Component Sound Analysis for Extracting and Analyzing Medical Information from Patient Encounters

Sounds associated with health and illness are vital for health care diagnoses and therapy. This project focuses on developing a system capable of processing and extracting additional features from sound and speech during a health care encounter. This recording and analysis may help with the treatment of a variety of diseases.The sound capture system uses high-fidelity microphones positioned around the room to record, store, analyze and display sound components of speech and other sound-generating aspects associated with the physical examination, such as breath sounds. The system also includes speech-to-text analysis to produce a transcript of the encounter. The system incorporates natural language processing to analyze conversations and organize useful information by helping with documentation of the patient’s condition. The final product provides the user with valuable data that may be incorporated into the electronic medical record system within the context of a digital “wired room.” This system can improve efficiency in medical care, improve diagnoses and reduce the time a physician needs to spend with each patient.