Automatic detection of CAP on central and fronto-central EEG leads via Support Vector Machines

Annu Int Conf IEEE Eng Med Biol Soc. 2011:2011:1491-4. doi: 10.1109/IEMBS.2011.6090364.

Abstract

The aim of this study is to implement a high-accuracy automatic detector of the Cyclic Alternating Pattern (CAP) during sleep. EEG data from four healthy subjects were used. Both the C4-A1 and the F4-C4 leads were analyzed for this study. Seven features were extracted from each of the two leads and two separate studies were performed for each set of descriptors. For both sets, a Support Vector Machine was trained and tested on the data with the Leave One Out cross-validation method. The two final classifications obtained on the two sets were merged, by considering a CAP A phase scored only if it had been recognized both on the central and on the frontal lead. The length of the A phase was then determined by the result on the fronto-central lead. This method leads to encouraging results, with a classification sensitivity on the whole dataset equal to 73.82%, specificity equal to 85.93%, accuracy equal to 84,05% and Cohen's kappa equal to 0.50.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Activity Cycles / physiology*
  • Adult
  • Algorithms
  • Biological Clocks / physiology*
  • Brain / physiology*
  • Diagnosis, Computer-Assisted / methods*
  • Electroencephalography / methods*
  • Female
  • Humans
  • Male
  • Pattern Recognition, Automated / methods*
  • Reproducibility of Results
  • Sensitivity and Specificity
  • Support Vector Machine*