Identification of molecular subtypes of dementia by using blood-proteins interaction-aware graph propagational network.

Plasma protein biomarkers have been considered promising tools for diagnosing dementia subtypes due to their low variability, cost-effectiveness, and minimal invasiveness in diagnostic procedures. Machine learning (ML) methods have been applied to enhance accuracy of the biomarker discovery. However, previous ML-based studies often overlook interactions between proteins, which are crucial in complex disorders like dementia. While protein-protein interactions (PPIs) have been used in network models, these models often fail to fully capture the diverse properties of PPIs due to their local awareness. This drawback increases the chance of neglecting critical components and magnifying the impact of noisy interactions. In this study, we propose a novel graph-based ML model for dementia subtype diagnosis, the graph propagational network (GPN). By propagating the independent effect of plasma proteins on PPI network, the GPN extracts the globally interactive effects between proteins. Experimental results showed that the interactive effect between proteins yielded to further clarify the differences between dementia subtype groups and contributed to the performance improvement where the GPN outperformed existing methods by 10.4% on average.

Long-Term Impact of Delirium on the Risk of Dementia in Hospitalized Older Patients: A Real-World Multicenter Study.

BACKGROUND: The association between delirium and dementia has been suggested, but mostly in the postoperative setting. This study aims to explore this relationship in a broader inpatient population, leveraging extensive real-world data to provide a more generalized understanding. METHODS: In this retrospective cohort study, electronic health records of 11,970,475 hospitalized patients aged over 60 from nine institutions in South Korea were analyzed. Patients with and without delirium were identified, and propensity score matching (PSM) was used to create comparable groups. A 10-year longitudinal analysis was conducted using the Cox proportional hazards model, which calculated the hazard ratio (HR) and 95% confidence interval (CI). Additionally, a meta-analysis was performed, aggregating results from all nine medical institutions. Lastly, we conducted various subgroup and sensitivity analyses to demonstrate the consistency of our study results across diverse conditions. RESULTS: After 1:1 PSM, a total of 47,306 patients were matched in both the delirium and nondelirium groups. Both groups had a median age group of 75-79 years, with 43.1% being female. The delirium group showed a significantly higher risk of all dementia compared with the nondelirium group (HR: 2.70 [95% CI: 2.27-3.20]). The incidence risk for different types of dementia was also notably higher in the delirium group (all dementia or mild cognitive impairment, HR: 2.46 [95% CI: 2.10-2.88]; Alzheimer's disease, HR: 2.74 [95% CI: 2.40-3.13]; vascular dementia, HR: 2.55 [95% CI: 2.07-3.13]). This pattern was consistent across all subgroup and sensitivity analyses. CONCLUSIONS: Delirium significantly increases the risk of onset for all types of dementia. These findings highlight the importance of early detection of delirium and prompt intervention. Further research studies are warranted to investigate the mechanisms linking delirium and dementia.

Comparative estimation of the effects of antihypertensive medications on schizophrenia occurrence: a multinational observational cohort study.

BACKGROUND: The association between antihypertensive medication and schizophrenia has received increasing attention; however, evidence of the impact of antihypertensive medication on subsequent schizophrenia based on large-scale observational studies is limited. We aimed to compare the schizophrenia risk in large claims-based US and Korea cohort of patients with hypertension using angiotensin-converting enzyme (ACE) inhibitors versus those using angiotensin receptor blockers (ARBs) or thiazide diuretics. METHODS: Adults aged 18 years who were newly diagnosed with hypertension and received ACE inhibitors, ARBs, or thiazide diuretics as first-line antihypertensive medications were included. The study population was sub-grouped based on age (> 45 years). The comparison groups were matched using a large-scale propensity score (PS)-matching algorithm. The primary endpoint was incidence of schizophrenia. RESULTS: 5,907,522; 2,923,423; and 1,971,549 patients used ACE inhibitors, ARBs, and thiazide diuretics, respectively. After PS matching, the risk of schizophrenia was not significantly different among the groups (ACE inhibitor vs. ARB: summary hazard ratio [HR] 1.15 [95% confidence interval, CI, 0.99-1.33]; ACE inhibitor vs. thiazide diuretics: summary HR 0.91 [95% CI, 0.78-1.07]). In the older subgroup, there was no significant difference between ACE inhibitors and thiazide diuretics (summary HR, 0.91 [95% CI, 0.71-1.16]). The risk for schizophrenia was significantly higher in the ACE inhibitor group than in the ARB group (summary HR, 1.23 [95% CI, 1.05-1.43]). CONCLUSIONS: The risk of schizophrenia was not significantly different between the ACE inhibitor vs. ARB and ACE inhibitor vs. thiazide diuretic groups. Further investigations are needed to determine the risk of schizophrenia associated with antihypertensive drugs, especially in people aged > 45 years.

