Publications by authors named "Sang-Joon Son"
Article Synopsis
- Recent advancements in Alzheimer's treatment now require verification of amyloid-β pathology using PET scans or cerebrospinal fluid, but blood tests could simplify this process.* -
- A study involving nearly 7,000 individuals identified that the plasma biomarker p-tau217 can reliably indicate amyloid-β pathology, especially in patients with probable Alzheimer’s dementia.* -
- The findings suggest that combining p-tau217 results with clinical assessments may allow for accurate diagnoses without the need for more invasive PET or CSF tests.*
Article Synopsis
- Mild cognitive impairment (MCI) is an early sign of dementia that requires tailored treatment based on its subtypes, namely Alzheimer's-related cognitive impairment (ADCI) and subcortical vascular cognitive impairment (SVCI).
- Recent advancements using plasma protein biomarkers and machine learning (ML) can enhance the diagnosis and management of MCI by revealing subtype characteristics, although many existing ML approaches fail to account for important protein-protein interactions (PPIs).
- The study introduces a new ML model called the eXplainable Graph Propagational Network (XGPN), which better captures global interactions between proteins, leading to improved classification of MCI subtypes with explainable results.
Longitudinal accelerated brain age in mild cognitive impairment and Alzheimer's disease.
Front Aging Neurosci
October 2024
Introduction: Brain age is a machine learning-derived estimate that captures lower brain volume. Previous studies have found that brain age is significantly higher in mild cognitive impairment and Alzheimer's disease (AD) compared to healthy controls. Few studies have investigated changes in brain age longitudinally in MCI and AD.
View Article and Find Full Text PDFArticle Synopsis
- The study investigates the relationship between white matter hyperintensities (WMH) on brain MRIs and cognitive decline, focusing on how these factors may differ between sexes.
- Researchers analyzed 713 participants aged 49-89, assessing the effects of modifiable risk factors for WMH and examining their impact on long-term dementia outcomes.
- Findings suggest that age and type 2 diabetes significantly influence WMH volume, with stronger correlations identified in females, and that WMH burden is linked to worse dementia outcomes over time specifically in females.
Article Synopsis
- The study examined amyloid beta (Aβ) positivity and cognitive decline among Koreans and non-Hispanic Whites (NHWs), involving over 5,000 Koreans and nearly 1,000 NHWs.
- It was found that cognitively unimpaired (CU) Koreans had a lower prevalence of Aβ positivity compared to their NHW counterparts, with an adjusted odds ratio of 0.60.
- Additionally, Aβ-positive Koreans experienced a faster cognitive decline than Aβ-positive NHWs during both CU and mild cognitive impairment stages.
Article Synopsis
- - This study investigated the link between delirium and dementia in a large group of hospitalized patients over 60 years old, using data from over 11 million electronic health records in South Korea.
- - After matching groups of patients with and without delirium, the results showed that those with delirium had a significantly higher risk of developing various forms of dementia, with hazard ratios indicating increased risks for Alzheimer's and vascular dementia.
- - The findings emphasize the critical need for early detection and treatment of delirium to potentially prevent dementia, suggesting further research is necessary to understand the relationship between the two conditions.
Article Synopsis
- Plasma protein biomarkers are promising for diagnosing dementia subtypes due to their low variability, cost-effectiveness, and minimally invasive nature; however, existing machine learning approaches often overlook the important interactions between these proteins.
- The study introduces a new machine learning model called the graph propagational network (GPN), which effectively captures global interactions between proteins by analyzing their effects on a protein-protein interaction (PPI) network.
- Experimental results demonstrate that the GPN significantly improves diagnosis accuracy, outperforming previous methods by an average of 10.4% by better differentiating between dementia subtypes.
Article Synopsis
- * The research analyzed MRI and amyloid PET scans from 454 participants, finding that a combined model showed improved accuracy in classifying cognitive impairment, particularly in those with Alzheimer's disease.
- * Results indicate that white matter inter-subject variability (WM-ISV) is linked to both cognitive decline and specific blood biomarkers, supporting the idea that white matter analysis could enhance clinical decision-making regarding cognitive health.
Article Synopsis
- The study investigates sex-specific risk factors for white matter hyperintensities (WMH), linked to cerebral small vessel disease (CSVD), and their impact on cognitive decline in older adults.
- Using MRI data from 713 participants (241 males and 472 females), it analyzes how factors like age and type 2 diabetes relate to WMH volume in both sexes.
- Results indicate that females had a stronger correlation between age and WMH volume, with type 2 diabetes affecting only females, and WMH burden negatively impacted longitudinal dementia outcomes specifically in females.
Article Synopsis
- Alzheimer's disease (AD) is a major cause of dementia, affecting 60-70% of dementia patients, with mild cognitive impairment (MCI) serving as a precursor stage where about 10-15% of individuals transition to AD each year.
- This study analyzed data from 196 subjects to identify the best combination of imaging features and machine learning models to predict the conversion from MCI to AD over a four-year follow-up, finding that 24% of patients progressed to AD.
- The Gradient Boosting Machine (GBM) model proved to be the most reliable, demonstrating that omitting certain imaging features can enhance prediction accuracy, thereby aiding clinicians in early diagnosis and treatment planning for MCI patients.
Article Synopsis
- * Data from over 9,000 individuals aged 65 and older was analyzed, revealing that employment generally reduces depressive symptoms, with those involved in GSEP jobs experiencing even greater reductions.
- * Findings suggest that lower-income seniors in GSEP roles report significantly less depression and dissatisfaction with life compared to their counterparts in non-GSEP jobs, highlighting the program's value in shaping effective health policies and interventions.
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.
View Article and Find Full Text PDFBackground: 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.
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.
View Article and Find Full Text PDFBackground: The menopause transition is a vulnerable period that can be associated with changes in mood and cognition. The present study aimed to investigate whether a symptomatic menopausal transition increases the risks of depression, anxiety, and sleep disorders.
Methods: This population-based, retrospective cohort study analysed data from five electronic health record databases in South Korea.
Article Synopsis
- The study examines how the frequency of contact with adult children influences late-life depression among older adults, highlighting increased risks associated with infrequent interactions, particularly post-pandemic.
- An analysis of 7,573 older adults revealed that both face-to-face and non-face-to-face interactions are crucial, with infrequent contact leading to a higher likelihood of depressive symptoms.
- Various factors, such as age, income, and physical health, were found to influence the relationship between contact frequency and depression, suggesting that maintaining connections can be vital for mental well-being in later life.
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.
View Article and Find Full Text PDFArticle Synopsis
- The project is a partnership between the IHCC and DAC aimed at creating a genomic risk assessment tool for Alzheimer's disease that incorporates data from diverse ethnic backgrounds.
- The GIRA model combines genetic factors, like polygenic risk scores and specific gene haplotypes, with non-genetic data such as age and sex.
- Early findings show the GIRA model can effectively identify individuals at higher risk for Alzheimer's, with implications for future clinical use and research.
Article Synopsis
- Several programs exist for measuring amyloid deposition in the brain through PET imaging, with Heuron being a less examined but clinically approved software.
- This study analyzed PET images from 408 patients, comparing the amyloid quantification results from Heuron and PMOD, finding that Heuron generally reported higher standardized uptake value ratios (SUVRs) across most areas.
- Despite these differences, the two methods showed interchangeable results for clinical assessment of amyloid deposits, indicating comparable effectiveness in measuring amyloid levels.
Virtual reality-based monitoring test for MCI: A multicenter feasibility study.
Front Psychiatry
January 2023
Objectives: As the significance of the early diagnosis of mild cognitive impairment (MCI) has emerged, it is necessary to develop corresponding screening tools with high ecological validity and feasible biomarkers. Virtual reality (VR)-based cognitive assessment program, which is close to the daily life of the older adults, can be suitable screening tools for MCI with ecological validity and accessibility. Meanwhile, dehydroepiandrosterone (DHEA) has been observed at a low concentration in the older adults with dementia or cognitive decline, indicating its potential as a biomarker of MCI.
View Article and Find Full Text PDFBackground: Predicting the course of depression is necessary for personalized treatment. Impaired glucose metabolism (IGM) was introduced as a promising depression biomarker, but no consensus was made. This study aimed to predict IGM at the time of depression diagnosis and examine the relationship between long-term prognosis and predicted results.
View Article and Find Full Text PDFArticle Synopsis
- - The study explores how effective polygenic risk scores (PRSs) for Alzheimer's disease (AD)—which compile genetic information from European ancestry—are when applied to a Korean population of 1,634 individuals, including both AD patients and cognitively healthy controls.
- - The findings indicate that a higher PRS correlates with an increased risk of AD dementia, as well as other related conditions such as amnestic mild cognitive impairment (aMCI) and earlier onset of symptoms, regardless of APOE ɛ4 genetic status.
- - This research suggests the potential for PRS to be utilized across diverse populations, thus highlighting the need for more inclusive genetic studies beyond European ancestry to better assess genetic risks for conditions like AD in different ethnic groups
Relationships of Physical Activity, Depression, and Sleep with Cognitive Function in Community-Dwelling Older Adults.
Int J Environ Res Public Health
November 2022
Article Synopsis
- This study analyzed how physical activity, depression, and sleep are interconnected and their combined impact on cognitive function in older adults living in the community.
- Researchers assessed 864 participants using various questionnaires to measure these factors and also collected demographic data.
- The findings showed that physical activity positively affects cognitive function both directly and indirectly through its relationship with depression, with sleep playing a significant role in these connections, and the effects vary with age.