Apnea in preterm newborns: determinants, pathophysiology, effects on cardiovascular parameters and treatment

et al. 2020

Med Biol Eng Comput

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 seconds. The results show that the algorithm based on CHSMM is a robust tool for monitoring of preterm infants in detecting apnea bradycardia episodes.

Section: Real Clinical Datamentioning

confidence: 99%

Apnea bradycardia detection based on new coupled hidden semi Markov model

et al. 2020

Med Biol Eng Comput

“…Furthermore, the amplitude of R-wave on the ECG (RAMP) has been considered since it is modulated by the respiratory activity [28]. Some works have also reported an increase in the duration of the QRS complex (QRSd) preceding episodes of AB, so this feature has also been extracted [29]. The total set of features that will be used as observations to evaluate the CHMM framework are thus: the RR interval, R-wave amplitude (RAMP) and QRS duration (QRSd).…”

Section: Evaluation Datasets 1) Simulated Datamentioning

confidence: 99%

“…This process is repeated five times for cross-validation with different, randomly chosen records, on the training and evaluation datasets. However, prior to this procedure, since the RAMP data are modulated by respiration activities [29] and the effect of apnea will first appear in the RAMP feature, we apply a synchronization time delay (τ ), whose possible values are observed around 4.5 s. The exact values of τ are also optimized and reported in Table III and in Fig. 6.…”

Section: Detection Of Ab In Real Datamentioning

confidence: 99%

Coupled Hidden Markov Model-Based Method for Apnea Bradycardia Detection

Masoudi

IEEE J. Biomed. Health Inform.

et al. 2016

In this paper, we present a novel framework for the coupled hidden Markov model (CHMM), based on the forward and backward recursions and conditional probabilities, given a multidimensional observation. In the proposed framework, the interdependencies of states networks are modeled with Markovian-like transition laws that influence the evolution of hidden states in all channels. Moreover, an offline inference approach by maximum likelihood estimation is proposed for the learning procedure of model parameters. To evaluate its performance, we first apply the CHMM model to classify and detect disturbances using synthetic data generated by the FitzHugh-Nagumo model. The average sensitivity and specificity of the classification are above 93.98% and 95.38% and those of the detection reach 94.49% and 99.34%, respectively. The method is also evaluated using a clinical database composed of annotated physiological signal recordings of neonates suffering from apnea-bradycardia. Different combinations of beat-to-beat features extracted from electrocardiographic signals constitute the multidimensional observations for which the proposed CHMM model is applied, to detect each apnea bradycardia episode. The proposed approach is finally compared to other previously proposed HMM-based detection methods. Our CHMM provides the best performance on this clinical database, presenting an average sensitivity of 95.74% and specificity of 91.88% while it reduces the detection delay by -0.59 s.

“…Other symptoms in the morphology of heartbeats, such as reduction of the QRS amplitude and its width prolongation, are also expected to be observed. Recent research has focused on the early detection of apnea from electrocardiogram (ECG) employing strong algorithms based on features extracted from all of its common symptoms (Altuve et al 2009, Haskova et al 2013. Accordingly, neonatal intensive care units (NICUs) are usually equipped with alarms which employ such detection algorithms.…”

Section: Introductionmentioning

confidence: 99%

“…The subtle changes in the ECG patterns can be interpreted as a change happening in the dynamic of the ECG beat generation process. In order to study such systems, one can propose using SKF, which is widely used for modelling systems with changeable dynamics (Ghahramani 1996, Marculescu et al 1998. In a simple form of SKF, it is assumed that the model has a linear dynamic at each time instant but it is time variant and switches among several linear subsystems over the time; each linear subsystem can be described by linear dynamical equations of continuous states (x k ) as state equations and a linear relation between states and observation (y k ) as an observation equation:…”

Section: Introductionmentioning

confidence: 99%

Switching Kalman filter based methods for apnea bradycardia detection from ECG signals

et al. 2015

Physiol. Meas.

Apnea bradycardia (AB) is an outcome of apnea occurrence in preterm infants and is an observable phenomenon in cardiovascular signals. Early detection of apnea in infants under monitoring is a critical challenge for the early intervention of nurses. In this paper, we introduce two switching Kalman filter (SKF) based methods for AB detection using electrocardiogram (ECG) signal.The first SKF model uses McSharry's ECG dynamical model integrated in two Kalman filter (KF) models trained for normal and AB intervals. Whereas the second SKF model is established by using only the RR sequence extracted from ECG and two AR models to be fitted in normal and AB intervals. In both SKF approaches, a discrete state variable called a switch is considered that chooses one of the models (corresponding to normal and AB) during the inference phase. According to the probability of each model indicated by this switch, the model with larger probability determines the observation label at each time instant.It is shown that the method based on ECG dynamical model can be effectively used for AB detection. The detection performance is evaluated by comparing statistical metrics and the amount of time taken to detect AB compared with the annotated onset. The results demonstrate the superiority of this method, with sensitivity and specificity 94.74[Formula: see text] and 94.17[Formula: see text], respectively. The presented approaches may therefore serve as an effective algorithm for monitoring neonates suffering from AB.