Search

IntroductionAlzheimer's Disease (AD) is a common dementia which affects linguistic function, memory, cognitive and visual spatial ability of the patients. Language is proved to have the relationship with AD, so the time that AD can be diagnosed in a doctor's office is coming.MethodsIn this study, the Pitt datasets are used to detect AD which is balanced in gender and age. First bidirectional Encoder Representation from Transformers (Bert) pretrained model is used to acquire the word vector. Then two channels are constructed in the feature extraction layer, which is, convolutional neural networks (CNN) and long and short time memory (LSTM) model to extract local features and global features respectively. The local features and global features are concatenated to generate feature vectors containing rich semantics, which are sent to softmax classifier for classification.ResultsFinally, we obtain a best accuracy of 89.3% which is comparative compared to other studies. In the meanwhile, we do the comparative experiments with TextCNN and LSTM model respectively, the combined model manifests best and TextCNN takes the second place.DiscussionThe performance illustrates the feasibility to predict AD effectively by using acoustic and linguistic datasets.

BackgroundAlzheimer's disease (AD) is difficult to diagnose on the basis of language because of the implicit emotion of transcripts, which is defined as a supervised fuzzy implicit emotion classification at the document level. Recent neural network-based approaches have not paid attention to the implicit sentiments entailed in AD transcripts.MethodA two-level attention mechanism is proposed to detect deep semantic information toward words and sentences, which enables it to attend to more words and fewer sentences differentially when constructing document representation. Specifically, a document vector was built by progressively aggregating important words into sentence vectors and important sentences into document vectors.ResultsExperimental results showed that our method achieved the best accuracy of 91.6% on annotated public Pitt corpora, which validates its effectiveness in learning implicit sentiment representation for our model.ConclusionThe proposed model can qualitatively select informative words and sentences using attention layers, and this method also provides good inspiration for AD diagnosis based on implicit sentiment transcripts.

Mobile phone use has rapidly increased worldwide, and pregnant women are passively or actively exposed to the associated electromagnetic radiation. Maternal cell phone exposure is related to behavioral difficulties in young offspring. However, whether prenatal mobile phone exposure can predispose the elderly offspring to cognitive impairment is unclear. The enriched environment (EE) has shown positive effects on cognition in an immature brain, but its impact on aging offspring after prenatal cell phone exposure is unknown. This study aimed to investigate whether prenatal exposure to mobile phone exerts long-term effects on cognition in elderly rat offspring and whether EE during adulthood can rescue cognitive impairment by altering the synaptic plasticity. Pregnant rats were subjected to prenatal short-term or long-term cell phone exposure and offspring rats were randomly assigned to standard or EE. Spatial learning and memory were investigated using Morris water maze (MWM) in elderly rat offspring. Hippocampal cellular morphology was assessed by hematoxylin-eosin staining and synaptic ultrastructure was evaluated with transmission electron microscopy. Expression of synaptophysin (SYN), postsynaptic density-95 (PSD-95), and brain-derived neurotrophic factor (BDNF) were detected by western blot. The results demonstrated that prenatal long-term but not short-term exposure to mobile phone lead to cognitive impairment, morphological changes in the hippocampal cells, reduced synaptic number, decreased SYN, PSD-95, and BDNF expression in elderly offspring, which were alleviated by postnatal EE housing. These findings suggest that prenatal long-term mobile phone exposure may pose life-long adverse effects on elderly offspring and impair cognition by disrupting the synaptic plasticity, which may be reversed by postnatal EE housing.