Objective: This study aims to validate the Korean version of Geriatric Suicide Ideation Scale-Screen (K-GSIS-Screen) and evaluate its clinical utility for screening suicidal ideation and risk among older adults across clinical and community settings. Methods: GSIS-Screen was translated into Korean and administered to 50 community-residing older adults and 49 elderly patients attending a depression clinic in the psychiatric department of a hospital. Reliability and validity were assessed by Cron-bach’s α and exploratory factor analysis. Then, clinical utility was further examined through receiver operating characteristic(ROC) curve analysis. Results: Exploratory factor analysis confirmed a single-factor structure. Overall findings demonstrated moderate to strong in-ternal consistency, convergent validity, and discriminant validity across community and clinical settings. Additionally, K-GSISScreen differentiated between older adults with and without suicidal ideation, with those in the former group scoring higher.ROC analysis confirmed an area under curve of 0.81. Conclusion The K-GSIS-Screen appears to be a useful primary screening tool for detecting suicidal ideation among older adults. It has the potential to facilitate rapid identification of suicidal ideation in clinical and community settings, thereby sup-porting early and appropriate interventions.

Objective: This study aimed to develop a machine learning model to predict cognitive decline in community-dwelling older adults. By integrating multimodal data, including demographic, psychosocial, and neuroimaging information, we sought to en-hance early detection of cognitive decline. Methods: Data were obtained from 159 participants in the Biobank Innovations for Chronic Cerebrovascular Disease with Alzheimer’s Disease Study. Participants underwent clinical assessments, neuropsychological testing, and magnetic resonance im-aging scans. Cognitive decline was defined as an increase in the Clinical Dementia Rating-Sum of Boxes of greater than 2.05 points per year at follow-up. Models were developed using the logistic classification, combining demographic, psychosocial as-sessments, and neuroimaging data. Model performance was evaluated using area under the curve (AUC), accuracy, and F1 score, while Shapley additive explanation values were used to assess feature importance. Results: The model that incorporated all data types achieved the highest performance, with an AUC of 0.834. The top predictor of cognitive decline was years of education, underscoring the importance of non-invasive, easily accessible data for prediction. Conclusion This machine learning model demonstrates significant potential for early cognitive decline prediction, offering a scalable tool for improving dementia screening and timely intervention, especially in resource-limited settings.

Objective: This study aims to validate the Korean version of Geriatric Suicide Ideation Scale-Screen (K-GSIS-Screen) and evaluate its clinical utility for screening suicidal ideation and risk among older adults across clinical and community settings. Methods: GSIS-Screen was translated into Korean and administered to 50 community-residing older adults and 49 elderly patients attending a depression clinic in the psychiatric department of a hospital. Reliability and validity were assessed by Cron-bach’s α and exploratory factor analysis. Then, clinical utility was further examined through receiver operating characteristic(ROC) curve analysis. Results: Exploratory factor analysis confirmed a single-factor structure. Overall findings demonstrated moderate to strong in-ternal consistency, convergent validity, and discriminant validity across community and clinical settings. Additionally, K-GSISScreen differentiated between older adults with and without suicidal ideation, with those in the former group scoring higher.ROC analysis confirmed an area under curve of 0.81. Conclusion The K-GSIS-Screen appears to be a useful primary screening tool for detecting suicidal ideation among older adults. It has the potential to facilitate rapid identification of suicidal ideation in clinical and community settings, thereby sup-porting early and appropriate interventions.

