Newborn Cry-Based Diagnosis System
characteristics of infant cries reflect central nervous system
integrity. The potential for their use in the early diagnosis of
various pathologies in newborns remains largely undeveloped. Our
aim is therefore to analyze the cries of newborns and to develop
a system of early diagnosis for the identification of selected
pathological conditions. In order to develop this system, we
identify and quantize the acoustic characteristics that appear
the most apt for betraying the pathological conditions.
minimal-cost system uses advanced signal-processing techniques
in order to alert paediatricians to the possible presence of
conditions needing attention in the absence of clinical signs.
The proposed system is usable for both preterm and full-term
developed focuses on two aspects of interest: 1) pathologies
that can be identified using standard techniques, and 2)
pathologies that are not detectable without in-depth examination
and specialized tests.
aim of the project is to broaden the diagnostic system to
include other serious pathological conditions that afflict
newborns. Early diagnosis before the onset of clinical symptoms
will increase the likelihood of successful intervention before
the illness has serious impact on the health of the infant.
project, a careful attention is given to both preterm and
full-term newborns. The preterm infants pose significant risks
related to functional immaturity of the organs. They also have a
vulnerability to infections and increased risk of brain damage
when babies suffer from important jaundice. Hence the need for
early diagnosis of various diseases that can affect this
category of infants.
is conducted in collaboration with Dr. Barrington, MD, Neonatology, Ste-Justine Hospital.
Good level in
signal/speech processing and machine learning, as well as Matlab
and C/C++ and/or Java programming.
Pr. Chakib Tadj, Chakib Tadj
École de technologie supérieure, Université du Québec (http://www.etsmtl.ca),
Montreal, Quebec, Canada.
to be discussed.