Assessing cognitive impairment and disability in older adults through the lens of whole brain white matter patterns.

INTRODUCTION: This study aimed to explore the potential of whole brain white matter patterns as novel neuroimaging biomarkers for assessing cognitive impairment and disability in older adults. METHODS: We conducted an in-depth analysis of magnetic resonance imaging (MRI) and amyloid positron emission tomography (PET) scans in 454 participants, focusing on white matter patterns and white matter inter-subject variability (WM-ISV). RESULTS: The white matter pattern ensemble model, combining MRI and amyloid PET, demonstrated a significantly higher classification performance for cognitive impairment and disability. Participants with Alzheimer's disease (AD) exhibited higher WM-ISV than participants with subjective cognitive decline, mild cognitive impairment, and vascular dementia. Furthermore, WM-ISV correlated significantly with blood-based biomarkers (such as glial fibrillary acidic protein and phosphorylated tau-217 [p-tau217]), and cognitive function and disability scores. DISCUSSION: Our results suggest that white matter pattern analysis has significant potential as an adjunct neuroimaging biomarker for clinical decision-making and determining cognitive impairment and disability. HIGHLIGHTS: The ensemble model combined both magnetic resonance imaging (MRI) and amyloid positron emission tomography (PET) and demonstrated a significantly higher classification performance for cognitive impairment and disability. Alzheimer's disease (AD) revealed a notably higher heterogeneity compared to that in subjective cognitive decline, mild cognitive impairment, or vascular dementia. White matter inter-subject variability (WM-ISV) was significantly correlated with blood-based biomarkers (glial fibrillary acidic protein and phosphorylated tau-217 [p-tau217]) and with the polygenic risk score for AD. White matter pattern analysis has significant potential as an adjunct neuroimaging biomarker for clinical decision-making processes and determining cognitive impairment and disability.

Independent replication of advanced brain age in mild cognitive impairment and dementia: detection of future cognitive dysfunction.

We previously developed a novel machine-learning-based brain age model that was sensitive to amyloid. We aimed to independently validate it and to demonstrate its utility using independent clinical data. We recruited 650 participants from South Korean memory clinics to undergo magnetic resonance imaging and clinical assessments. We employed a pretrained brain age model that used data from an independent set of largely Caucasian individuals (n = 757) who had no or relatively low levels of amyloid as confirmed by positron emission tomography (PET). We investigated the association between brain age residual and cognitive decline. We found that our pretrained brain age model was able to reliably estimate brain age (mean absolute error = 5.68 years, r(650) = 0.47, age range = 49-89 year) in the sample with 71 participants with subjective cognitive decline (SCD), 375 with mild cognitive impairment (MCI), and 204 with dementia. Greater brain age was associated with greater amyloid and worse cognitive function [Odds Ratio, (95% Confidence Interval {CI}): 1.28 (1.06-1.55), p = 0.030 for amyloid PET positivity; 2.52 (1.76-3.61), p < 0.001 for dementia]. Baseline brain age residual was predictive of future cognitive worsening even after adjusting for apolipoprotein E e4 and amyloid status [Hazard Ratio, (95% CI): 1.94 (1.33-2.81), p = 0.001 for total 336 follow-up sample; 2.31 (1.44-3.71), p = 0.001 for 284 subsample with baseline Clinical Dementia Rating ≤ 0.5; 2.40 (1.43-4.03), p = 0.001 for 240 subsample with baseline SCD or MCI]. In independent data set, these results replicate our previous findings using this model, which was able to delineate significant differences in brain age according to the diagnostic stages of dementia as well as amyloid deposition status. Brain age models may offer benefits in discriminating and tracking cognitive impairment in older adults.

Privacy-Preserving Federated Model Predicting Bipolar Transition in Patients With Depression: Prediction Model Development Study.

BACKGROUND: Mood disorder has emerged as a serious concern for public health; in particular, bipolar disorder has a less favorable prognosis than depression. Although prompt recognition of depression conversion to bipolar disorder is needed, early prediction is challenging due to overlapping symptoms. Recently, there have been attempts to develop a prediction model by using federated learning. Federated learning in medical fields is a method for training multi-institutional machine learning models without patient-level data sharing. OBJECTIVE: This study aims to develop and validate a federated, differentially private multi-institutional bipolar transition prediction model. METHODS: This retrospective study enrolled patients diagnosed with the first depressive episode at 5 tertiary hospitals in South Korea. We developed models for predicting bipolar transition by using data from 17,631 patients in 4 institutions. Further, we used data from 4541 patients for external validation from 1 institution. We created standardized pipelines to extract large-scale clinical features from the 4 institutions without any code modification. Moreover, we performed feature selection in a federated environment for computational efficiency and applied differential privacy to gradient updates. Finally, we compared the federated and the 4 local models developed with each hospital's data on internal and external validation data sets. RESULTS: In the internal data set, 279 out of 17,631 patients showed bipolar disorder transition. In the external data set, 39 out of 4541 patients showed bipolar disorder transition. The average performance of the federated model in the internal test (area under the curve [AUC] 0.726) and external validation (AUC 0.719) data sets was higher than that of the other locally developed models (AUC 0.642-0.707 and AUC 0.642-0.699, respectively). In the federated model, classifications were driven by several predictors such as the Charlson index (low scores were associated with bipolar transition, which may be due to younger age), severe depression, anxiolytics, young age, and visiting months (the bipolar transition was associated with seasonality, especially during the spring and summer months). CONCLUSIONS: We developed and validated a differentially private federated model by using distributed multi-institutional psychiatric data with standardized pipelines in a real-world environment. The federated model performed better than models using local data only.

Trans-ethnic genomic informed risk assessment for Alzheimer's disease: An International Hundred K+ Cohorts Consortium study.

BACKGROUND: As a collaboration model between the International HundredK+ Cohorts Consortium (IHCC) and the Davos Alzheimer's Collaborative (DAC), our aim was to develop a trans-ethnic genomic informed risk assessment (GIRA) algorithm for Alzheimer's disease (AD). METHODS: The GIRA model was created to include polygenic risk score calculated from the AD genome-wide association study loci, the apolipoprotein E haplotypes, and non-genetic covariates including age, sex, and the first three principal components of population substructure. RESULTS: We validated the performance of the GIRA model in different populations. The proteomic study in the participant sites identified proteins related to female infertility and autoimmune thyroiditis and associated with the risk scores of AD. CONCLUSIONS: As the initial effort by the IHCC to leverage existing large-scale datasets in a collaborative setting with DAC, we developed a trans-ethnic GIRA for AD with the potential of identifying individuals at high risk of developing AD for future clinical applications.

Shared genetic effects of emotion and subcortical volumes in healthy adults.

Ample studies have reported a strong association between emotion and subcortical volumes; still, the underlying mechanism regarding this relation remains unclear. Using a twin design, the current study aimed to explore the intrinsic association between emotion and subcortical volumes by examining their phenotypic, genetic, and environmental correlations. We used a group dataset of 960 individuals from the Human Connectome Project (234 monozygotic twins, 145 dizygotic twins, 581 not twins, males = 454, age = 22-37 years). We found that both emotion and subcortical volumes were heritable. Of the 17 emotional traits, 13 were significantly phenotypically correlated with the volumes of multiple subcortical regions. There was no environmental correlation between emotion and subcortical volumes; however, we found a genetic overlap between overall emotional traits and caudate volume. Taken together, our results showed that emotion and subcortical volumes were heritable and closely related. Although the caudate has been often studied with execution of movement, given that the caudate volume is genetically associated with diverse emotional domains, such as negative affect, psychological well-being, and social relationships, it may suggest that the caudate volume might also be an important factor when studying the brain basis of emotion.

