• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1055-1056
• /
• 2023

이 논문은 음성 데이터를 이용하여 치매 징후를 진단하는 프로그램을 개발하는 과정과 결과에 대해 소개한다. MFCC (Mel-frequency cepstral coefficients) 기술을 사용하여 음성 패턴을 추출하고 기계 학습 모델을 적용하여 치매 징후를 탐지하는 방법을 설명한다. 실험 결과는 치매 조기 진단 및 관리에 유용한 음성 기반 도구의 중요성을 강조한다.

• Smart Media Journal
• /
• v.13 no.6
• /
• pp.90-97
• /
• 2024

This paper focuses on detecting Alzheimer's Disease (AD). The most usual form of dementia is Alzheimer's disease, which causes permanent cause memory cell damage. Alzheimer's disease, a neurodegenerative disease, increases slowly over time. For this matter, early detection of Alzheimer's disease is important. The purpose of this work is using Magnetic Resonance Imaging (MRI) to diagnose AD. A Convolution Neural Network (CNN) model, Reset, and VGG the pre-trained learning models are used. Performing analysis and validation of layers affects the effectiveness of the model. T1-weighted MRI images are taken for preprocessing from ADNI. The Dataset images are taken from the Alzheimer's Disease Neuroimaging Initiative (ADNI). 3D MRI scans into 2D image slices shows the optimization method in the training process while achieving 96% and 94% accuracy in VGG 16 and ResNet 18 respectively. This study aims to classify AD from brain 3D MRI images and obtain better results.

• Journal of Convergence for Information Technology
• /
• v.9 no.8
• /
• pp.248-253
• /
• 2019

Early diagnosis of mild cognitive impairment (MCI) can reduce the incidence of dementia. This study developed the MCI prediction model for the elderly in Korea. The subjects of this study were 3,240 elderly (1,502 men, 1,738 women) aged 65 and over who participated in the Korean Longitudinal Survey of Aging (KLoSA) in 2012. Outcome variables were defined as MCI prevalence. Explanatory variables were age, marital status, education level, income level, smoking, drinking, regular exercise more than once a week, average participation time of social activities, subjective health, hypertension, diabetes Respectively. The prediction model was developed using Restricted Boltzmann Machine (RBM) neural network. As a result, age, sex, final education, subjective health, marital status, income level, smoking, drinking, regular exercise were significant predictors of MCI prediction model of rural elderly people in Korea using RBM neural network. Based on these results, it is required to develop a customized dementia prevention program considering the characteristics of high risk group of MCI.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.11
• /
• pp.2924-2944
• /
• 2023

Alzheimer's disease (AD) is a neurological condition that is recognized as one of the primary causes of memory loss. AD currently has no cure. Therefore, the need to develop an efficient model with high precision for timely detection of the disease is very essential. When AD is detected early, treatment would be most likely successful. The most often utilized indicators for AD identification are the Mini-mental state examination (MMSE), and the clinical dementia. However, the use of these indicators as ground truth marking could be imprecise for AD detection. Researchers have proposed several computer-aided frameworks and lately, the supervised model is mostly used. In this study, we propose a novel 3D Convolutional Neural Network Multilayer Perceptron (3D CNN-MLP) based model for AD classification. The model uses Attention Mechanism to automatically extract relevant features from Magnetic Resonance Images (MRI) to generate probability maps which serves as input for the MLP classifier. Three MRI scan categories were considered, thus AD dementia patients, Mild Cognitive Impairment patients (MCI), and Normal Control (NC) or healthy patients. The performance of the model is assessed by comparing basic CNN, VGG16, DenseNet models, and other state of the art works. The models were adjusted to fit the 3D images before the comparison was done. Our model exhibited excellent classification performance, with an accuracy of 91.27% for AD and NC, 80.85% for MCI and NC, and 87.34% for AD and MCI.

• Korean Journal of Biological Psychiatry
• /
• v.23 no.2
• /
• pp.63-68
• /
• 2016

Objectives Haenyeo are Korean professional women breath-hold divers in Jeju island. The aim of this study was to investigate the clinical characteristics of depressed Haenyeo group, compared to non-Haenyeo depressed group. Methods This study included 75 Haenyeo and 340 non-Haenyeo with depressive disorders recruited from the Dementia Early Detection Program in Jeju island. Structural diagnostic interviews were performed using the Korean version of Mini International Neuropsychiatric Interview. All patients completed the questionnaires, including the Subjective Memory Complaints Questionnaire (SMCQ), the Patient Health Questionnaire-15 (PHQ-15), and the Blessed dementia scale. Depression was evaluated by the Korean version of short form the Geriatric Depression Scale (K-SGDS) and cognition was assessed by the Korean version of the Consortium to Establish a Registry for Alzheimer's Disease (CERAD) assessment packet. Results Although the mean scores of the K-SGDS were similar between Haenyeo and non-Haenyeo depressed groups, the Haenyeo group showed a higher mean score on the PSQ-15 (p < 0.001, ANCOVA adjusting for age, the K-SGDS and education). The Haenyeo group showed poorer performance on the Korean Version of Frontal Assessment Batter (p < 0.001), the Mini-Mental State Examination in the Korean version of the CERAD Assessment Packet (p < 0.018), the word fluency test (p < 0.001), and the word list memory test (p = 0.012) in ANCOVA adjusting for age and education. The mean SMCQ score was higher in the Haenyeo depressed group than in the non-Haenyeo depressed group. Conclusions The Haenyeo depressed group shows cognitive dysfunction, especially frontal lobe dysfunction, compared to the non-Haenyeo depressed group, indicating the Haenyeo depressed group may have more severe frontolimbic dysfunction due to chronic exposure to hypoxia. The Haenyeo depressed group suffers more somatic symptoms than the non-Haenyeo depressed group.

• Korean Journal of Psychosomatic Medicine
• /
• v.24 no.2
• /
• pp.200-207
• /
• 2016

Objectives : Alzheimer's disease(AD) is characterized by progressive decline of cognitive function and also by various behavioral psychological symptoms of dementia(BPSD) which causes distress to their caregivers. The purpose of this study was to investigate association between each AD patients' behavioral psychological symptoms and their caregivers' burden. Methods : Participants were 80 AD patients and their caregivers. We used Korean neuropsychiatric inventory (K-NPI) to assess the symptoms of patients and Korean version of Zarit Burden Interview(ZBI) to evaluate caregivers' burden. Results : The results showed ZBI score, which is the index for caregivers' burden, had a statistically significant positive correlation with the frequency of delusion, hallucination, agitation/aggression, depression, anxiety, disinhibition and irritability, the severity of hallucination, agitation/aggression, anxiety, disinhibition, aberrant motor, and sleep, and the global score(frequency${\times}$severity) for delusion, hallucination, agitation/aggression, depression, anxiety, disinhibition, aberrant motor, and sleep. There were significant correlations between each scale for cognitive function(i.e. MMSE-KC, CDR, GDS) and ZBI scale. Correlations between each scale for activity of daily living(i.e. Barthel -ADL, K-ADL) and ZBI scale were also significant. Conclusions : There were a significant correlation between BPSD and caregiver burden. Caregiver burden was also correlated with cognitive function and activity of daily living. Early detection and preventive treatment of these symptoms in BPSD might make improvement of caregivers' quality of life as well as AD patients'.

• Journal of Preventive Medicine and Public Health
• /
• v.49 no.2
• /
• pp.134-138
• /
• 2016

Objectives: Season of birth, an exogenous indicator of early life environment, has been related to higher risk of adverse psychiatric outcomes but the findings for Alzheimer's disease (AD) have been inconsistent. We investigated whether the month or season of birth are associated with AD. Methods: A nationwide nested case-control study including all community-dwellers with clinically verified AD diagnosed in 2005 to 2012 (n=70 719) and up to four age- sex- and region of residence-matched controls (n=282 862) residing in Finland. Associations between month and season of birth and AD were studied with conditional logistic regression. Results: Month of birth was not associated with AD (p=0.09). No strong associations were observed with season (p=0.13), although in comparison to winter births (December-February) summer births (June-August) were associated with higher odds of AD (odds ratio, 1.03; 95% confidence interval, 1.00 to 1.05). However, the absolute difference in prevalence in winter births was only 0.5% (prevalence of those born in winter were 31.7% and 32.2% for cases and controls, respectively). Conclusions: Although our findings do not support the hypothesis that season of birth is related to AD/dementia risk, they do not invalidate the developmental origins of health and disease hypothesis in late-life cognition. It is possible that season does not adequately capture the early life circumstances, or that other (postnatal) risk factors such as lifestyle or socioeconomic factors overrule the impact of prenatal and perinatal factors.

