Interactive Lungs Auscultation with Reinforcement Learning Agent
This addresses the problem of accessible respiratory health monitoring for non-experts, particularly for children, by automating guidance in auscultation.
The paper tackles the challenge of enabling laypeople to perform lung auscultation at home by proposing a reinforcement learning agent that interactively guides users through the procedure, reducing examination time fourfold without significantly compromising diagnosis accuracy.
To perform a precise auscultation for the purposes of examination of respiratory system normally requires the presence of an experienced doctor. With most recent advances in machine learning and artificial intelligence, automatic detection of pathological breath phenomena in sounds recorded with stethoscope becomes a reality. But to perform a full auscultation in home environment by layman is another matter, especially if the patient is a child. In this paper we propose a unique application of Reinforcement Learning for training an agent that interactively guides the end user throughout the auscultation procedure. We show that \textit{intelligent} selection of auscultation points by the agent reduces time of the examination fourfold without significant decrease in diagnosis accuracy compared to exhaustive auscultation.