Comparison of analogue and electronic stethoscopes for pulmonary auscultation by internal medicine residents

Abstract

BackgroundElectronic stethoscopes are becoming more common in clinical practice. They may improve the accuracy and efficiency of pulmonary auscultation, but the data to support their benefit are limited.ObjectiveTo determine how auscultation with an electronic stethoscope may affect clinical decision making.MethodsAn online module consisting of six fictional ambulatory cases was developed. Each case included a brief history and lung sounds recorded with an analogue and electronic stethoscope. Internal medicine resident participants were randomly selected to hear either the analogue or electronic lung sounds. Numbers of correct answers, time spent on each case and numbers of times the recordings were played were compared between the groups who heard each mode of auscultation, with a p value of less than 0.05 indicating statistical significance.Results61 internal medicine residents completed at least one case, and 41 residents completed all six cases. There were no significant differences in overall scores between participants who heard analogue and electronic lung sounds (3.14±0.10 out of 6 correct for analogue, 3.20±0.10 out of 6 for electronic, p=0.74). There were no significant differences in performance for any of the six cases (p=0.78), time spent on the cases (p=0.67) or numbers of times the recordings were played (p=0.85).ConclusionWhen lung sounds were amplified with an electronic stethoscope, we did not detect an effect on performance, time spent on the cases or numbers of times participants listened to the recordings.

Real-World Verification of Artificial Intelligence Algorithm-Assisted Auscultation of Breath Sounds in Children

“…Faced with the above situation, scientists invented the electronic stethoscope and have attempted to apply it to the real clinical environment. To some extent, the electronic stethoscope overcomes some of the shortcomings of the traditional stethoscope in sound data storage and sharing, but it does not improve the accuracy and efficiency of breath sound recognition (6). In recent years, artificial intelligence (AI) algorithms have been applied to the processing and recognition of breath sounds, among which the most commonly used algorithms include artificial neural networks, Gaussian mixture models and support vector machines, and some promising achievements have been reported (7).…”