Antepartum fetal heart rate feature extraction and classification using empirical mode decomposition and support vector machine
2011

Fetal Heart Rate Classification Using EMD and SVM

Sample size: 90 publication 10 minutes Evidence: moderate

Author Information

Author(s): Krupa Niranjana, MA Mohd Ali, Zahedi Edmond, Ahmed Shuhaila, Hassan Fauziah M

Primary Institution: Universiti Kebangsaan Malaysia

Hypothesis

Can empirical mode decomposition and support vector machine effectively classify fetal heart rate recordings as 'normal' or 'at risk'?

Conclusion

The proposed methodology is a promising new approach for the feature extraction and classification of fetal heart rate signals.

Supporting Evidence

  • The method achieved a 5-fold cross-validation accuracy of 86%.
  • The sensitivity and specificity for the training set were 100% and 90%, respectively.
  • The Kappa value for the training set was 0.923, indicating good agreement.
  • The testing set showed a sensitivity of 95% and specificity of 70%.

Takeaway

This study found a new way to look at baby heart rates to tell if they are healthy or in danger, using special math and computer techniques.

Methodology

Fetal heart rates were recorded from 15 subjects, and features were extracted using empirical mode decomposition, followed by classification using support vector machine.

Potential Biases

High inter-observer and intra-observer variability in visual inspection may affect results.

Limitations

The sifting process used in EMD is time-consuming, and the number of decomposed components varies with respect to the signal.

Participant Demographics

15 subjects with singleton pregnancies, gestation age ranging from 34 to 40 weeks.

Statistical Information

P-Value

0.05

Confidence Interval

95%

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1475-925X-10-6

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication