• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.178-190
• /
• 2021

Alzheimer's disease (AD) is an insidious and degenerative neurological disease. It is a new topic for AD patients to use magnetic resonance imaging (MRI) and computer technology and is gradually explored at present. Preprocessing and correlation analysis on MRI data are firstly made in this paper. Then kernel principal component analysis (KPCA) is used to extract features of brain gray matter images. Finally supervised classification schemes such as AdaBoost algorithm and support vector machine algorithm are used to classify the above features. Experimental results by means of AD program Alzheimer's Disease Neuroimaging Initiative (ADNI) database which contains brain structural MRI (sMRI) of 116 AD patients, 116 patients with mild cognitive impairment, and 117 normal controls show that the proposed method can effectively assist the diagnosis and analysis of AD. Compared with principal component analysis (PCA) method, all classification results on KPCA are improved by 2%-6% among which the best result can reach 84%. It indicates that KPCA algorithm for feature extraction is more abundant and complete than PCA.

• Journal of Multimedia Information System
• /
• v.9 no.1
• /
• pp.21-32
• /
• 2022

Early-stage diagnosis of Alzheimer's Disease (AD) from Cognitively Normal (CN) patients is crucial because treatment at an early stage of AD can prevent further progress in the AD's severity in the future. Recently, computer-aided diagnosis using magnetic resonance image (MRI) has shown better performance in the classification of AD. However, these methods use a traditional machine learning algorithm that requires supervision and uses a combination of many complicated processes. In recent research, the performance of deep neural networks has outperformed the traditional machine learning algorithms. The ability to learn from the data and extract features on its own makes the neural networks less prone to errors. In this paper, a dense neural network is designed for binary classification of Alzheimer's disease. To create a classifier with better results, we studied result of different activation functions in the prediction. We obtained results from 5-folds validations with combinations of different activation functions and compared with each other, and the one with the best validation score is used to classify the test data. In this experiment, features used to train the model are obtained from the ADNI database after processing them using FreeSurfer software. For 5-folds validation, two groups: AD and CN are classified. The proposed DNN obtained better accuracy than the traditional machine learning algorithms and the compared previous studies for AD vs. CN, AD vs. Mild Cognitive Impairment (MCI), and MCI vs. CN classifications, respectively. This neural network is robust and better.

• Journal of Korean society of Dental Hygiene
• /
• v.22 no.5
• /
• pp.411-416
• /
• 2022

Objectives: This study aimed to identify pathogenic microorganisms in the oral cavity of Alzheimer's dementia patients and recognize the necessity and importance of oral prevention management. Methods: The participants comprised 40 dementia patients aged 60 years or older and general patients who were using nursing care facilities in Gwangju from February to July 2017. Samples were collected with Eazyperio products for oral pathogenic microbial testing. Eighteen types of bacteria could be detected by analyzing Multiplex-Quantity Real Time polymerase chain reaction at a genetic testing agency. Results: The study comprised more women than men. Most participants were in their 80s. Statistically significant differences were observed in some oral pathogenic microorganisms. Conclusions: Pathogenic microorganisms could more easily proliferate in the oral cavities of Alzheimer's dementia patients than they could among general elderly participants due to a lack of awareness of oral hygiene and prevention management. To improve this, it is considered necessary to deploy oral health care professionals.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.86-93
• /
• 2024

The development of functional magnetic resonance imaging (fMRI) has significantly contributed to mapping brain functions and understanding brain networks during rest. This paper proposes a CNN-LSTM-based classification model to classify the progression stages of Alzheimer's disease. Firstly, four preprocessing steps are performed to remove noise from the fMRI data before feature extraction. Secondly, the U-Net architecture is utilized to extract spatial features once preprocessing is completed. Thirdly, the extracted spatial features undergo LSTM processing to extract temporal features, ultimately leading to classification. Experiments were conducted by adjusting the temporal dimension of the data. Using 5-fold cross-validation, an average accuracy of 96.4% was achieved, indicating that the proposed method has high potential for identifying the progression of Alzheimer's disease by analyzing fMRI data.

