Methods Inf Med 2007; 46(02): 196-201
DOI: 10.1055/s-0038-1625406
Original Article
Schattauer GmbH

Fetal Heart Rate Deceleration Detection Using a Discrete Cosine Transform Implementation of Singular Spectrum Analysis

P. A. Warrick
1   Biomedical Engineering Department, McGill University, Montréal, Québec, Canada
4   LMS Medical Systems, Inc., Montréal, Québec, Canada
,
D. Precup
2   School of Computer Science, McGill University, Montréal, Québec, Canada
,
E. F. Hamilton
3   Department of Obstetrics and Gynecology, McGill University, Montréal, Québec, Canada
4   LMS Medical Systems, Inc., Montréal, Québec, Canada
,
R. E. Kearney
1   Biomedical Engineering Department, McGill University, Montréal, Québec, Canada
› Author Affiliations
Further Information

Publication History

Publication Date:
11 January 2018 (online)

Summary

Objectives : To develop a singular-spectrum analysis (SSA) based change-point detection algorithm applicable to fetal heart rate (FHR) monitoring to improve the detection of deceleration events.

Methods : We present a method for decomposing a signal into near-orthogonal components via the discrete cosine transform (DCT) and apply this in a novel online manner to change-point detection based on SSA. The SSA technique forms models of the underlying signal that can be compared over time; models that are sufficiently different indicate signal change points. To adapt the algorithm to deceleration detection where many successive similar change events can occur, we modify the standard SSA algorithm to hold the reference model constant under such conditions, an approach that we term “base-hold SSA”. The algorithm is applied to a database of 15 FHR tracings that have been preprocessed to locate candidate decelerations and is compared to the markings of an expert obstetrician.

Results : Of the 528 true and 1285 false decelerations presented to the algorithm, the base-hold approach improved on standard SSA, reducing the number of missed decelerations from 64 to 49 (21.9%) while maintaining the same reduction in false-positives (278).

Conclusions : The standard SSA assumption that changes are infrequent does not apply to FHR analysis where decelerations can occur successively and in close proximity; our base-hold SSA modification improves detection of these types of event series.

 
  • References

  • 1. Broomhead D, King G. Extracting qualitative dynamics from experimental data. Physica D 1986; 20: 217-236.
  • 2. Moskvina V. Application of the singular spectrum analysis for change-point detection in time series [dissertation]. Cardiff (UK): Cardiff University; 2001
  • 3. Basseville M, Nikiforov I. Detection of Abrupt Changes: Theory and Applications. Englewood Cliffs (NJ): Prentice Hall; 1993
  • 4. Jager F, Mark R, Moody G, Divjak S. Analysis of transient ST segment changes during ambulatory monitoring using the Karhunen-Loève transform. In: Computers in Cardiology 1992: 691-694.
  • 5. Maier C, Dickhaus H, Bauch M, Penzel T. Comparison of heart rhythm and morphological ECG features in recognition of sleep apnea from the ECG. In: Murray A Computers in Cardiology 2003: 311-314.
  • 6. Akansu A, Haddad R. Multiresolution Signal Decomposition: Transforms, Subbands, Wavelets. 2nd ed. Englewood Cliffs (NJ): Academic Press; 2001
  • 7. Haykin S. Adaptive Filtering. 4th ed. Upper Saddle River (NJ): Prentice-Hall; 2002
  • 8. Warrick P, Hamilton E, Macieszczak M. Neural network based detection of fetal heart rate patterns. In: Proceedings of the 2005 IEEE International Joint Conference on Neural Networks; 2400-05