Automated Detection of Central Apnea in Preterm Infants

More Info


In 2010, an estimated 14.9 million babies were born preterm, which amounted to 11.1% of all livebirths worldwide, ranging from about 5% in several European countries to 18% in some African countries . The rate of preterm births has increased remarkably. Prematurity of birth can predispose neonates to undesirable cessations of breathing, a condition termed as Apnea of Prematurity. The prevalence of this condition poses problems, because when untreated or inadequately treated Apnea of Prematurity, may impair development. This thesis investigates the automated central apnea detection in preterminfants based on raw waveform analysis of one-lead ECG and chest impedance signals. For this purpose, 18 novel features and 34 features of existing research that characterize different aspects of chest impedance and ECG signals were extracted for automated apnea classification. Features aim to extract information regarding respiratory and cardiac regularity, estimated from chest impedance and ECG signals. These features are indicators of some properties of cardio-respiratory physiology, which is not independent of the presence of apnea and thus can be in turn used to classify apnea. The objective is to find the most discriminative subset of features from one-lead ECG and chest impedance signals that can be used by a machine-learning approach to study and accurately detect central apnea. This was achieved by applying feature selection algorithms in order to remove redundant or irrelevant features without incurring much loss of information. In this thesis, nine hours of continuously recorded data of ten very low-birth-weight infants (birthweight < 1,500 gr) undergoing continuous cardiopulmonary monitoring in the NICU at Maxima Medisch Centrum from 2008 were included in the analysis. The dataset was annotated by two neonatologists. Results from this work indicate that the analysis of chest impedance and ECG signals with a support vector machine can automatically detect Apnea of Prematurity.