• BMB Reports
• /
• v.48 no.1
• /
• pp.13-18
• /
• 2015

Alzheimer's disease severely compromises cognitive function. One of the mechanisms to explain the pathology of Alzheimer's disease has been the hypotheses of amyloid-pore/channel formation by complex $A{\beta}$-aggregates. Clinical studies suggested the moderate alcohol consumption can reduces probability developing neurodegenerative pathologies. A recent report explored the ability of ethanol to disrupt the generation of complex $A{\beta}$ in vitro and reduce the toxicity in two cell lines. Molecular dynamics simulations were applied to understand how ethanol blocks the aggregation of amyloid. On the other hand, the in silico modeling showed ethanol effect over the dynamics assembling for complex $A{\beta}$-aggregates mediated by break the hydrosaline bridges between Asp 23 and Lys 28, was are key element for amyloid dimerization. The amyloid pore/ channel hypothesis has been explored only in neuronal models, however recently experiments suggested the frog oocytes such an excellent model to explore the mechanism of the amyloid pore/channel hypothesis. So, the used of frog oocytes to explored the mechanism of amyloid aggregates is new, mainly for amyloid/pore hypothesis. Therefore, this experimental model is a powerful tool to explore the mechanism implicates in the Alzheimer's disease pathology and also suggests a model to prevent the Alzheimer's disease pathology.

• Korean Journal of Biological Psychiatry
• /
• v.12 no.2
• /
• pp.98-106
• /
• 2005

Objectives:Donepezil is a widely used drug for the treatment of patients with Alzheimer's disease(AD). The aim of the present study was to clarify the efficacy and the characteristics of responders to donepezil. Methods:Patients with probable AD(n=80;75.7 years) and small vessel dementia(SVD)(n=18;77.8 years) who received donepezil were retrospectively analyzed using Alzheimer's registry, and three questions were asked:1) Does donepezil therapy improves cognitive symptoms in patients with dementia? 2) If donepezil improves cognitive symptoms, which items of the K-MMSE are improved? 3) What are the characteristics of responder to donepezil medication? Results:1) After donepezil medication, cognitive function measured by the K-MMSE was significantly improved in both types of dementia(AD and SVD), However, statistical differences were not found between these groups. 2) In a clinical trial of donepezil, the patients performed better than before mediation on K-MMSE items assessing orientation, recall, construction, concentration, calculation. 3) In AD, the K-MMSE score before medication was closely related with response of donepezil. Conclusion:This study suggests that donepezil improves various cognitive functions in both types of dementia, and the responsive group had significantly lower K-MMSE scores than the non-responsive group before medication.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.19 no.1
• /
• pp.130-138
• /
• 2005

This experiment was designed to investigate the effect of Phellodendron amurense(PLDA) on the Alzheimer's disease. The effects of PLDA extract on $IL-1{\beta}$, IL-6, amyloid precursor proteins(APP), acetylcholinesterase(AChE), glial fibrillary acidic protein(GFAP) mRNA of PC-12 cell treated by $A{\beta}$ plus $rIL-1{\beta}$ and AChE activity of PC-12 cell lysate treated by $A{\beta}$ plus $rIL-1{\beta}$ and behavior of memory deficit mice induced by scopolamine and mice glucose, uric acid, AChE activity of memory deficit rats induced by scopolamine were investigated, respectively. PLDA extract suppressed $IL-1{\beta}$, IL-6, APP, AChE, GFAP mRNA in PC-12 cell treated by $A{\beta}$ plus $rIL-1{\beta}$ ; AChE activity in cell lysate of PC-12 cell treated by $A{\beta}$ plus $rIL-1{\beta}$. PLDA extract increased glucose, decreased uric acid and AChE significantly in the serum of the memory deficit rats induced by scopolamine. PLDA extract group showed significantly inhibitory effect on the memory deficit of mice induced by scopolamine in the experiment of Morris water maze. According to the above results, it is suggested that PLDA extract might be usefully applied for prevention and treatment of Alzheimer's disease.

