January 1, 2011BioMedical Engineering OnLineOpen Access

A framework for automatic heart sound analysis without segmentation

View Full Paper

Ask AI

Bookmark

Structured PICO

Population

Heart sounds obtained from several on-line databases and recorded with an electronic stethoscope

Intervention

Automatic heart sound analysis framework without segmentation (envelope detection, auto-correlation, discrete wavelet transform, principal component analysis, and neural network bagging predictors)

Outcome

Classification performance (geometric mean) for healthy vs. diseased heart sounds

A novel segmentation-free framework for automatic heart sound analysis demonstrated high classification performance and noise robustness, offering a potential tool for automated auscultation.

Limitations

More tests are needed to address any bias that may have been introduced by different sources of heart sounds in the current training set
Need to build a new training set recorded from actual patients to further evaluate the method

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Supports segmentation-free automated heart sound classification development; leaves open prospective clinical validation before practice adoption.

Cite This Study

Yuenyong et al. (2011) studied this question.

synapsesocial.com/papers/6a22f218a5663ce015b7ab54 https://doi.org/10.1186/1475-925x-10-13

View Full Paper

Ask AI

Bookmark

Implication

Supports segmentation-free automated heart sound classification development; leaves open prospective clinical validation before practice adoption.