Title :
Pattern discrimination of endocrine markers of depressive disorders
Author :
Hermida, R.C. ; Ayala, D.E. ; Halberg, F.
Author_Institution :
ETSI Telecommun., Santiago Univ., Vigo, Spain
Abstract :
A computer method of pattern discrimination, the so-called monotest, involving the leave-one-out technique for the estimation of the probability of misclassification, was used in the search for classifiers of personality. The study looked for chronoendocrine relations characteristic of a depression-prone personality (DPP) in 12 plasma hormones sampled around the clock for four seasons for a small number of clinically and psychologically healthy women, 29-36 years of age. Since the best classifiers differ among seasons, results illustrate the need to consider the intermodulation of rhythms at several frequencies, whenever endocrine variables are used for the evaluation of depressive disorders
Keywords :
computerised pattern recognition; medical diagnostic computing; 29 to 36 yr; chronoendocrine relations; computer method; depression-prone personality; depressive disorders; endocrine markers; leave-one-out technique; misclassification probability; pattern discrimination; plasma hormones; psychologically healthy women; rhythms intermodulation; Biochemistry; Clocks; Diseases; Endocrine system; Frequency; Plasmas; Psychology; Rhythm; Telecommunication standards; Testing;
Conference_Titel :
Engineering in Medicine and Biology Society, 1989. Images of the Twenty-First Century., Proceedings of the Annual International Conference of the IEEE Engineering in
Conference_Location :
Seattle, WA
DOI :
10.1109/IEMBS.1989.95967