• Journal of Oriental Neuropsychiatry
• /
• v.18 no.1
• /
• pp.63-78
• /
• 2007

Objective : This experiment was designed to investigate the effect of Thalictrum foetidum(TFD) on the Alzheimer's disease. Method : The effects of TFD on amyloid precursor proteins(APP), acetylcholinesterase(AChE), glial fibrillary acidic protein(GFAP) mRNA of PC-12 cell treated by amyloid ${\beta}$ $protein(A{\beta})$ and $IL-1{\beta}$, IL-6, $TNF-{\alpha}$ mRNA of THP-l cell treated by lipopolysaccharide(LPS), AChE activity of PC-12 cell lysate treated by $A{\beta}$ and behavior of the memory deficit mice induced by scopolamine, and glucose, AChE in serum of the memory deficit mice induced by scopolamine were investigated, respectively. Results : The results were summarized as follows ; 1. TFD suppressed APP, AChE, GFAP mRNA in PC-12 cell treated by $A{\beta}$. 2. TFD suppressed $IL-1{\beta}$, IL-6, $TNF-{\alpha}$ mRNA in THP-l cell treated by LPS 3.. TFD suppressed AChE activity in cell lysate of PC-12 cell treated by $A{\beta}$. 4. TFD increased glucose and decreased AChE significantly in the serum of the memory deficit mice induced by scopolamine. 5. TFD group showed significantly inhibitory effect on the scopolamine-induced impairment of learning and memory in the experiment of Morris water maze. Conclusion : According to the above results, it is suggested that TFD might be usefully applied for prevention and treatment of Alzheimer's disease.

• Journal of Oriental Neuropsychiatry
• /
• v.28 no.4
• /
• pp.401-408
• /
• 2017

Objectives: The purpose of this study is to obtain the differential variable and learning effect of the serial position effect, targeting individuals aged 60 years and over. A total of 89 individuals were categorized into the following groups: Alzheimer's group, vascular dementia group, elderly depression group, and normal group. Methods: Considering the size of the groups used for comparison, of the total 89 participants, 28 were in the Alzheimer's group, 24 in the vascular dementia group, 16 in the elderly depression group, and 21 were randomly chosen for the normal group. In the CERAD-K word list memory test, 10 words were shown to the subjects. We then asked them to freely recall the words. After changing the order of the words three times, the same process was followed. Results: First, a significant difference was observed among the groups in terms of word recalling rate. The analysis conducted afterward showed that, as predicted, the depressed group showed significantly better performance in recalling the words. Second, the vascular dementia patients and the Alzheimer's patients showed, as predicted, better recall of the largest recency region of words shown. Third, the normal group and the elderly depressed group showed a high-performance rate, proving that the reiterative method can contribute to the recalling process. Thus, we demonstrated that the Alzheimer's group showed the deterioration of short memory recalling skills and the elderly depressed showed deteriorated output performance skill.

• Korean Journal of Clinical Pharmacy
• /
• v.27 no.3
• /
• pp.161-170
• /
• 2017

Background: There is recent evidence that insulin resistance is responsible for increasing the risk of developing cognitive dysfunction. To systematically review the influence of intranasal insulin treatment on the cognitive function in Alzheimer's disease patients. Methods: Randomized controlled trials comparing the cognitive effects of intranasal insulin therapy in Alzheimer's disease patients with controlled interventions were retrieved from Pubmed, Medline, Embase and Cochrane library. Meta-analysis was conducted on the cognitive measurements with a subgroup analysis by dose, gender and apolipoprotein E allele 4 (ApoE ${\varepsilon}4$) status. Results: Seven randomized controlled trials were eligible for inclusion. Intranasal insulin had a positive influence on the cognitive function as compared to placebo without a statistical significance (standardized mean difference; SMD = 0.109; 95% confidence interval; CI -0.04 to 0.26; P=0.14). In subgroup analysis, a 20 IU dose of intranasal insulin induced a significant improvement in cognitive function (SMD = 0.14; 95% CI 0.05 to 0.24; P=0.004), but 40 IU did not show this effect (SMD = -0.01; 95% CI -0.11 to 0.09; P=0.82). ApoE ${\varepsilon}4$ positive patients showed a significant decline in cognitive function as compared to ApoE ${\varepsilon}4$ positive patients in the control group (SMD = -0.213; 95% CI -0.38 to -0.04; P=0.015). Such an effect was not apparent in ApoE ${\varepsilon}4$ negative patients. Gender had no influence on the cognitive outcomes. Conclusion: The results indicate that intranasal insulin may have beneficial effect in improving the cognitive function in Alzheimer's disease patients.