Apnea bradycardia detection based on new coupled hidden semi Markov model
- PDF / 611,391 Bytes
- 11 Pages / 595.224 x 790.955 pts Page_size
- 6 Downloads / 167 Views
ORIGINAL ARTICLE
Apnea bradycardia detection based on new coupled hidden semi Markov model Nasim Montazeri Ghahjaverestan1,2,3 1,2 ´ Alfredo I. Hernandez
´ 1,2,4 · · Mohammad Bagher Shamsollahi3 · Di Ge1,2 · Alain Beuchee
Received: 3 February 2020 / Accepted: 14 October 2020 © International Federation for Medical and Biological Engineering 2020
Abstract In this paper, a method for apnea bradycardia detection in preterm infants is presented based on coupled hidden semi Markov model (CHSMM). CHSMM is a generalization of hidden Markov models (HMM) used for modeling mutual interactions among different observations of a stochastic process through using finite number of hidden states with corresponding resting time. We introduce a new set of equations for CHSMM to be integrated in a detection algorithm. The detection algorithm was evaluated on a simulated data to detect a specific dynamic and on a clinical dataset of electrocardiogram signals collected from preterm infants for early detection of apnea bradycardia episodes. For simulated data, the proposed algorithm was able to detect the desired dynamic with sensitivity of 96.67% and specificity of 98.98%. Furthermore, the method detected the apnea bradycardia episodes with 94.87% sensitivity and 96.52% specificity with mean time delay of 0.73 s. The results show that the algorithm based on CHSMM is a robust tool for monitoring of preterm infants in detecting apnea bradycardia episodes. Keywords Coupled hidden semi Markov model (CHSMM) · Coupled hidden Markov model (CHMM) · Forward-Backward (FB) algorithm · Electrocardiography (ECG) · Apnea bradycardia (AB)
1 Introduction Apnea of prematurity is a common complication in preterm infants born prior 37 weeks of gestation. Apnea of prematurity is associated with repetitive long (> 15 − 20 s) interruptions in respiratory airflow, which cause drop in blood oxygen saturation and occurrence of an arrhythmia called bradycardia characterized by reduction in heart rate [1]. According to the American Academy of Pediatrics, an episode of apnea of prematurity is defined as a pause in breathing for 20
Electronic supplementary material The online version of this article (https://doi.org/10.1007/s11517-020-02277-8) contains supplementary material, which is available to authorized users. Alfredo I. Hern´andez
[email protected]
Extended author information available on the last page of the article.
s or more, or shorter accompanied by bradycardia (less than 100 beats per minutes) [2]. Monitoring and treatment of apnea bradycardia require hospitalization that increases healthcare costs. If not treated, apnea bradycardia leads to higher risk of infant mortality [3] and in case of survival, can cause adverse neurobehavioral deficits during childhood [4]. Monitoring of preterm infants in neonatal intensive care unit (NICU) and early detection of apnea episodes prevent the fatal cardiorespiratory and neurobehavorial outcomes of apnea bradycardia. The detection of apnea bradycardia has been investigated in a few studies
Data Loading...
