M. Schmidt et al., Comparative investigations of algorithms for the detection of breaths in newborns with disturbed respiratory signals, COMPUT BIOM, 31(6), 1998, pp. 413-425
The correct detection of the beginning of inspiration and expiration in the
respiratory signals is an essential prerequisite for accurate lung functio
n testing in newborns. Five algorithms for breath detection using pneumotac
hographically measured flow and volume signals were investigated with regar
d to the error rate. To compare and to evaluate the reliability of these al
gorithms 12 minimally and 12 severely disturbed flow and volume signals fro
m spontaneously breathing newborns were used. With the exception of an algo
rithm based on Walsh-transformed signals, all algorithms work reliably terr
or rate <1.1%) if disturbances are minimal. In severely disturbed signals t
here is a great difference between the algorithms. The most robust algorith
m tested (trigger of the how signal with an additional plausibility check o
f the recognized breath) resulted in an error rate of <3.4%. Not all algori
thms tested are suitable for real-time applications because they differ con
siderably in delay time for breath detection. (C) 1998 Academic Press.