The effect of sex and physical frailty on incident disability after 2 years among community-dwelling older adults: KFACS study.

BACKGROUND: This study investigated the impact of physical frailty on the development of disabilities in mobility, activities of daily living (ADL), and instrumental activities of daily living (IADL) according to sex among community-dwelling Korean older adults. METHODS: We used data of 2,905 older adults aged 70-84 years from the Korean Frailty and Aging Cohort Study (KFACS) at baseline (2016-2017) and Wave 2 (2018-2019). Fried's physical frailty phenotype was used to identify frailty. RESULTS: After adjustment, frailty showed a higher impact for women than men on developing mobility disability (odds ratio [OR]=14.00, 95% confidence interval [CI]=4.8-40.78 vs. OR=9.89, 95% CI=4.28-22.86) and IADL disability after two years (OR=7.22, 95% CI=2.67-19.56 vs. OR=3.19, 95% CI=1.17-8.70). Pre-frailty led to mobility disability for women and men (OR=2.77, 95% CI=1.93-3.98 vs. OR=2.49, 95% CI=1.66-3.72, respectively), and IADL disability only for women (OR=3.01, 95% CI=1.28-7.09). Among the IADL components, both men and women who were prefrail or frail showed increased disability in 'using transportation'. Among men, pre-frailty was significantly associated with disability in "going out" and "shopping". In women, frailty was significantly associated with disability in "doing laundry," "performing household chores," "shopping," and "managing money". CONCLUSIONS: Physical frailty increased disability over 2 years for women more than men. Physical frailty increased disability in outdoor activity-related IADL components in men and household work-related IADL components in women. This study highlights the need for gender-specific policies and preventative programs for frailty, particularly restorative interventions that focus on women who are physically frail.

Dementia key gene identification with multi-layered SNP-gene-disease network.

MOTIVATION: Recently, various approaches for diagnosing and treating dementia have received significant attention, especially in identifying key genes that are crucial for dementia. If the mutations of such key genes could be tracked, it would be possible to predict the time of onset of dementia and significantly aid in developing drugs to treat dementia. However, gene finding involves tremendous cost, time and effort. To alleviate these problems, research on utilizing computational biology to decrease the search space of candidate genes is actively conducted.In this study, we propose a framework in which diseases, genes and single-nucleotide polymorphisms are represented by a layered network, and key genes are predicted by a machine learning algorithm. The algorithm utilizes a network-based semi-supervised learning model that can be applied to layered data structures. RESULTS: The proposed method was applied to a dataset extracted from public databases related to diseases and genes with data collected from 186 patients. A portion of key genes obtained using the proposed method was verified in silico through PubMed literature, and the remaining genes were left as possible candidate genes. AVAILABILITY AND IMPLEMENTATION: The code for the framework will be available at http://www.alphaminers.net/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Risk of Mortality in Elderly Coronavirus Disease 2019 Patients With Mental Health Disorders: A Nationwide Retrospective Study in South Korea.

OBJECTIVE: This study aimed to investigate the different clinical characteristics among elderly coronavirus disease 2019 (COVID-19) patients with and without mental disorders in South Korea and determine if these characteristics have an association with underlying mental disorders causing mortality. METHOD: A population-based comparative cohort study was conducted using the national claims database. Individuals aged ≥65 years with confirmed COVID-19 between January 1, 2020 and April 10, 2020 were assessed. The endpoints for evaluating mortality for all participants were death, 21 days after diagnosis, or April 10, 2020. The risk of mortality associated with mental disorders was estimated using Cox hazards regression. RESULTS: We identified 814 elderly COVID-19 patients (255 [31.3%] with mental disorder and 559 [68.7%] with nonmental disorder). Individuals with mental disorders were found more likely to be older, taking antithrombotic agents, and had diabetes, hypertension, chronic obstructive lung disease, and urinary tract infections than those without mental disorders. After propensity score stratification, our study included 781 patients in each group (236 [30.2%] with mental disorder and 545 [69.8%] with nonmental disorder). The mental disorder group showed higher mortality rates than the nonmental disorder group (12.7% [30/236] versus 6.8% [37/545]). However, compared to patients without mental disorders, the hazard ratio (HR) for mortality in elderly COVID-19 patients with mental disorders was not statistically significant (HR: 1.57, 95%CI: 0.95-2.56). CONCLUSION: Although the association between mental disorders in elderly individuals and mortality in COVID-19 is unclear, this study suggests that elderly patients with comorbid conditions and those taking psychiatric medications might be at a higher risk of COVID-19.

A Randomized Comparison of Medication and Cognitive Behavioral Therapy for Treating Depression in Low-Income Young Minority Women.

BACKGROUND Longitudinal data arise frequently in biomedical science and health studies where each subject is repeatedly measured over time. We compared the effectiveness of medication and cognitive behavioral therapy on depression in predominantly low-income young minority women. MATERIAL AND METHODS The treatment effects on patients with low-level depression may differ from the treatment effects on patients with high-level depression. We used a quantile regression model for longitudinal data analysis to determine which treatment is most beneficial for patients at different stress levels over time. RESULTS The results confirm that both treatments are effective in reducing the depression score over time, regardless of the depression level. CONCLUSIONS Compared to cognitive behavioral therapy, treatment with medication more often effective, although the size of the effect differs. Thus, no matter how severe a patient's depression symptoms are, antidepressant medication is effective in decreasing depression symptoms.

Large intracranial volume accelerates conversion to dementia in males and APOE4 non-carriers with mild cognitive impairment.

BACKGROUND: It is unclear how brain reserve interacts with gender and apolipoprotein E4 (APOE4) genotype, and how this influences the progression of Alzheimer's disease (AD). The association between intracranial volume (ICV) and progression to AD in subjects with mild cognitive impairment (MCI), and differences according to gender and APOE4 genotype, was investigated. METHODS: Data from subjects initially diagnosed with MCI and at least two visits were downloaded from the ADNI database. Those who progressed to AD were defined as converters. The longitudinal influence of ICV was determined by survival analysis. The time of conversion from MCI to AD was set as a fiducial point, as all converters would be at a similar disease stage then, and longitudinal trajectories of brain atrophy and cognitive decline around that point were compared using linear mixed models. RESULTS: Large ICV increased the risk of conversion to AD in males (HR: 4.24, 95% confidence interval (CI): 1.17-15.40) and APOE4 non-carriers (HR: 10.00, 95% CI: 1.34-74.53), but not in females or APOE4 carriers. Cognitive decline and brain atrophy progressed at a faster rate in males with large ICV than in those with small ICV during the two years before and after the time of conversion. CONCLUSIONS: Large ICV increased the risk of conversion to AD in males and APOE4 non-carriers with MCI. This may be due to its influence on disease trajectory, which shortens the duration of the MCI stage. A longitudinal model of progression trajectory is proposed.

Association of alcohol drinking with verbal and visuospatial memory impairment in older adults: Clinical Research Center for Dementia of South Korea (CREDOS) study.

BACKGROUND: The study's aim was to examine the association of alcohol consumption with verbal and visuospatial memory impairment in older people. METHODS: Participants were 1,572, aged ≥60 years, in the hospital-based registry of the Clinical Research Center for Dementia of South Korea (CREDOS). Moderate drinking was defined as no more than seven drinks per week and three drinks per day. Memory impairment was defined as performance with more than 1 standard deviation below the mean value on the Seoul Verbal Learning Test and Rey Complex Figure Test. RESULTS: Those who consumed alcohol moderately, compared with abstainers, had a lower odds of verbal memory impairment (Odds Ratio [OR] = 0.64; 95% Confidence Interval [CI]: 0.46-0.87), adjusting for covariates. Visuospatial memory, however, was not significantly associated with alcohol consumption. CONCLUSIONS: Moderate alcohol drinking is associated with a reduced likelihood of verbal memory impairment among older people attending memory clinics.

Effects of a multidomain lifestyle modification on cognitive function in older adults: an eighteen-month community-based cluster randomized controlled trial.

BACKGROUND: A healthy lifestyle may protect against cognitive decline. We examined outcomes in elderly individuals after 18 months of a five-group intervention program consisting of various modalities to prevent cognitive decline. METHODS: We conducted a cluster randomized controlled trial assessing 460 community-dwelling individuals aged 60 years and older in a geriatric community mental health center in Suwon, Republic of Korea, between 2008 and 2010. We developed an intervention program based on the principles of contingency management, which could be delivered by ordinary primary health workers. Group A (n = 81) received standard care services. Group B (n = 80) received bimonthly (once every 2 months) telephonic care management. Group C (n = 111) received monthly telephonic care management and educational materials similar to those in group B. Group D (n = 93) received bimonthly health worker-initiated visits and counseling. Group E (n = 94) received bimonthly health worker-initiated visits, counseling, and rewards for adherence to the program. RESULTS: The primary outcome was the change in Mini-Mental State Examination (MMSE) scores from baseline to the final follow-up visit at 18 months. Group E showed superior cognitive function to group A (adjusted coefficient ß = 0.99, p = 0.044), with participation in cognitive activities being the most important determining factor among several health behaviors (adjusted coefficient ß = 1.04, p < 0.01). CONCLUSIONS: Engaging in cognitive activities, in combination with positive health behaviors, may be most beneficial in preserving cognitive abilities in community-dwelling older adults.

Explainable multimodal prediction of treatment-resistance in patients with depression leveraging brain morphometry and natural language processing.

Although 20 % of patients with depression receiving treatment do not achieve remission, predicting treatment-resistant depression (TRD) remains challenging. In this study, we aimed to develop an explainable multimodal prediction model for TRD using structured electronic medical record data, brain morphometry, and natural language processing. In total, 247 patients with a new depressive episode were included. TRD-predictive models were developed based on the combination of following parameters: selected tabular dataset features, independent components-map weightings from brain T1-weighted magnetic resonance imaging (MRI), and topic probabilities from clinical notes. All models applied the extreme gradient boosting (XGBoost) algorithm via five-fold cross-validation. The model using all data sources showed the highest area under the receiver operating characteristic of 0.794, followed by models that used combined brain MRI and structured data, brain MRI and clinical notes, clinical notes and structured data, brain MRI only, structured data only, and clinical notes only (0.770, 0.762, 0.728, 0.703, 0.684, and 0.569, respectively). Classifications of TRD were driven by several predictors, such as previous exposure to antidepressants and antihypertensive medications, sensorimotor network, default mode network, and somatic symptoms. Our findings suggest that a combination of clinical data with neuroimaging and natural language processing variables improves the prediction of TRD.

Neuroimaging and natural language processing-based classification of suicidal thoughts in major depressive disorder.

Suicide is a growing public health problem around the world. The most important risk factor for suicide is underlying psychiatric illness, especially depression. Detailed classification of suicide in patients with depression can greatly enhance personalized suicide control efforts. This study used unstructured psychiatric charts and brain magnetic resonance imaging (MRI) records from a psychiatric outpatient clinic to develop a machine learning-based suicidal thought classification model. The study included 152 patients with new depressive episodes for development and 58 patients from a geographically different hospital for validation. We developed an eXtreme Gradient Boosting (XGBoost)-based classification models according to the combined types of data: independent components-map weightings from brain T1-weighted MRI and topic probabilities from clinical notes. Specifically, we used 5 psychiatric symptom topics and 5 brain networks for models. Anxiety and somatic symptoms topics were significantly more common in the suicidal group, and there were group differences in the default mode and cortical midline networks. The clinical symptoms plus structural brain patterns model had the highest area under the receiver operating characteristic curve (0.794) versus the clinical notes only and brain MRI only models (0.748 and 0.738, respectively). The results were consistent across performance metrics and external validation. Our findings suggest that focusing on personalized neuroimaging and natural language processing variables improves evaluation of suicidal thoughts.

Association of Geriatric Depressive Symptoms and Government-Initiated Senior Employment Program: A Population-Based Study.

