This paper reports on results of a pattern recognition technique for classifying pathological mental states of bipolar disorders using information gathered from the electrodermal response. The rationale behind this work is that the autonomic nervous system dynamics, non-invasively quantified through the electrodermal response processing, is altered by the specific mood state. Starting from the hypothesis that bipolar disorders are associated with affective dysfunctions, we processed data gathered from four bipolar patients through eleven experimental trials while an ad-hoc emotional stimulation is administered. Intra- and inter-subject variability were investigated. We show that, using a deconvolution-based approach to estimate sympathetic ANS markers and simple k-Nearest Neighbor algorithms, the proposed methodology is able to discern up to three mood states such as depression, hypo-mania, and euthymia with an average intra-subject accuracy greater than 98% and inter-subject accuracy greater than 82%.

A pattern recognition approach based on electrodermal response for pathological mood identification in bipolar disorders / Lanata Antonio; Greco Alberto; Valenza Gaetano; Scilingo Enzo Pasquale. - (2014), pp. 3601-3605. (Intervento presentato al convegno 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014 tenutosi a Florence, ita nel 2014) [10.1109/ICASSP.2014.6854272].

A pattern recognition approach based on electrodermal response for pathological mood identification in bipolar disorders

Lanata Antonio;
2014

Abstract

This paper reports on results of a pattern recognition technique for classifying pathological mental states of bipolar disorders using information gathered from the electrodermal response. The rationale behind this work is that the autonomic nervous system dynamics, non-invasively quantified through the electrodermal response processing, is altered by the specific mood state. Starting from the hypothesis that bipolar disorders are associated with affective dysfunctions, we processed data gathered from four bipolar patients through eleven experimental trials while an ad-hoc emotional stimulation is administered. Intra- and inter-subject variability were investigated. We show that, using a deconvolution-based approach to estimate sympathetic ANS markers and simple k-Nearest Neighbor algorithms, the proposed methodology is able to discern up to three mood states such as depression, hypo-mania, and euthymia with an average intra-subject accuracy greater than 98% and inter-subject accuracy greater than 82%.
2014
ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2014 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2014
Florence, ita
2014
Lanata Antonio; Greco Alberto; Valenza Gaetano; Scilingo Enzo Pasquale
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1192137
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 22
  • ???jsp.display-item.citation.isi??? 3
social impact