In this paper, a new method for the classification of Alzheimer’s disease (AD) using multi-feature combination of structural magnetic resonance imaging is proposed. Firstly, hippocampal segmentation and cortical thickness and volume measurement were performed using FreeSurfer software. Then, histogram, gradient, length of gray level co-occurrence matrix and run-length matrix were used to extract the three-dimensional (3D) texture features of the hippocampus, and the parameters with significant differences between AD, MCI and NC groups were selected for correlation study with MMSE score. Finally, AD, MCI and NC are classified and identified by the extreme learning machine. The results show that texture features can provide better classification results than volume features on both left and right sides. The feature parameters with complementary texture, volume and cortical thickness had higher classification recognition rate, and the classification accuracy of the right side (100%) was higher than that of the left side (91.667%). The results showed that 3D texture analysis could reflect the pathological changes of hippocampal structures of AD and MCI patients, and combined with multi-feature analysis, it could better reflect the essential differences between AD and MCI cognitive impairment, which was more conducive to clinical differential diagnosis.
The electroencephalogram (EEG) signal is a general reflection of the neurophysiological activity of the brain, which has the advantages of being safe, efficient, real-time and dynamic. With the development and advancement of machine learning research, automatic diagnosis of Alzheimer’s diseases based on deep learning is becoming a research hotspot. Started from feedforward neural networks, this paper compared and analysed the structural properties of neural network models such as recurrent neural networks, convolutional neural networks and deep belief networks and their performance in the diagnosis of Alzheimer’s disease. It also discussed the possible challenges and research trends of this research in the future, expecting to provide a valuable reference for the clinical application of neural networks in the EEG diagnosis of Alzheimer’s disease.
ObjectivesTo systematically review the efficacy and safety of butylphthalide soft capsule with routine treatment for Alzheimer’s disease (AD).MethodsDatabases including CNKI, WanFang Data, VIP, CBM, PubMed, EMbase, and The Cochrane Library were electronically searched from September 2002 to July 2018 to collect randomized controlled trials of butylphthalide soft capsule with routine treatment for Alzheimer’s disease. The trial was screened based on inclusion and exclusion criteria, and the methodological quality of the included trial was assessed. Meta-analysis was then performed by Revman 5.3 software.ResultsA total of 8 studies involving 576 patients were included. The butylphthalide soft capsule group included 283 patients and the control group included 293 patients. The result of meta-analysis showed that butylphthalide soft capsule with routine treatment (Donepezil hydrochloride or Memantine or EGb761) significantly improved the score of mini-mental state examination (MMSE) (MD=3.19, 95% CI 2.69 to 3.69, P<0.001) and clinical efficacy (RR=1.36, 95%CI 1.21 to 1.53, P<0.001). There was no significant difference in number of adverse events between the butylphthalide group and the control group (RR=1.13, 95%CI 0.77 to 1.67, P=0.52).ConclusionsBased on the routine treatment, combining with butylphthalide soft capsule can further facilitate cognitive function of AD and improve clinical efficacy. At the same time, no increase in adverse reactions has been found. However, due to the low quality of the included studies, more high quality randomized controlled trials are required to verify the results.
Objective To analyze the characteristic and temporal trend in mortality and disease burden of Alzheimer’s disease (AD) and other forms of dementia in Guangzhou from 2008 to 2019, and estimate the disease burden attributable to smoking to provide evidence for promoting local health policy of prevention and intervention of dementia. Methods Based on the data of Guangzhou surveillance point of the National Mortality Surveillance System (NMSS), the crude mortality, standardized mortality, years of life lost (YLL) of AD and other dementia were calculated. The indirect method was used to estimate years lived with disability (YLD) and disability-adjusted life years (DALY).The distribution and changing trends of the index rates were compared from 2008 to 2019 using Joinpoint Regression Program. Based on the data of Guangzhou Chronic Disease and Risk Factors Monitoring System in 2013, the indexes of disease burden of AD and other forms of dementia attributable to smoking in 2018 was calculated. Results The standardized mortality rate, YLL rate, YLD rate and DALY rate of AD and other forms of dementia in Guangzhou increased from 0.45/100 000, 0.05‰, 0.02‰ and 0.07 ‰ in 2008 to 1.28/100 000, 0.15‰, 0.07‰ and 0.22‰ in 2019, respectively. The average annual changing trend was statistically significant (AAPC=11.30%, 13.09%, 13.09%, 13.09%, P<0.001）. In most years, the mortality and disease burden of women were higher than those of men, but men had higher growing trend than women in standardized mortality rate, YLL rate, YLD rate and DALY rate from 2008 to 2019, with a slower growing speed after the year 2012.The disease burden of dementia attributable to smoking in men was significantly higher than that in women. Conclusion The mortality and disease burden of AD and other forms of dementia in Guangzhou have dramatically increased over the past twelve years. Intervention against modifiable factors such as smoking, and prevention and screening for dementia in key populations should be strengthened. Support policies for dementia care management should be adopted to reduce the disease burden caused by premature death and disability.
Objective To generate eukaryotic expression vector of pcDNA3.1-β-site amyloid precursor protein cleaving enzyme (BACE) and obtain its transient expression in COS-7 cells. Methods A 1.5 kb cDNA fragment was amplified from the total RNA of the human neuroblastoma cells by the RT-PCR method and was cloned into the plasmid pcDNA3.1. The vector was identified by the double digestion with restriction enzymes BamHI and XhoI and was sequenced by the Sanger-dideoxy-mediated chain termination. The expression of the BACE gene was detected by immunocytochemistry. Results The results showed that the cDNA fragment included 1.5 kb total coding region. The recombinant eukaryotic cell expression vector of pcDNA3.1-BACE was constructed successfully, and the sequence of insert was identical to the published sequence. The COS-7 cells transfected with the pcDNA3.1BACE plasmid expressed a high level of the BACE protein in the cytoplasm. Conclusion The recombinant plasmid pcDNA3.1-BACE can provide a very useful tool for the research on the cause of Alzheimer’s disease and lay an important foundation for preventing Alzheimer’s disease.
