Title :
Hidden Markov models based on symbolic dynamics for statistical modeling of cardiovascular control in hypertensive pregnancy disorders
Author :
Baier, V. ; Baumert, M. ; Caminal, P. ; Vallverdú, M. ; Faber, R. ; Voss, A.
Author_Institution :
Dept. of Med. Eng., Univ. of Appl. Sci. Jena, Germany
Abstract :
Discrete hidden Markov models (HMMs) were applied to classify pregnancy disorders. The observation sequence was generated by transforming RR and systolic blood pressure time series using symbolic dynamics. Time series were recorded from 15 women with pregnancy-induced hypertension, 34 with preeclampsia and 41 controls beyond 30th gestational week. HMMs with five to ten hidden states were found to be sufficient to characterize different blood pressure variability, whereas significant classification in RR-based HMMs was found using fifteen hidden states. Pregnancy disorders preeclampsia and pregnancy induced hypertension revealed different patho-physiological autonomous regulation supposing different etiology of both disorders.
Keywords :
biocontrol; blood pressure measurement; hidden Markov models; obstetrics; signal classification; statistical analysis; time series; cardiovascular control; hidden Markov models; hypertensive pregnancy disorders; patho-physiological autonomous regulation; preeclampsia; signal classification; statistical modeling; symbolic dynamics; systolic blood pressure time series; Biomedical engineering; Blood pressure; Blood pressure variability; Cardiology; Cardiovascular system; Heart rate variability; Hidden Markov models; Hypertension; Pregnancy; Pressure control; Blood pressure variability; cardiovascular control; heart rate variability; hidden Markov model; preeclampsia; pregnancy induced hypertension; Algorithms; Blood Pressure; Blood Pressure Determination; Computer Simulation; Diagnosis, Computer-Assisted; Electrocardiography; Feedback; Female; Heart Rate; Humans; Hypertension, Pregnancy-Induced; Markov Chains; Models, Cardiovascular; Models, Statistical; Pattern Recognition, Automated; Pregnancy; Statistics as Topic;
Journal_Title :
Biomedical Engineering, IEEE Transactions on
DOI :
10.1109/TBME.2005.859812
