MIT Automated Auscultation System

• Main Author: Syed, Zeeshan Hassan, 1980-
• Other Authors: John V. Guttag.
• Format: Others
• Language: English
• Published: Massachusetts Institute of Technology 2005
• Subjects: Electrical Engineering and Computer Science.
• Online Access: http://hdl.handle.net/1721.1/18018

Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2003. === Includes bibliographical references (p. 123-127). === At every annual exam, the primary care physician uses a stethoscope to listen for cardiac abnormalities. This approach is non-invasive, inexpensive, and fast. It is also highly unreliable. Over 80% of the people referred to cardiologists as suffering from the most commonly diagnosed condition, mitral valve prolapse (MVP), do not have this condition. Working in conjunction with cardiologists at MGH, we developed a robust, low cost, easy to use tool that can be employed to diagnose MVP in the office of primary care physicians. The system fuses signals from an electronic stethoscope and a two-lead EKG, and uses software running on a desktop or laptop computer to make a diagnosis. We also provide a number of novel audiovisual diagnostic aids. These allow physicians to visualize both individual heart beats and a visual-prototypical heart beat constructed from a sequence of beats. They also permit doctors to listen to an audio-prototypical heart-beat, audio enhanced heart-beats that amplify clinically significant sounds, and slowed down heart-beats that make it easier to separate clinically relevant cardiac events. We tested our system on 51 patients. The number of false positives was reduced to approximately 10%. While there is no generally accepted statistic on false negatives, anecdotal experience indicates that our system also outperforms physicians in this respect. === by Zeeshan Hassan Syed. === M.Eng.