The recurrent neural network architecture improves the processing ability of time-series data. However, issues such as exploding gradients and poor feature extraction limit its application in the automatic diagnosis of mild cognitive impairment (MCI). This paper proposed a research approach for building an MCI diagnostic model using a Bayesian-optimized bidirectional long short-term memory network (BO-BiLSTM) to address this problem. The diagnostic model was based on a Bayesian algorithm and combined prior distribution and posterior probability results to optimize the BO-BiLSTM network hyperparameters. It also used multiple feature quantities that fully reflected the cognitive state of the MCI brain, such as power spectral density, fuzzy entropy, and multifractal spectrum, as the input of the diagnostic model to achieve automatic MCI diagnosis. The results showed that the feature-fused Bayesian-optimized BiLSTM network model achieved an MCI diagnostic accuracy of 98.64% and effectively completed the diagnostic assessment of MCI. In conclusion, based on this optimization, the long short-term neural network model has achieved automatic diagnostic assessment of MCI, providing a new diagnostic model for intelligent diagnosis of MCI.
Transcranial direct current stimulation (tDCS) is a non-invasive neuromodulation technique that can modulate cortical neuronal excitability through scalp electrodes, thereby potentially enhancing cognitive function. However, to date, no specific stimulation targets have been identified in studies on tDCS for improving cognitive function. Previous research has suggested that the left dorsolateral prefrontal cortex (DLPFC) and parietal-occipital regions (PO) of the human brain may be potential therapeutic targets. Based on this, the present study aims to compare the mechanisms of how tDCS affect working memory by modulating DLPFC and PO regions, providing empirical support for clinical application. According to different stimulation targets, the experiment was divided into DLPFC group, PO group and sham group in this study. A total of 20 participants were recruited to participate in the tDCS regulation trial. Each participant was randomly assigned to receive two types of stimuli, with a minimum interval of 3 days between each stimulus (a total of 40 stimuli). This study designed the "3-back " working memory task paradigm, calculated and analyzed the reaction time (RT) and accuracy (AC) of three groups of subjects in cognitive tasks before and after receiving tDCS regulation. This study collected resting state electroencephalogram (EEG) signals from three groups of subjects before and after regulation, and compared and analyzed the autocorrelation of each brain functional area, the cross-correlation between different brain functional regions, and the corresponding network topology characteristics. The results showed that after regulation, for subjects in the DLPFC group and PO group, the AC increased and RT decreased, with the DLPFC group demonstrating better effects. Additionally, DLPFC stimulation could enhance the autocorrelation and cross-brain connectivity of targets and related brain regions in the theta and beta frequency bands, and improve the clustering coefficient and local efficiency of brain regions in these frequency bands. However, PO stimulation and sham stimulation had no such effects. This study confirms that tDCS stimulation of DLPFC can improve cognitive function by enhancing the network connectivity of brain regions related to the theta and beta frequency bands, providing experimental evidence and theoretical support for the clinical rehabilitation of brain cognitive dysfunction using tDCS.
In order to fully explore the neural oscillatory coupling characteristics of patients with mild cognitive impairment (MCI), this paper analyzed and compared the strength of the coupling characteristics for 28 MCI patients and 21 normal subjects under six different-frequency combinations. The results showed that the difference in the global phase synchronization index of cross-frequency coupling under δ-θ rhythm combination was statistically significant in the MCI group compared with the normal control group (P = 0.025, d = 0.398). To further validate this coupling feature, this paper proposed an optimized convolutional neural network model that incorporated a time-frequency data enhancement module and batch normalization layers to prevent overfitting while enhancing the robustness of the model. Based on this optimized model, with the phase locking value matrix of δ-θ rhythm combination as the single input feature, the diagnostic accuracy of MCI patients was (95.49 ± 4.15)%, sensitivity and specificity were (93.71 ± 7.21)% and (97.50 ± 5.34)%, respectively. The results showed that the characteristics of the phase locking value matrix under the combination of δ-θ rhythms can adequately reflect the cognitive status of MCI patients, which is helpful to assist the diagnosis of MCI.