p-leader based classification of first stage intrapartum fetal HRV

Roberto Leonarduzzi (1, 2) , Jiri Spilka (3) , Herwig Wendt (4, 5) , Stéphane Jaffard (6) , Maria E. Torres (1, 2) , Patrice Abry (3) , Muriel Doret (7)

1 CONICET - Consejo Nacional de Investigaciones Científicas y Técnicas [Buenos Aires]
2 UNER - Universidad Nacional de Entre Ríos [Argentine]
3 Phys-ENS - Laboratoire de Physique de l'ENS Lyon
4 IRIT-SC - Signal et Communications
5 CNRS - Centre National de la Recherche Scientifique
6 LAMA - Laboratoire d'Analyse et de Mathématiques Appliquées
7 HCL - Hospices Civils de Lyon

Interpretation and analysis of intrapartum fetal heart rate, enabling early detection of fetal acidosis, remains a challenging signal processing task. Recently, a variant of the wavelet-based multifractal analysis, based on p-exponents and p-leaders, which provides a rich framework for data regularity analysis, has been proposed. The present contribution aims at studying the benefits of using the p-leader multifractal formalism for discrimination of intrapartum fetal heart rate. First, a dependence on p of the multifractal properties of data is evidenced and interpreted. Second, classification between healthy subjects and fetuses suffering from acidosis is shown to have satisfactory performance that increases when p is decreased.

Mots clés: Wavelets; Multifractal analysis; p-leaders; Intrapartumfetal heart rate variability; Acidosis detection

Domaines: Synthèse d'image et réalité virtuelle [cs.GR]; Traitement du signal et de l'image [eess.SP]; Traitement des images [eess.IV]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Intelligence artificielle [cs.AI]

Roberto Leonarduzzi, Jiri Spilka, Herwig Wendt, Stéphane Jaffard, Maria E. Torres, et al.. p-leader based classification of first stage intrapartum fetal HRV. VI Latin American Congress on Biomedical Engineering (CLAIB 2014), Oct 2014, Paraná, Argentina. pp. 504-507. ⟨hal-01500525⟩