Dataset Information

Machine Learning-Based Identification of Diagnostic Biomarkers for Korean Male Sarcopenia Through Integrative DNA Methylation and Methylation Risk Score: From the Korean Genomic Epidemiology Study (KoGES).

ABSTRACT:

Background

Sarcopenia, characterized by a progressive decline in muscle mass, strength, and function, is primarily attributable to aging. DNA methylation, influenced by both genetic predispositions and environmental exposures, plays a significant role in sarcopenia occurrence. This study employed machine learning (ML) methods to identify differentially methylated probes (DMPs) capable of diagnosing sarcopenia in middle-aged individuals. We also investigated the relationship between muscle strength, muscle mass, age, and sarcopenia risk as reflected in methylation profiles.

Methods

Data from 509 male participants in the urban cohort of the Korean Genome Epidemiology Study_Health Examinee study were categorized into quartile groups based on the sarcopenia criteria for appendicular skeletal muscle index (ASMI) and handgrip strength (HG). To identify diagnostic biomarkers for sarcopenia, we used recursive feature elimination with cross validation (RFECV), to pinpoint DMPs significantly associated with sarcopenia. An ensemble model, leveraging majority voting, was utilized for evaluation. Furthermore, a methylation risk score (MRS) was calculated, and its correlation with muscle strength, function, and age was assessed using likelihood ratio analysis and multinomial logistic regression.

Results

Participants were classified into two groups based on quartile thresholds: sarcopenia (n = 37) with ASMI and HG in the lowest quartile, and normal ranges (n = 48) in the highest. In total, 238 DMPs were identified and eight probes were selected using RFECV. These DMPs were used to build an ensemble model with robust diagnostic capabilities for sarcopenia, as evidenced by an area under the receiver operating characteristic curve of 0.94. Based on eight probes, the MRS was calculated and then validated by analyzing age, HG, and ASMI among the control group (n = 424). Age was positively correlated with high MRS (coefficient, 1.2494; odds ratio [OR], 3.4882), whereas ASMI and HG were negatively correlated with high MRS (ASMI coefficient, -0.4275; OR, 0.6521; HG coefficient, -0.3116; OR, 0.7323).

Conclusion

Overall, this study identified key epigenetic markers of sarcopenia in Korean males and developed a ML model with high diagnostic accuracy for sarcopenia. The MRS also revealed significant correlations between these markers and age, HG, and ASMI. These findings suggest that both diagnostic models and the MRS can play an important role in managing sarcopenia in middle-aged populations.

SUBMITTER: Ahn S

PROVIDER: S-EPMC11231442 | biostudies-literature | 2024 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine Learning-Based Identification of Diagnostic Biomarkers for Korean Male Sarcopenia Through Integrative DNA Methylation and Methylation Risk Score: From the Korean Genomic Epidemiology Study (KoGES).

Ahn Seohyun S Sung Yunho Y Song Wook W

Journal of Korean medical science 20240708 26

<h4>Background</h4>Sarcopenia, characterized by a progressive decline in muscle mass, strength, and function, is primarily attributable to aging. DNA methylation, influenced by both genetic predispositions and environmental exposures, plays a significant role in sarcopenia occurrence. This study employed machine learning (ML) methods to identify differentially methylated probes (DMPs) capable of diagnosing sarcopenia in middle-aged individuals. We also investigated the relationship between muscl ...[more]

PMID: 38978487

Similar Datasets

Project description:BackgroundThe association between dietary cholesterol and metabolic diseases remains controversial. However, the majority of studies focus on egg intake, and there is a limitation in the availability of prospective cohort studies. Our study examined the association between dietary cholesterol and the incidence risk of metabolic syndrome (MetS) in middle aged adults using large prospective cohort study in Republic of Korea.MethodsThe Health Examinees cohort from the Korean Genome and Epidemiology Study was used from baseline to follow-up. Dietary cholesterol intake was assessed by the validated semi-quantitative food frequency questionnaire. Participants were classified as quintile groups according to adjusted dietary cholesterol for total energy intake. MetS was defined as more than 3 of the 5 components of MetS. Hazard ratio (HR) and 95% confidence intervals (CI) for MetS were evaluated by multivariable cox regression analyses.ResultsOf the total 40,578 participants, metabolic syndrome developed in 4,172 (10.28%) individuals during an average follow-up period of approximately 4.76 years. Dietary cholesterol did not exhibit a significant association with the risk of MetS after adjusting for potential confounding factors, but a trend was observed indicating an increased risk with higher intake (p for trend = 0.044). Among the components of MetS, the incidence risk of high waist circumference (HR: 1.164, 95% CI: 1.049-1.290), high blood pressure (HR: 1.188, 95% CI: 1.075-1.313), high serum triglyceride (HR: 1.132, 95% CI: 1.044-1.227) and high fasting blood glucose (HR: 1.217, 95% CI: 1.132-1.308) in the group that consumed the highest dietary cholesterol intake was increased compared with the group that consumed the lowest dietary cholesterol intake. Dose-response relationship suggested a positive linear association between dietary cholesterol intake and the risk of high waist circumference (p-linearity = 0.004), blood pressure (p-linearity = 0.012), and triglycerides (p-linearity = 0.005).ConclusionThis study suggests a positive association between dietary cholesterol intake and the risk of MetS and its components (abdominal obesity, hypertension, hypertriglyceridemia, and hyperglycemia) in middle-aged Korean adults.

Project description:BackgroundAir pollution is a global public health concern and incidence rates of metabolic syndrome (MetS) are increasing. To evaluate the effect of long-term air pollution exposure, we examined the association between long-term exposure to ambient air pollution and the incidences of MetS among Korean adults.MethodsWe used data from the Korean Genome and Epidemiology Study's Cardiovascular Disease Association Study, a population-based cohort consisting of community-dwelling Korean adults between 2005 and 2011, who were followed up with until 2016 (n = 7,428). Air pollution exposure was estimated using the Congestion Mitigation and Air Quality model based on the participants' addresses. The participants had a physical examination at every visit during follow-up, and MetS was defined based on the National Institute of Health's National Cholesterol Education Program-Adult Treatment Panel III. We used Cox proportional hazard model to analyze the association between long-term air pollution exposure and incidences of MetS per interquartile range (IQR) increment of the annual concentration after adjusting for potential confounders using single and two-pollutant analysis.ResultsThe hazard ratios (HR) of MetS per IQR increment in PM2.5, SO2, NO2, and CO were 1.19 (95% CI: 1.12-1.27), 1.57 (95% CI: 1.47-1.68), 1.11 (95% CI: 1.03-1.20), and 1.63 (95% CI: 1.48-1.78), respectively. The incidences of MetS components, which are high blood pressure, elevated fasting glucose, abdominal obesity, high fasting triglyceride (TG), and low fasting high-density lipoprotein (HDL-C), were significantly associated with an IQR increment especially in SO2 and CO. In subgroup analysis, males had higher risk of MetS than females. The HR was the highest in the 60-69 year old age group for all pollutants.ConclusionIn the present study, we found that long-term ambient air pollution exposure increased the incidences of MetS and its components among Korean adults, especially in males and the elderly population.

Dataset Information

Machine Learning-Based Identification of Diagnostic Biomarkers for Korean Male Sarcopenia Through Integrative DNA Methylation and Methylation Risk Score: From the Korean Genomic Epidemiology Study (KoGES).

Background

Methods

Results

Conclusion

Publications

Machine Learning-Based Identification of Diagnostic Biomarkers for Korean Male Sarcopenia Through Integrative DNA Methylation and Methylation Risk Score: From the Korean Genomic Epidemiology Study (KoGES).

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets