auscultation for diagnosing VHD in primary care.

Methods

Cardiac auscultation was undertaken by one of two experienced general practitioners (primary care/family doctors) in a subset of 251 asymptomatic participants aged >65 years undergoing echocardiography within a large community-based screening study of subjects with no known VHD. Investigators were blinded to the echocardiographic findings. Newly detected VHD was classified as mild (mild regurgitation of any valve or aortic sclerosis) or significant (at least moderate regurgitation or mild stenosis of any valve).

Results

Newly identified VHD was common, with mild disease in 170/251 participants (68%) and significant disease in 36/251 (14%). The sensitivity of auscultation was low for the diagnosis of mild VHD (32%) but slightly higher for significant VHD (44%), with specificities of 67% and 69%, respectively. Likelihood ratios were not statistically significant for the diagnosis of either mild or significant VHD in the overall cohort, but showed possible value for auscultation in non-overweight subjects (body mass index <25 kg/m2).

Conclusion

Cardiac auscultation has limited accuracy for the detection of VHD in asymptomatic patients and is a poor diagnostic screening tool in primary care, particularly for overweight subjects. Ensuring easy access to echocardiography in patients with symptoms suggesting VHD is likely to represent a better diagnostic strategy.

[Heart murmur in children less than 2 years-old: looking for a safe and effective referral strategy]

INTRODUCTION

Current guidelines in Spain recommend performing transthoracic echocardiography (TTE) in all children under 2 years of age with a heart murmur. In 2014, the American Paediatric Association published the first appropriate use criteria (AUC) for outpatient paediatric transthoracic echocardiography (TTE) to promote its cost-efficient use. The aim of this article is to analyse the AUC and other clinical factors as predictors of congenital heart disease (CHD) in children less than 2 years of age with a heart murmur, and to develop a safe and efficient referral strategy.

PATIENTS AND METHOD

Case-control study conducted with children less than 2 years of age, referred from Paediatric Primary Care to Paediatric Cardiology during a 4-year study. A predictive model for CHD was determined using multivariate analysis.

RESULTS

A total of 688 patients were included, with 129 (19%) cases of CHD. An age less than 3 months (adjusted odds ratio [ORa] 3.8 [1.5-8.4], p=.030) and fulfilling AUC (ORa 16.3 [9.4-28.3], p<.001) were predictors of CHD. Concurrent infection (ORa 0.6 [0.2-0.8], p<.001) and a negative neonatal screening with pulse oximetry (ORa 0.1 [0.05-0.4], p=.001) decreased the risk of CHD. The referral strategy that included these criteria had a 98% sensitivity, 39% specificity, and positive and negative predictive values of 27% and 99%, respectively. It could not diagnose 2% of CHD (all mild), and showed a 32% TTE reduction rate compared to our current strategy.

CONCLUSION

To refer children less than 3 months old, fulfilling AUC, without a concurrent infection, or without negative neonatal pulse oximetry screening, is a safe and efficient strategy for the management of heart murmur in children under 2 years of age.

Cardiac Auscultation in the Modern Era: Premature Requiem or Phoenix Rising?

Competent cardiac auscultation remains a most important skill for the detection of heart disease. Currently it is poorly taught and often ignored or poorly performed, resulting in inaccurate and inefficient patient assessments. This review documents that teaching can be over 90% effective with new, proven teaching methods emphasizing repetition and normal-abnormal comparisons of sounds, using computer-aided and online resources. At present, these concepts are not widely adopted by medical schools. Our current knowledge of teaching heart auscultation is critically reviewed, including traditional bedside, clinic and classroom settings, as well as computer, simulator, and multimedia-based learning. The assessment of auscultation skill in the learning process. The adoption of competence-based learning promises to integrate the assessment of auscultation skill in the learning process. Newer teaching methods, such as auditory training and repetitive listening, offer excellent murmur recognition and diagnosis learning, and hand-held ultrasound is proposed as a helpful adjunct to teaching auscultation. Although ongoing research remains important to develop better teaching methods, the adoption of proven existing concepts has great potential to improve teaching and practice of this valuable skill.

AMSSM Position Statement on Cardiovascular Preparticipation Screening in Athletes: Current Evidence, Knowledge Gaps, Recommendations and Future Directions

Cardiovascular screening in young athletes is widely recommended and routinely performed prior to participation in competitive sports. While there is general agreement that early detection of cardiac conditions at risk for sudden cardiac arrest and death (SCA/D) is an important objective, the optimal strategy for cardiovascular screening in athletes remains an issue of considerable debate. At the center of the controversy is the addition of a resting electrocardiogram (ECG) to the standard preparticipation evaluation using history and physical examination. The American Medical Society for Sports Medicine (AMSSM) formed a task force to address the current evidence and knowledge gaps regarding preparticipation cardiovascular screening in athletes from the perspective of a primary care sports medicine physician. The absence of definitive outcomes-based evidence at this time precludes AMSSM from endorsing any single or universal cardiovascular screening strategy for all athletes, including legislative mandates. This statement presents a new paradigm to assist the individual physician in assessing the most appropriate cardiovascular screening strategy unique to their athlete population, community needs, and resources. The decision to implement a cardiovascular screening program, with or without the addition of ECG, necessitates careful consideration of the risk of SCA/D in the targeted population and the availability of cardiology resources and infrastructure. Importantly, it is the individual physician's assessment in the context of an emerging evidence-base that the chosen model for early detection of cardiac disorders in the specific population provides greater benefit than harm. AMSSM is committed to advancing evidenced-based research and educational initiatives that will validate and promote the most efficacious strategies to foster safe sport participation and reduce SCA/D in athletes.

In defence of auscultation: a glorious future?

Auscultation of the heart using a simple stethoscope continues to be a central aspect of the cardiovascular examination despite declining proficiency and availability of competing technologies such as hand-held ultrasound. In the ears and mind of a trained cardiologist, heart sounds can provide important information to help screen for certain diseases such as valvar lesions and many congenital defects. Using emerging technology, auscultation is poised to undergo a transformation that will simultaneously improve the teaching and evaluation of this important clinical skill and create a new generation of smart stethoscopes, capable of assisting the clinician in quickly and confidently screening for heart disease. These developments have important implications for global health, screening of athletes and recognition of congenital heart disease.

AMSSM Position Statement on Cardiovascular Preparticipation Screening in Athletes: Current evidence, knowledge gaps, recommendations and future directions

Cardiovascular screening in young athletes is widely recommended and routinely performed prior to participation in competitive sports. While there is general agreement that early detection of cardiac conditions at risk for sudden cardiac arrest and death (SCA/D) is an important objective, the optimal strategy for cardiovascular screening in athletes remains an issue of considerable debate. At the centre of the controversy is the addition of a resting ECG to the standard preparticipation evaluation using history and physical examination. The American Medical Society for Sports Medicine (AMSSM) formed a task force to address the current evidence and knowledge gaps regarding preparticipation cardiovascular screening in athletes from the perspective of a primary care sports medicine physician. The absence of definitive outcome-based evidence at this time precludes AMSSM from endorsing any single or universal cardiovascular screening strategy for all athletes, including legislative mandates. This statement presents a new paradigm to assist the individual physician in assessing the most appropriate cardiovascular screening strategy unique to their athlete population, community needs and resources. The decision to implement a cardiovascular screening programme, with or without the addition of ECG, necessitates careful consideration of the risk of SCA/D in the targeted population and the availability of cardiology resources and infrastructure. Importantly, it is the individual physician's assessment in the context of an emerging evidence base that the chosen model for early detection of cardiac disorders in the specific population provides greater benefit than harm. AMSSM is committed to advancing evidenced-based research and educational initiatives that will validate and promote the most efficacious strategies to foster safe sport participation and reduce SCA/D in athletes.

Small Steps in Impacting Clinical Auscultation of Medical Students

The objective of this study was to determine if a training module improves the auscultation skills of medical students at the University of Maryland School of Medicine. Second-year medical students completed pretests on 12 heart sounds followed by a 45-minute training module on clinical auscultation, with retesting immediately after the intervention and during their third-year pediatrics clerkship. The control group consisted of third-year medical students who did not have the intervention. There was a 23% improvement in the identification of heart sounds postintervention (P < .001). Diastolic and valvular murmurs were poorly identified pre- and post intervention. There was a 6% decline in accuracy of the intervention group in the following academic year. The intervention group was superior to the control group at identifying the tested heart sounds (49% vs 43%, P = .04). The accuracy of second-year medical students in identifying heart sounds improved after a brief training module.

Automated Identification of Innocent Still's Murmur in Children

OBJECTIVE

Still's murmur is the most common innocent heart murmur in children. It is also the most commonly misdiagnosed murmur, resulting in a high number of unnecessary referrals to pediatric cardiologist. The purpose of this study was to develop a computer algorithm for automated identification of Still's murmur that may help reduce unnecessary referrals.

METHODS

We first developed an accurate segmentation algorithm to locate the first and the second heart sounds. Once these sounds were identified, we extracted signal features specific to Still's murmur. Subsequently, machine learning-based classifiers, artificial neural network and support vector machine, were used to identify Still's murmur.

RESULTS

We evaluated our classifiers using the jackknife method using 87 Still's murmurs and 170 non-Still's murmurs. Our algorithm identified Still's murmur accurately with 84-93% sensitivity and 91-99% specificity.

CONCLUSION

We have achieved accurate automated identification of Still's murmur while minimizing false positives. The performance of our algorithm is comparable to the rate of murmur identification by auscultation by pediatric cardiologists.

SIGNIFICANCE

To our knowledge, our solution is the first murmur classifier that focuses singularly on Still's murmur. Following further refinement and testing, the presented algorithm could reduce the number of children with Still's murmur referred unnecessarily to pediatric cardiologists.

