Title: Sleep staging from Heart Rate Variability: time-varying spectral features and Hidden Markov Models
Authors: Martin Oswaldo Mendez, Matteo Matteucci, Vincenza Castronovo, Luigi Ferini-Strambi, Sergio Cerutti, Anna Maria Bianchi
Addresses: Bioengineering Department, Politecnico di Milano, piazza Leonardo da Vinci 32, 20133 Milan, Italy. ' Electronics and Information Department, Politecnico di Milano, piazza Leonardo da Vinci 32, 20133 Milan, Italy. ' Sleep Disorder Center, University Vite a Salute, Ospedale San Raffaele, Via Prinetti 29, I-20127 Milan, Italy. ' Sleep Disorder Center, University Vite a Salute, Ospedale San Raffaele, Via Prinetti 29, I-20127 Milan, Italy. ' Bioengineering Department, Politecnico di Milano, piazza Leonardo da Vinci 32, 20133 Milan, Italy. ' Bioengineering Department, Politecnico di Milano, piazza Leonardo da Vinci 32, 20133 Milan, Italy
Abstract: An alternative DSS which models the behaviour of the Heart Rate Variability (HRV) signal linked to stable (NREM) and instable (REM) cerebral waves during sleep and a probabilistic model of the sleep stages transitions for decision was developed. Time-Varying Autoregressive Models (TVAMs) were used as feature extractor while Hidden Markov Models (HMM) was used as time series classifier. 24 full polysomnography recordings from healthy sleepers were used for the analysis and those were separated in two sets of 12 each: training and test set. The classification performance for the test set was specificity = 0.851, accuracy = 0.793 and sensitivity = 0.702.
Keywords: HRV; heart rate variability; DSS; decision support systems; sleep stages; time-varying analysis; HMM; hidden Markov models; cerebral waves; probabilistic modelling; feature extraction; time series classification.
DOI: 10.1504/IJBET.2010.032695
International Journal of Biomedical Engineering and Technology, 2010 Vol.3 No.3/4, pp.246 - 263
Published online: 13 Apr 2010 *
Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article