• The Korean Journal of Physiology and Pharmacology
• /
• v.18 no.6
• /
• pp.447-456
• /
• 2014

Until now, a disease-modifying therapy (DMT) that has an ability to slow or arrest Alzheimer's disease (AD) progression has not been developed, and all clinical trials involving AD patients enrolled by clinical assessment alone also have not been successful. Given the growing consensus that the DMT is likely to require treatment initiation well before full-blown dementia emerges, the early detection of AD will provide opportunities to successfully identify new drugs that slow the course of AD pathology. Recent advances in early detection of AD and prediction of progression of the disease using various biomarkers, including cerebrospinal fluid (CSF) $A{\beta}_{1-42}$, total tau and p-tau181 levels, and imagining biomarkers, are now being actively integrated into the designs of AD clinical trials. In terms of therapeutic mechanisms, monitoring these markers may be helpful for go/no-go decision making as well as surrogate markers for disease severity or progression. Furthermore, CSF biomarkers can be used as a tool to enrich patients for clinical trials with prospect of increasing statistical power and reducing costs in drug development. However, the standardization of technical aspects of analysis of these biomarkers is an essential prerequisite to the clinical uses. To accomplish this, global efforts are underway to standardize CSF biomarker measurements and a quality control program supported by the Alzheimer's Association. The current review summarizes therapeutic targets of developing drugs in AD pathophysiology, and provides the most recent advances in the clinical utility of CSF biomarkers and the integration of CSF biomarkers in current clinical trials.

• Journal of the Korean Society of Radiology
• /
• v.10 no.5
• /
• pp.307-312
• /
• 2016

Alzheimer's disease is the most common degenerative brain diseases that causes dementia. ${\beta}$-amyloid neuritic plaque density that accumulates in the brain is difficult to perform daily living, such as memory loss, language ability deterioration. It is used to estimate ${\beta}$-amyloid neuritic plaque density in adult patients with cognitive impairment who are being evaluated for Alzheimer's disease and other causes of cognitive impairment. Using the $^{18}F$-Florbetaben with high sensitivity and specificity for the ${\beta}$-amyloid neuritic plaque density to evaluate the usefulness for the early diagnosis of Alzheimer's disease. In $^{18}F$-FDG Brain imaging shows no specific findings. And it appeared on the MR-Brain imaging without atrophy of the hippocampus. However, the intake of ${\beta}$-amyloid neuritic plaque density in $^{18}F$-Florbetaben informs that it is the progress of Alzheimer's disease. Therefore, $^{18}F$-Florobetaben is very useful for early diagnosis of Alzheimer's disease.

• Biomedical Science Letters
• /
• v.21 no.1
• /
• pp.1-8
• /
• 2015

Alzheimer's disease is a common form of dementia occurring among the elderly population and can be identified by symptoms such as cognition impairments, memory loss and neuronal dysfunction. Alzheimer's disease was found to be caused by the deposition of $\beta$-amyloid plaques and neurofibrillary tangles. In addition, mutation in the APP (Amyloid precursor protein), Presenilin 1 (PSEN1) and Presenilin 2 (PSEN2) genes were also found to contribute to Alzheimer's disease. Since the potential conformational diagnosis of Alzheimer's disease requires histopathological tests on brain through autopsy, potential early diagnosis still remains challenging. In recent years, several researches have proposed the use of biomarkers for early diagnosis. In cerebrospinal fluid (CSF), $\beta$-amyloid(1-42), phosphorylated-tau and total tau were suggested to be effective biomarkers for Alzheimer's disease diagnosis. However, a single biomarker might not be sufficient for potential diagnosis of Alzheimer's disease. Thus, the use of RNA interference (RNAi) through microRNAs (miRNAs) has been proposed by several researchers for simultaneous analysis of several biomarkers using microarray technology. These miRNA based biomarkers can be analysed from both blood and CSF, but miRNAs from blood are advantageous over CSF as they are non-invasive and simple for collection. Moreover, the RNAi based therapeutics by siRNA (short interference RNA) or shRNA (short hairpin RNA) have also been proposed to be effective in the treatment of Alzheimer's disease. This review describes the promising application of RNAi technology in therapeutics and as a biomarker for both Alzheimer's disease diagnosis and treatment.