Skip to Main content Skip to Navigation

Méthodes probabilistes pour le monitoring cardio-respiratoire des nouveau-nés prématurés

Abstract : The surveillance of premature newborns placed in intensive care units led to the notion of monitoring and the acquisition of many physiological signals. While this information is well used for the diagnosis and prevention of emergency situations, it must be acknowledged that, to date, it is less the case for predictive purposes. This is mainly due to the difficulty of extracting reliable information in real time, without any visual control, from non-stationary signals. This thesis aims to propose robust methods, adapted to the context of neonatal intensive care units and real time. For this purpose, a set of generic methods applied to cardiac variability, but capable of being adapted to other physiological constants such as respiration, have been developed and tested in clinical context. Four main parts illustrate these points : - The proposal of an original multicharacteristic probabilistic real time detection method for robust detection of interest events of noisy physiological signals. Generic, this solution is applied to the robust QRS complex detection of the ECG signals. It is based on the real time calculation of several posterior probabilities of the signal properties before merging them into a decision node using the weighted Kullback-Leibler divergence. Compared to two classic methods from the literature on two noisy databases, it has a lower detection error rate (20.91% vs. 29.02% (wavelets) and 33.08% (Pan-Tompkins) on the test database). - The proposal of using hidden semi-markovian models for the segmentation of temporal periods with most reliable event detections. Compared to two methods from the literature, the proposed solution achieves better performance, the error criterion obtained is significantly lower (between -21.37% and -74.98% depending on the basis and approach evaluated). - The selection of an optimal detector for the monitoring of apnea-bradycardia events, in terms of reliability and precocity, based on ECG data obtained from newborns. The performance of the selected detector will be compared to the alarms generated by an industrial continuous monitoring device traditionally used in neonatology service (Philips IntelliVue monitor). The method based on the abrupt change of the RR average achieves the best results in terms of time (3.99 s vs. 11.53 s for the IntelliVue monitor) and reliability (error criterion of 43.60% vs. 80.40%). - The design and development of SYNaPSE (SYstem for Noninvasive Physiological Signal Explorations) software platform for the acquisition of various physiological signals in large quantities, and in a non-invasive way, within the care units. The modular design of this platform, as well as its real time properties, allows simple and fast integration of complex signal processing methods. Its translational interest is shown in the analysis of a database in order to study the impact of bilirubin on cardiac variability.
Complete list of metadata
Contributor : ABES STAR :  Contact
Submitted on : Wednesday, February 20, 2019 - 12:04:09 PM
Last modification on : Wednesday, September 14, 2022 - 10:20:04 AM


Version validated by the jury (STAR)


  • HAL Id : tel-02040949, version 1


Matthieu Doyen. Méthodes probabilistes pour le monitoring cardio-respiratoire des nouveau-nés prématurés. Traitement du signal et de l'image [eess.SP]. Université Rennes 1, 2018. Français. ⟨NNT : 2018REN1S049⟩. ⟨tel-02040949⟩



Record views


Files downloads