Banca de QUALIFICAÇÃO: GLEIDSON MENDES REBOUÇAS

Uma banca de QUALIFICAÇÃO de DOUTORADO foi cadastrada pelo programa.
DISCENTE : GLEIDSON MENDES REBOUÇAS
DATA : 14/10/2019
HORA: 09:00
LOCAL: INSTITUTO DO CEREBRO
TÍTULO:

Classification model to diagnosis of posttraumatic stress disorder based on autonomic variables and speech analysis


PALAVRAS-CHAVES:

Autonomic Nervous System, Speech, Theoretical Models, Posttraumatic Stress Disorders, Anxiety Disorders, and Obsessive Compulsive Disorder


PÁGINAS: 99
GRANDE ÁREA: Ciências Biológicas
ÁREA: Fisiologia
RESUMO:

The study of the adaptive nature of the stress response shows the major role of the physiological mechanisms associated with the hypothalamic-pituitary-adrenal endocrine axis (HPA) and the Autonomic Nervous System (ANS), in its sympathetic and parasympathetic divisions, as well as the immune system. Individuals with different neuropsychiatric disorders present signs and symptoms that indicate ANS deregulation (dysautonomia), as observed from the persistent state of excitability that characterizes, for example, in the patients diagnosed with Posttraumatic Stress Disorder (PTSD and in their oral speech expression.This occurrence may be present in other psychiatric disorders that are part of the psychophysiological spectrum similar to PTSD such as anxiety disorder (ED) and obsessive compulsive disorder (OCD). The objective of this study was to develop a diagnostic classification mathematical model for PTSD based on the measurement of autonomic variables and speech structure. 298 males aged 22 to 48 years allocated into four groups: PTSD (n = 76), AT (n = 77), OCD (n = 73) and Control (n = 72) were investigated. The PCL-5, BAI and YBOCS questionnaires were used to obtain the psychometric data related respectively to PTSD, TA and OCD. The SpeechGraphs® software was used to analyze the representation of the word trajectory and to quantitatively characterize the speech complexification. An ECG signal (ADInstruments model PowerLab®) was used to analyze heart rate variability (HRV) and skin conductance. Machine learning techniques (Decision Tree and Naive Bayes) were employed to obtain the mathematical model. The model generated for PTSD classification based on autonomic measurements presented accuracy of 92.3% (p <0.0001) and Kappa index of 89.7% with the generation of a decision algorithm using parasympathetic axis (SDNN and RMSSD) and sympathetic (LF). The model generated for PTSD classification based on speech trajectory measurements presented accuracy of 80.9% (p <0.0001) and Kappa index of 71.4% with the generation of a decision algorithm using lexical diversity measures ( Nodes), recurrence (RE, PE) and connectivity (LSC, LCC and L3). The model generated using autonomic measurements obtained better accuracy for PTSD classification and may reflect a more efficient strategy not only for identification but for future investigations regarding risk stratification, categorization of disorder severity or clinical evolution


MEMBROS DA BANCA:
Interno - 2069422 - DIEGO ANDRES LAPLAGNE
Presidente - 6346130 - MARIA BERNARDETE CORDEIRO DE SOUSA
Interno - 1660044 - SIDARTA TOLLENDAL GOMES RIBEIRO

Notícia cadastrada em: 08/10/2019 16:51
SIGAA | Superintendência de Tecnologia da Informação - (84) 3342 2210 | Copyright © 2006-2024 - UFRN - sigaa06-producao.info.ufrn.br.sigaa06-producao