Objective: This study aimed to develop a machine learning model to predict cognitive decline in community-dwelling older adults. By integrating multimodal data, including demographic, psychosocial, and neuroimaging information, we sought to en-hance early detection of cognitive decline. Methods: Data were obtained from 159 participants in the Biobank Innovations for Chronic Cerebrovascular Disease with Alzheimer’s Disease Study. Participants underwent clinical assessments, neuropsychological testing, and magnetic resonance im-aging scans. Cognitive decline was defined as an increase in the Clinical Dementia Rating-Sum of Boxes of greater than 2.05 points per year at follow-up. Models were developed using the logistic classification, combining demographic, psychosocial as-sessments, and neuroimaging data. Model performance was evaluated using area under the curve (AUC), accuracy, and F1 score, while Shapley additive explanation values were used to assess feature importance. Results: The model that incorporated all data types achieved the highest performance, with an AUC of 0.834. The top predictor of cognitive decline was years of education, underscoring the importance of non-invasive, easily accessible data for prediction. Conclusion This machine learning model demonstrates significant potential for early cognitive decline prediction, offering a scalable tool for improving dementia screening and timely intervention, especially in resource-limited settings.

Objective: This study aims to validate the Korean version of Geriatric Suicide Ideation Scale-Screen (K-GSIS-Screen) and evaluate its clinical utility for screening suicidal ideation and risk among older adults across clinical and community settings. Methods: GSIS-Screen was translated into Korean and administered to 50 community-residing older adults and 49 elderly patients attending a depression clinic in the psychiatric department of a hospital. Reliability and validity were assessed by Cron-bach’s α and exploratory factor analysis. Then, clinical utility was further examined through receiver operating characteristic(ROC) curve analysis. Results: Exploratory factor analysis confirmed a single-factor structure. Overall findings demonstrated moderate to strong in-ternal consistency, convergent validity, and discriminant validity across community and clinical settings. Additionally, K-GSISScreen differentiated between older adults with and without suicidal ideation, with those in the former group scoring higher.ROC analysis confirmed an area under curve of 0.81. Conclusion The K-GSIS-Screen appears to be a useful primary screening tool for detecting suicidal ideation among older adults. It has the potential to facilitate rapid identification of suicidal ideation in clinical and community settings, thereby sup-porting early and appropriate interventions.

Objective: This study aimed to develop a machine learning model to predict cognitive decline in community-dwelling older adults. By integrating multimodal data, including demographic, psychosocial, and neuroimaging information, we sought to en-hance early detection of cognitive decline. Methods: Data were obtained from 159 participants in the Biobank Innovations for Chronic Cerebrovascular Disease with Alzheimer’s Disease Study. Participants underwent clinical assessments, neuropsychological testing, and magnetic resonance im-aging scans. Cognitive decline was defined as an increase in the Clinical Dementia Rating-Sum of Boxes of greater than 2.05 points per year at follow-up. Models were developed using the logistic classification, combining demographic, psychosocial as-sessments, and neuroimaging data. Model performance was evaluated using area under the curve (AUC), accuracy, and F1 score, while Shapley additive explanation values were used to assess feature importance. Results: The model that incorporated all data types achieved the highest performance, with an AUC of 0.834. The top predictor of cognitive decline was years of education, underscoring the importance of non-invasive, easily accessible data for prediction. Conclusion This machine learning model demonstrates significant potential for early cognitive decline prediction, offering a scalable tool for improving dementia screening and timely intervention, especially in resource-limited settings.

Objective: This study aims to validate the Korean version of Geriatric Suicide Ideation Scale-Screen (K-GSIS-Screen) and evaluate its clinical utility for screening suicidal ideation and risk among older adults across clinical and community settings. Methods: GSIS-Screen was translated into Korean and administered to 50 community-residing older adults and 49 elderly patients attending a depression clinic in the psychiatric department of a hospital. Reliability and validity were assessed by Cron-bach’s α and exploratory factor analysis. Then, clinical utility was further examined through receiver operating characteristic(ROC) curve analysis. Results: Exploratory factor analysis confirmed a single-factor structure. Overall findings demonstrated moderate to strong in-ternal consistency, convergent validity, and discriminant validity across community and clinical settings. Additionally, K-GSISScreen differentiated between older adults with and without suicidal ideation, with those in the former group scoring higher.ROC analysis confirmed an area under curve of 0.81. Conclusion The K-GSIS-Screen appears to be a useful primary screening tool for detecting suicidal ideation among older adults. It has the potential to facilitate rapid identification of suicidal ideation in clinical and community settings, thereby sup-porting early and appropriate interventions.

