학술논문

Multiple feature acoustic classification of BSCC artificial heart valves
Document Type
Conference
Source
Proceedings of IEEE Symposium on Computer-Based Medical Systems (CBMS) Computer-based medical systems Computer-Based Medical Systems, 1994., Proceedings 1994 IEEE Seventh Symposium on. :125-130 1994
Subject
Bioengineering
Computing and Processing
Communication, Networking and Broadcast Technologies
Robotics and Control Systems
Artificial heart
Heart valves
Laser sintering
Flanges
Resonance
Frequency estimation
Prosthetics
Acoustic signal processing
Manufacturing
Welding
Language
Abstract
Mechanical prosthetic heart valves generate sounds which may be used to infer their structural status. Acoustical signal processing methods have been applied to the Bjork-Shiley Convexo-Concave (BSCC) heart valve, which in rare instances may experience outlet strut fracture. An objective classifier has been developed that isolates and characterizes a frequency component shown to be associated with the intact BSCC valve. Analysis of recordings from 24 confirmed clinical cases resulted in a 93% specificity (13 of 14 properly classified as intact) and 100% sensitivity (10 of 10 properly classified as structurally altered).ETX