Objective To evaluate the relationship between genetic polymorphism of ApoE and Alzheimer’s disease in Chinese population. Methods Such databases as PubMed, EBSCO, CNKI, CBM, and WangFang Data were searched from their establishment to December 2010 to collect the literature about the relationship between genetic polymorphism of ApoE and Alzheimer’s disease in Chinese population. RevMan 5.0 was adopted to conduct consistency check and data merging, and to evaluate publication bias. Results ApoEε4 was the risky allele (Plt;0.05) in Chinese population, and its pooled odds ratios and 95%CI was 3.53 (2.49 to 5.00). ApoEε3 was the protective alleles (Plt;0.05) in Chinese population, and its pooled odds ratios and 95%CI was 0.52 (0.40 to 0.68). ApoEε4/ε4, ApoEε4/ε3, and ApoEε4/ε2 were the risky genotypes (all Plt;0.05) in Chinese population, and their pooled odds ratios and 95%CI were 10.17 (4.25 to 24.19), 2.57 (2.04 to 3.25), and 1.94 (1.13 to 3.34), respectively. ApoEε3/ε3 was the protective genotype (Plt;0.05) in Chinese population, and its pooled odds ratios and 95%CI was 0.67 (0.57 to 0.77). Conclusion In Chinese population, some ApoE alleles and genotypes are associated with Alzheimer’s disease.
Alzheimer’s disease (AD) classification models usually segment the entire brain image into voxel blocks and assign them labels consistent with the entire image, but not every voxel block is closely related to the disease. To this end, an AD auxiliary diagnosis framework based on weakly supervised multi-instance learning (MIL) and multi-scale feature fusion is proposed, and the framework is designed from three aspects: within the voxel block, between voxel blocks, and high-confidence voxel blocks. First, a three-dimensional convolutional neural network was used to extract deep features within the voxel block; then the spatial correlation information between voxel blocks was captured through position encoding and attention mechanism; finally, high-confidence voxel blocks were selected and combined with multi-scale information fusion strategy to integrate key features for classification decision. The performance of the model was evaluated on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and Open Access Series of Imaging Studies (OASIS) datasets. Experimental results showed that the proposed framework improved ACC and AUC by 3% and 4% on average compared with other mainstream frameworks in the two tasks of AD classification and mild cognitive impairment conversion classification, and could find the key voxel blocks that trigger the disease, providing an effective basis for AD auxiliary diagnosis.
Alzheimer’s disease (AD) is an irreversible neurodegenerative disorder that damages patients’ memory and cognitive abilities. Therefore, the diagnosis of AD holds significant importance. The interactions between regions of interest (ROIs) in the brain often involve multiple areas collaborating in a nonlinear manner. Leveraging these nonlinear higher-order interaction features to their fullest potential contributes to enhancing the accuracy of AD diagnosis. To address this, a framework combining nonlinear higher-order feature extraction and three-dimensional (3D) hypergraph neural networks is proposed for computer-assisted diagnosis of AD. First, a support vector machine regression model based on the radial basis function kernel was trained on ROI data to obtain a base estimator. Then, a recursive feature elimination algorithm based on the base estimator was applied to extract nonlinear higher-order features from functional magnetic resonance imaging (fMRI) data. These features were subsequently constructed into a hypergraph, leveraging the complex interactions captured in the data. Finally, a four-dimensional (4D) spatiotemporal hypergraph convolutional neural network model was constructed based on the fMRI data for classification. Experimental results on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database demonstrated that the proposed framework outperformed the Hyper Graph Convolutional Network (HyperGCN) framework by 8% and traditional two-dimensional (2D) linear feature extraction methods by 12% in the AD/normal control (NC) classification task. In conclusion, this framework demonstrates an improvement in AD classification compared to mainstream deep learning methods, providing valuable evidence for computer-assisted diagnosis of AD.
Biological markers play a pivotal role in the early and accurate diagnosis of Alzheimer’s disease, enabling precise identification and monitoring of therapeutic interventions. The detection of central β-amyloid and Tau proteins has become an indispensable tool in clinical trials. Recent years have witnessed substantial progress in the development of readily accessible and cost-effective blood biomarkers. This comprehensive article provides a comprehensive overview of the clinical applications of blood biomarkers, encompassing β-amyloid, phosphorylated Tau protein, neurofilament light chain protein, and glial fibrillary acidic protein, all of which have demonstrated clinical relevance in Alzheimer’s disease diagnosis. Notably, phosphorylated Tau protein exhibits superior diagnostic efficacy. The incorporation of blood biomarkers facilitates early screening, accurate diagnosis, and efficacious treatment of Alzheimer’s disease.
Normal brain aging and a serious of neurodegenerative diseases may lead to decline in memory, attention and executive ability and poorer quality of life. The mechanism of the decline is not clear now and is still a hot issue in the fields of neuroscience and medicine. A large number of researches showed that resting state functional brain networks based functional magnetic resonance imaging (fMRI) are sensitive and susceptive to the change of cognitive function. In this paper, the researches of brain functional connectivity based on resting fMRI in recent years were compared, and the results of subjects with different levels of cognitive decline including normal brain aging, mild cognitive impairment (MCI) and Alzheimer’s disease (AD) were reviewed. And the changes of brain functional networks under three different levels of cognitive decline are introduced in this paper, which will provide the basis for the detection of normal brain aging and clinical diseases.