The 200th anniversary of the stethoscope: Can this low-tech device survive in the high-tech 21st century?

In 1816, Laennec discovered that auscultation of the heart and lungs could effectively be performed by placing a hollow cylinder (initially made of a roll of paper) between the chest of the patient and the ear of the examiner. This was the first step in the development of the stethoscope, which was a breakthrough in the diagnosis and management of cardiac and pulmonary patients. Technical improvements of the stethoscope followed and in cardiac patients auscultation soon became a major diagnostic tool. In the second half of the 20th century, new powerful non-invasive diagnostic modalities were developed and the interest in auscultation declined. As a result, the auscultatory skills of students and physicians at all levels of training decreased to a disappointingly low level. We now must decide whether we should stimulate the use of and proficiency in auscultation or if we should accept the further decline and eventual abolishment of this component of the physical examination. Reviewing the literature and taking into consideration the setting in which the patients are presented, including the availability of advanced diagnostic facilities, we conclude that the time-honoured stethoscope, in spite of its limitations, still has potential as a patient-friendly, effective, and economical instrument in medical practice. However, new initiatives are required to train students, physicians and allied health professionals in cardiac auscultation to avoid misinterpretations that may harm the patients and generate extra costs. To be successful such programs will require wide support from the medical community.

Cardiac auscultation via simulation: a survey of the approach of UK medical schools

Background

A decline in clinical skills of medical students and junior doctors is well documented. We aim to determine how the 32 UK medical schools utilise simulated heart sounds to develop medical students’ cardiac auscultation skills.

Methods

Representatives of all 32 UK medical schools were contacted with a survey questionnaire. Data analysis was carried out using SPSS. Continuous variables e.g. teaching group size were described using median and interquartile range (IQR).

Results

27 Medical schools use a form of simulated heart sounds as a teaching method (2 representatives were unsure, 3 did not respond). This teaching is mandatory in 17 schools. Simulation-based teaching tends to be offered during 3rd year of medical training [median = 3rd year, interquartile range (IQR) 2–3]. Seven medical schools offered simulation teaching more than once. The median number of students in each session was 7.5 [IQR = 5.5–9.5]. One medical school reported that they were unsure how best to implement the heart sound simulation into the medical undergraduate curriculum.

Conclusion

The results of our survey of all the UK medical schools suggest that heart sound simulation are used mainly as an introduction to heart murmurs rather than a tool for repetitive practice, complementing clinical experience. Most medical schools do not measure the impact of such teaching on clinical examination.

International trial of online auditory training programme for distinguishing innocent and pathological murmurs

AIM

Recognition of normal and abnormal heart sounds and murmurs is an important but declining clinical skill among practitioners. Current teaching methods are often ineffective. This may result from inadequate repetition and normal-abnormal comparisons needed for auditory recognition. This paper describes a rapid new method of teaching murmur recognition using principles of auditory training.

METHODS

Participants were 120 Australian and 42 Canadian medical students. The medical students were randomised to intervention and control (no intervention) groups. The 1-h online programme structured like a computer game used auditory training methodology to teach students to distinguish between innocent and pathological murmurs. Participants underwent pre- and post-testing on 20 paediatric murmurs. Post-testing occurred immediately following training and after 2 months. Twenty-two Canadian medical students were retested 1 year later with a brief mastery-style reinforcement programme.

RESULTS

Median pre- and post-test scores improved in about 1 h from 75-95% (P < 0.001) for Australian students and 85-95% (P = 0.004) for Canadian students. Two-month post-test scores declined for Australian students to 85% (P = 0.001), and for Canadian students to 85% (P = 0.02). Australian controls had no significant change during the study period, whereas Canadian controls improved slightly. The group receiving reinforcement after 1 year had a median final score of 90%.

CONCLUSIONS

This auditory training programme rapidly teaches students to distinguish innocent and pathological murmurs with at least 90% accuracy. The skill declines within 2 months but can be restored with brief mastery reinforcement 1 year later.

Hearing, Listening, Action: Enhancing nursing practice through aural awareness education

Abstract Noise overload within the clinical environment has been found to interfere with the healing process for patients, as well as nurses ability to effectively assess patients. Awareness and responsibility for noise production begins during initial nursing training and consequently a program to enhance aural awareness skills was designed for graduate entry nursing students in an Australian university. The program utilised an innovative combination of music education activities to develop the students' ability to distinguishing individual sounds (hearing), appreciate patient's experience of sounds (listening) and improve their auscultation skills and reduce the negative effects of noise on patients (action). Using a mixed methods approach, students' reported heightened auscultation skills and greater recognition of both patients' and clinicians' aural overload. Results of this pilot suggest that music education activities can assist nursing students to develop their aural awareness and to action changes within the clinical environment to improve the patient's experience of noise.