Classification of heart valve single leg separations from acoustic clinical measurements
Conference
·
OSTI ID:10167760
Our system classifies the condition (intact or single leg separated) of in vivo Bjork-Shiley Convexo-Concave (BSCC) heart valves by processing acoustic measurements of clinical heart valve opening sounds. We use spectral features as inputs to a two-stage classifier, which first classifies individual heart beats, then classifies valves. Performance is measured by probability of detection and probability of false alarm, and by confidence intervals on the probability of correct classification. The novelty of the work lies in the application of advanced techniques to real heart valve data, and extensions of published algorithms that enhance their applicability. We show that even when given a very small number of training samples, the classifier can achieve a probability of correct classification of 100%.
- Research Organization:
- Lawrence Livermore National Lab., CA (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- W-7405-ENG-48
- OSTI ID:
- 10167760
- Report Number(s):
- UCRL-JC--117704; CONF-9410156--1; ON: DE94015179
- Country of Publication:
- United States
- Language:
- English
Similar Records
Classification of heart valve condition using acoustic measurements
Processing of prosthetic heart valve sounds for single leg separation classification
Signal processing of Shiley heart valve data for fracture detection
Conference
·
Mon Nov 14 23:00:00 EST 1994
·
OSTI ID:145958
Processing of prosthetic heart valve sounds for single leg separation classification
Journal Article
·
Thu Jun 01 00:00:00 EDT 1995
· Journal of the Acoustical Society of America
·
OSTI ID:45656
Signal processing of Shiley heart valve data for fracture detection
Technical Report
·
Wed Mar 31 23:00:00 EST 1993
·
OSTI ID:10177267