Analysis of non-linear respiratory influences on Sleep Apnea classification

Alexander Caicedo, Carolina Varon, Sabine Van Huffel

Resultado de la investigación: Contribución a una revistaArtículo de la conferenciarevisión exhaustiva

2 Citas (Scopus)

Resumen

In this paper we propose the use of Kernel Principal Component Regression (KPCR) in order to model the nonlinear interaction between heart rate (HR) and respiration. We used wavelets in order to decompose the respiratory signal in 2 different frequency bands; namely, the low frequency band (LF) 0-0. 078Hz, and the high frequency band (HF) 0.078-2. 5Hz. We used the decomposed respiration as regressors in the KPCR model. Using the results provided by KPCR we computed the coupling between HR and the respiration in the LF and HF bands, separately. We evaluated the predictive power of these scores using the Physionet Sleep Apnea Dataset. In addition, we compare these results with the ones previously reported in our group, where we used a linear model based on orthogonal subspace projections and wavelet regression. We found that the features extracted using the nonlinear model improved the classification rate for apneic episodes when compared to the linear model, AUC =92.36 vs AUC = 88.29%.

Idioma originalInglés estadounidense
Número de artículo7043112
Páginas (desde-hasta)593-596
Número de páginas4
PublicaciónComputing in Cardiology
Volumen41
N.ºJanuary
EstadoPublicada - 2014
Publicado de forma externa
Evento41st Computing in Cardiology Conference, CinC 2014 - Cambridge, Estados Unidos
Duración: sep 7 2014sep 10 2014

All Science Journal Classification (ASJC) codes

  • Informática (todo)
  • Cardiología y medicina cardiovascular

Huella

Profundice en los temas de investigación de 'Analysis of non-linear respiratory influences on Sleep Apnea classification'. En conjunto forman una huella única.

Citar esto