Objective: This study aimed to develop a machine learning model to predict cognitive decline in community-dwelling older adults. By integrating multimodal data, including demographic, psychosocial, and neuroimaging information, we sought to en-hance early detection of cognitive decline. Methods: Data were obtained from 159 participants in the Biobank Innovations for Chronic Cerebrovascular Disease with Alzheimer’s Disease Study. Participants underwent clinical assessments, neuropsychological testing, and magnetic resonance im-aging scans. Cognitive decline was defined as an increase in the Clinical Dementia Rating-Sum of Boxes of greater than 2.05 points per year at follow-up. Models were developed using the logistic classification, combining demographic, psychosocial as-sessments, and neuroimaging data. Model performance was evaluated using area under the curve (AUC), accuracy, and F1 score, while Shapley additive explanation values were used to assess feature importance. Results: The model that incorporated all data types achieved the highest performance, with an AUC of 0.834. The top predictor of cognitive decline was years of education, underscoring the importance of non-invasive, easily accessible data for prediction. Conclusion This machine learning model demonstrates significant potential for early cognitive decline prediction, offering a scalable tool for improving dementia screening and timely intervention, especially in resource-limited settings.

Astrocyte occupies 20%-40% of all glial cells in human central nervous system (CNS) and is important regulator of CNS inflam-matory response. Astrocytes are responsible for controlling neuronal and synaptic homeostasis and playing a critical role in the maintenance of redox status. Reactive astrogliosis, astrocyte remodeling, clasmatodendrosis, and paralysis are related to Alzheimer’s disease dementia (AD). Various astrocyte biomarkers in AD have been applied. Regarding positron emission tomography imaging, radioisotopes such as [11C]-deuterium-L-deprenyl, [18F]-(S)-(2-methylpyrid-5-yl)-6-[(3-fluoro-2-hydroxy)propoxy]quinoline, [11C]-(2-(4,5-dihydro-1H-imidazol-2-yl)-1-methyl-1H-indole) have been proposed for surrogate markers of astrogliosis. There is also now a steadily growing interest in GFAP (glial fibrillary acidic protein) and S100 as cerebrospinal fluid and blood markers. In the fu-ture, early intervention related to reactive astrogliosis would make a clue for the early diagnosis and treatment of Alzheimer’s disease.

Objective: We developed the Indoor Cognitive Training combined with Physical Activity (ICT-PA) program, incorporating memory registration, navigation, and image recall through wearable sensors and Bluetooth Low Energy tags, aimed at enhancing cognitive function and physical activity in elderly individuals with mild cognitive impairment (MCI). Methods: Thirty-six elderly individuals over 60 years diagnosed with MCI participated in a 6-week ICT-PA program. The primary outcome measure was the Consortium to Establish a Registry for Alzheimer’s Disease Neuropsychological Assessment Battery Total Score 1 (CERAD-TS1), and the secondary outcome measures were the Mini-Mental State Examination (MMSE), Subjective Memory Complaints Questionnaire (SMCQ), and Korean version of the Geriatric Depression Scale (GDS-KR). Changes in scores before and after the program were analyzed using paired t-tests. Program satisfaction was evaluated using a 5-point Likert scale. Results: CERAD-TS1 scores significantly improved after ICT-PA training (pre 57.3±11.3; post 60.3±13.1; p=0.006), while MMSE, SMCQ and GDS-KR scores remained unchanged. Subgroup analysis showed significant CERAD-TS improvements in the compliance group (>360 minutes of ICT-PA use) (pre 58.5±11.7; post 62.7±12.9; p=0.002). The average program satisfaction score was 7.7±1.6 out of 10. Data are presented as mean±standard deviation. Conclusion The ICT-PA program effectively improved cognitive functions in MCI patients, with high satisfaction rates.