Characterization of activity epochs in actimetric registries for infantile colic diagnosis: Identification and feature extraction based on wavelets and symbolic dynamics.

The diagnosis and therapy planning of high prevalence pathologies such as infantile colic can be substantially improved by statistical signal processing of activity/rest registries. Assuming that colic episodes are associated to activity episodes, diagnosis aid systems should be based on preprocessing techniques able to separate real activity from rest epochs, and feature extraction methods to identify meaningful indices with diagnostic capabilities. In this paper, we propose a two step diagnosis aid methodology for infantile colic in children below 3 months old. Identification of activity periods is performed by means of a wavelet based activity filter which does not depend on the acquisition device (as so far proposed methods do). In addition, symbolic dynamic analysis is used for extraction of discriminative indices from the activity time series. Results on real data yielded 100% sensitivity and 80% specificity in a study group composed of 46 cases and 10 control subjects.