Automated Heart and Lung Auscultation in Robotic Physical Examinations
This work addresses health screening in medical robotics by enabling autonomous physical examinations, though it is incremental as it builds on existing methods for robotic and auscultation tasks.
This paper tackled the problem of autonomous robotic auscultation for heart and lung sounds by using Bayesian Optimization with visual and auditory feedback to select high-quality locations, achieving similar sound quality to human tele-operation in experiments on 4 subjects and identifying a previously unknown cardiac pathology.
This paper presents the first implementation of autonomous robotic auscultation of heart and lung sounds. To select auscultation locations that generate high-quality sounds, a Bayesian Optimization (BO) formulation leverages visual anatomical cues to predict where high-quality sounds might be located, while using auditory feedback to adapt to patient-specific anatomical qualities. Sound quality is estimated online using machine learning models trained on a database of heart and lung stethoscope recordings. Experiments on 4 human subjects show that our system autonomously captures heart and lung sounds of similar quality compared to tele-operation by a human trained in clinical auscultation. Surprisingly, one of the subjects exhibited a previously unknown cardiac pathology that was first identified using our robot, which demonstrates the potential utility of autonomous robotic auscultation for health screening.