OBJECTIVE: The impact of the government-initiated senior employment program (GSEP) on geriatric depressive symptoms is underexplored. Unearthing this connection could facilitate the planning of future senior employment programs and geriatric depression interventions. In the present study, we aimed to elucidate the possible association between geriatric depressive symptoms and GSEP in older adults. METHODS: This study employed data from 9,287 participants aged 65 or older, obtained from the 2020 Living Profiles of Older People Survey. We measured depressive symptoms using the Korean version of the 15-item Geriatric Depression Scale. The principal exposure of interest was employment status and GSEP involvement. Data analysis involved multiple linear regression. RESULTS: Employment, independent of income level, showed association with decreased depressive symptoms compared to unemployment (p<0.001). After adjustments for confounding variables, participation in GSEP jobs showed more significant reduction in depressive symptoms than non-GSEP jobs (ß=-0.968, 95% confidence interval [CI]=-1.197 to -0.739, p<0.001 for GSEP jobs, ß=-0.541, 95% CI=-0.681 to -0.401, p<0.001 for non-GSEP jobs). Notably, the lower income tertile in GSEP jobs showed a substantial reduction in depressive symptoms compared to all income tertiles in non-GSEP jobs. CONCLUSION: The lower-income GSEP group experienced lower depressive symptoms and life dissatisfaction compared to non-GSEP groups regardless of income. These findings may provide essential insights for the implementation of government policies and community-based interventions.

Higher HbA1c Is Associated With Greater 2-Year Progression of White Matter Hyperintensities.

White matter hyperintensity (WMH) lesions on brain MRI images are surrogate markers of cerebral small vessel disease. Longitudinal studies examining the association between diabetes and WMH progression have yielded mixed results. Thus, in this study, we investigated the association between HbA1c, a biomarker for the presence and severity of hyperglycemia, and longitudinal WMH change after adjusting for known risk factors for WMH progression. We recruited 64 participants from South Korean memory clinics to undergo brain MRI at the baseline and a 2-year follow-up. We found the following. First, higher HbA1c was associated with greater global WMH volume (WMHV) changes after adjusting for known risk factors (ß = 7.7 × 10-4; P = 0.025). Second, the association between baseline WMHV and WMHV progression was only significant at diabetic levels of HbA1c (P < 0.05, when HbA1c >6.51%), and non-apolipoprotein E (APOE) ε4 carriers had a stronger association between HbA1c and WMHV progression (ß = -2.59 × 10-3; P = 0.004). Third, associations of WMHV progression with HbA1c were particularly apparent for deep WMHV change (ß = 7.17 × 10-4; P < 0.01) compared with periventricular WMHV change and, for frontal (ß = 5.00 × 10-4; P < 0.001) and parietal (ß = 1.53 × 10-4; P < 0.05) lobes, WMHV change compared with occipital and temporal WMHV change. In conclusion, higher HbA1c levels were associated with greater 2-year WMHV progression, especially in non-APOE ε4 participants or those with diabetic levels of HbA1c. These findings demonstrate that diabetes may potentially exacerbate cerebrovascular and white matter disease.

A multimodal machine learning model for predicting dementia conversion in Alzheimer's disease.

Alzheimer's disease (AD) accounts for 60-70% of the population with dementia. Mild cognitive impairment (MCI) is a diagnostic entity defined as an intermediate stage between subjective cognitive decline and dementia, and about 10-15% of people annually convert to AD. We aimed to investigate the most robust model and modality combination by combining multi-modality image features based on demographic characteristics in six machine learning models. A total of 196 subjects were enrolled from four hospitals and the Alzheimer's Disease Neuroimaging Initiative dataset. During the four-year follow-up period, 47 (24%) patients progressed from MCI to AD. Volumes of the regions of interest, white matter hyperintensity, and regional Standardized Uptake Value Ratio (SUVR) were analyzed using T1, T2-weighted-Fluid-Attenuated Inversion Recovery (T2-FLAIR) MRIs, and amyloid PET (αPET), along with automatically provided hippocampal occupancy scores (HOC) and Fazekas scales. As a result of testing the robustness of the model, the GBM model was the most stable, and in modality combination, model performance was further improved in the absence of T2-FLAIR image features. Our study predicts the probability of AD conversion in MCI patients, which is expected to be useful information for clinician's early diagnosis and treatment plan design.