Reliable diagnosis of depressive disorder is essential for both optimal treatment and prevention of fatal outcomes. This study aimed to elucidate the effectiveness of two non-linear measures, Higuchi's Fractal Dimension (HFD) and Sample Entropy (SampEn), in detecting depressive disorders when applied on EEG. HFD and SampEn of EEG signals were used as features for seven machine learning algorithms including Multilayer Perceptron, Logistic Regression, Support Vector Machines with the linear and polynomial kernel, Decision Tree, Random Forest, and Naı ¨ve Bayes classifier, discriminating EEG between healthy control subjects and patients diagnosed with depression. This study confirmed earlier observations that both non-linear measures can discriminate EEG signals of patients from healthy control subjects. The results suggest that good classification is possible even with a small number of principal components. Average accuracy among classifiers ranged from 90.24 to 97.56%. Among the two measures, SampEn had better performance. Using HFD and SampEn and a variety of machine learning techniques we can accurately discriminate patients diagnosed with depression vs controls which can serve as a highly sensitive, clinically relevant marker for the diagnosis of depressive disorders.
ObjectivesBiomarkers of major depressive disorder (MDD), its phases and forms have long been sought. Objectives were to examine whether the complexity of EEG activity, measured by Higuchi's fractal dimension (HFD) and sample entropy (SampEn), differs between healthy subjects, patients in remission, and in episode phase of the recurrent depression and whether the changes are differentially distributed between hemispheres and cortical regions.MethodsResting state EEG with eyes closed was recorded from 22 patients suffering from recurrent depression (11 in remission, 11 in the episode), and 20 age and sex‐matched healthy control subjects. Artifact‐free EEG epochs were analyzed by in‐house developed programs running HFD and SampEn algorithms.ResultsDepressed patients had higher HFD and SampEn complexity compared to healthy subjects. The complexity was higher in patients who were in remission than in those in the acute episode. Altered complexity was present in the frontal and centro‐parietal regions when compared to control group. The complexity in frontal and parietal regions differed between the two phases of depressive disorder.ConclusionsComplexity measures of EEG distinguish between the healthy controls, patients in remission and episode. Further studies are needed to establish whether these measures carry a potential to aid clinically relevant decisions about depression.
The objective of this preliminary study was to quantify changes in complexity of EEG using fractal dimension (FD) alongside linear methods of spectral power, event-related spectral perturbations, coherence, and source localization of EEG generators for theta (4-7 Hz), alpha (8-12 Hz), and beta (13-23 Hz) frequency bands due to a memory load effect in an auditory-verbal short-term memory (AVSTM) task for words. We examined 20 healthy individuals using the Sternberg's paradigm with increasing memory load (three, five, and seven words). The stimuli were four-letter words. Artifact-free 5-s EEG segments during retention period were analyzed. The most significant finding was the increase in FD with the increase in memory load in temporal regions T3 and T4, and in parietal region Pz, while decrease in FD with increase in memory load was registered in frontal midline region Fz. Results point to increase in frontal midline (Fz) theta spectral power, decrease in alpha spectral power in parietal region-Pz, and increase in beta spectral power in T3 and T4 region with increase in memory load. Decrease in theta coherence within right hemisphere due to memory load was obtained. Alpha coherence increased in posterior regions with anterior decrease. Beta coherence increased in fronto-temporal regions. Source localization delineated theta activity increase in frontal midline region, alpha decrease in superior parietal region, and beta increase in superior temporal gyrus with increase in memory load. In conclusion, FD as a nonlinear measure may serve as a sensitive index for quantifying dynamical changes in EEG signals during AVSTM tasks.
The current study is a preliminary examination of cognitive profiles and cortical distribution of the spectral power of different electroencephalogram (EEG) rhythms in children with specific language impairment and subclinical epileptiform discharges. Although a number of empirical studies point to higher incidence of abnormal EEGs in children with specific language impairment, only a few studies were found examining electrophysiological characteristics, such as locus of discharges and connections with cognitive functioning in this population of children. The sample included 12 children with specific language impairment (SLI) and abnormal EEG who underwent testing of cognitive functioning using the Wechsler Intelligence Scale for Children (WISC). The control sample included 13 children with specific language impairment and regular EEG. Results point to lower scores on several subtests of the performance scale for children with abnormal EEG than for the group with regular EEG. Detailed EEG analysis of cortical distribution of the spectral power of different EEG rhythms partially confirms the results of neuropsychological assessment, pointing to abnormal function of frontal and temporal regions. Higher values of spectral power of the delta brain rhythm in frontal regions are associated with lower results on the WISC performance scale. Results are discussed in the context of subgroups of the population of children with SLI.
In addition to difficulties in social interaction and communication, children with autistic spectrum disorder (ASD) also exhibit behaviors that interfere with daily activities and are difficult to control, which can lead to disturbances in the household and extended family. The child's limited social, emotional and communicative abilities, their unequal cognitive development and maladaptive behaviors are a source of stress for parents. The goal of our study was to assess the level of stress in parents of children with ASD in relation to gender, education, age of parents, the child's age, and speech and language skills. The sample of this study consisted of 40 parents (20 mothers and 20 fathers) 21 to 56 years of age. All respondents were parents of children with ASD; 22 were parents of children receiving treatment at the Institute for Experimental Phonetics and Speech Pathology "Đorđe Kostić" and 18 parents were members of the Association of parents of children with autism. In this study, we used The Parental Stress Scale (Berry & Jones, 1995) to assess the level of stress among parents. The results show that there are no statistically significant differences in the level of stress in relation to parental sex, parental age, the child's age and child's expressive language development. We found a statistically significant effect of parental education level (p=0.005), child's receptive language development (p=0.008), and child's verbal communication development (p=0.015) on parental stress level.Parental lower education level, child's inability to understand speech, and undeveloped verbal communication of the child can lead to greater parental stress. The stress of parents can significantly complicate and slow down the process of child rehabilitation. It is important to know that it is equally necessary to support fathers and mothers, parents of all ages, parents of children of all ages and different speech and language skills and that particular attention should be given to parents with lower education.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.