12 April 2022 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Altered resting-state EEG activity has been repeatedly reported in major depressive disorder (MDD), but no robust biomarkers have been identified until now. The poor consistency of EEG alterations may be due to inconsistent resting conditions; that is, the eyes-open (EO) and eyes-closed (EC) conditions. Here, we explored the effect of the EO and EC conditions on EEG biomarkers for discriminating MDD subjects and healthy control (HC) subjects. EEG data were recorded from 30 first-episode MDD and 26 HC subjects during an 8-min resting-state session. The features were extracted using spectral power, Lempel–Ziv complexity, and detrended fluctuation analysis. Significant features were further selected via the sequential backward feature selection algorithm. Support vector machine (SVM), logistic regression, and linear discriminate analysis were used to determine a better resting condition to provide more reliable estimates for identifying MDD. Compared with the HC group, we found that the MDD group exhibited widespread increased $\beta $ and $\gamma $ powers ( ${p} < 0.01$ ) in both conditions. In the EO condition, the MDD group showed increased complexity and scaling exponents in the $\alpha $ band relative to HC subjects ( ${p} < 0.05$ ). The best classification performance of the combined feature sets was found in the EO condition, with the leave-one-out classification accuracy of 89.29%, sensitivity of 90.00%, and specificity of 88.46% using SVM with the linear kernel classifier when the threshold was set to 0.7, followed by the $\beta $ and $\gamma $ spectral features with an average accuracy of 83.93%. Overall, EO and EC conditions indeed affected the between-group variance, and the EO condition is suggested as the more separable resting condition to identify depression. Specially, the $\beta $ and $\gamma $ powers are suggested as potential biomarkers for first-episode MDD.
1 January 2025 in Depression and Anxiety
Background: Aberrant gamma oscillations in major depressive disorder (MDD) have attracted extensive attention, but evidence delineating such neural signatures is lacking. The auditory steady‐state response (ASSR) elicited by periodic auditory stimuli is a robust probe of gamma oscillations. Here, we sought to characterize early transient auditory evoked responses (AEPs) and sustained gamma ASSRs in MDD, thereby identifying reliable neurophysiological signatures and providing preliminary interpretations of gamma auditory response deficits in MDD. Methods: Electroencephalographic data were obtained from 40 first‐episode drug‐naïve patients with MDD and 41 demographically matched healthy controls (HCs) during a 40‐Hz ASSR paradigm, encompassing two periodic stimuli—chirp and click stimuli. Source analysis of transient AEPs was performed to identify generators involved in early information processing dysfunction. In addition, spectrotemporal and spatial characteristics of 40‐Hz ASSRs were analyzed using event‐related spectral perturbation, inter‐trial phase coherence, and functional connectivity index. Results: Compared to HCs, patients showed a reduced P200 amplitude that was source‐localized to the middle temporal gyrus, possibly reflecting an underlying impairment in the processes of early allocation or auditory information perception within the auditory pathways. Meanwhile, attenuated 40‐Hz power and phase coherence, in conjunction with suppressed right frontotemporal and frontocentral connectivity, were observed in MDD, highlighting the multidimensional entrained gamma inhibition. Correlation analyses revealed that the decreased right frontocentral connectivity was strongly related to increased anxiety severity. Importantly, these abnormalities correlated with the patient’s symptoms were only found with the chirp stimulus, suggesting that the chirp stimulus has tremendous potential to reveal specific neurophysiological signatures of MDD. Conclusions: Our data reveal impaired gamma auditory responses in first‐episode drug‐naïve patients with MDD and suggest that right frontocentral connectivity elicited by the chirp stimulus may represent a promising signature for predicting clinical symptoms.
9 April 2021 in Journal of Ambient Intelligence and Humanized Computing
Through the COVID-19 epidemic in 2020, the society has deeply realized the inevitability and necessity of building a community that shares the future of mankind. In the face of severely complex international trends and domestic and international economic conditions, artificial intelligence plays an important auxiliary role in the regular prevention and management of COVID-19. In order to effectively correspond to the formalized extensional prevention and control theory, it is essential to use coordination models, rule systems, prevention and control mechanisms, and governance landscapes to build artificial intelligence corresponding systems. This article uses a basic genetic algorithm to realize the robot path plan. This mainly includes the establishment of environmental models, the discovery of chromosomes and the determination of coding methods, the selection and design of fitness functions, and related designs. This paper proposes a new adaptive adjustment mode based on the basic genetic algorithm, which improves the selection and mutation operation, and improves the optimization efficiency of the genetic algorithm. Building an artificial intelligence response system may face various technical risks and governance dilemmas. Only by improving the rule system of artificial intelligence, creating an epidemic prevention and control ecology, conserving the public spirit of the whole people, strengthening the governance of the source of crisis, and further improving the new momentum of economic and social development and public safety. The modernization of governance capabilities can better respond to the current complex situation.