Cataracts are a major cause of visual impairment worldwide, particularly among older adults, with an increasing prevalence due to population aging. Surgery is the primary treatment; however, preventive strategies are crucial for reducing the disease burden. This study aimed to investigate dietary and health-related factors associated with cataract occurrence and develop a predictive model using machine learning. Data were derived from the Korea National Health and Nutrition Examination Survey 2015–2017. The study included 190 women aged 60–79 years: 124 with cataracts and 66 controls. Analyzed variables included sociodemographic, behavioral, chronic disease, and dietary intake factors. After data preprocessing, 4 machine learning algorithms: support vector machine (SVM), random forest (RF), eXtreme gradient boosting, and multilayer perceptron were used. Model performance was evaluated using accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUROC) and precision-recall curves. Among the tested models, the SVM achieved the best performance under stratified 10-fold cross-validation, with 71% accuracy, 86% precision, 73% recall, 79% F1-score, 65% AUROC, and 81% AUPRC. According to our findings, the odds of having cataracts can be effectively predicted using dietary and health data without relying on specialized ophthalmic equipment. The proposed model demonstrates the potential of machine learning-based tools for early identification and prevention of cataracts. Future studies with larger and more diverse samples, as well as integrating additional data sources such as genomics and lifestyle factors, are warranted to refine predictive accuracy and enhance personalized nutrition-based interventions.
This study aimed to identify major dietary patterns among Korean adolescents, examine their changes over the past 16 years, and evaluate differences by sex. Data were analyzed from 7,679 adolescents aged 12–18 years who participated in the 2007–2022 Korea National Health and Nutrition Examination Survey and completed health, examination, and nutrition surveys. Dietary intake was assessed using a 24-hour recall, and cluster analysis was performed based on the energy contribution of 26 food groups. Associations between dietary patterns and nutrient intake were examined using survey-weighted linear regression. Three dietary patterns were identified: Bread, Meat, & Dairy (33.1%); Rice-based Diet (45.5%); and Convenient Foods (21.3%). Among boys, the Rice-based Diet group showed the highest prevalence of obesity and the largest proportion of low-income households, whereas the Bread, Meat, & Dairy group exhibited higher rates of supplement use and high-income status (all p < 0.05). Among girls, the Convenient Foods group tended to be older and was more likely to skip breakfast, consume alcohol, eat out daily, and perceive themselves as overweight (all p < 0.05). Over the 16-year period, adherence to the Bread, Meat, & Dairy pattern increased, whereas adherence to the Rice-based Diet pattern declined in both sexes (p < 0.01). These findings highlight a shift toward Westernized dietary patterns among Korean adolescents. Accordingly, nutrition policies and interventions should adopt tailored strategies that account for both sex and socioeconomic differences to promote healthier eating habits and support long-term adolescent health.
Chronic obstructive pulmonary disease (COPD) is a major respiratory disorder characterized by irreversible airflow limitation. The role of diet in the prevention and management of COPD is receiving increasing attention. This study aimed to examine the association between the composite intake of vegetables, fruits, meat, and fish and pulmonary function as well as COPD prevalence in a representative sample of Korean adults aged ≥ 40 years using data from the 7th Korea National Health and Nutrition Examination Survey. Higher vegetable intake was associated with significantly better pulmonary function parameters, including forced vital capacity (p < 0.001), forced vital capacity percent predicted (p = 0.050), forced expiratory volume (FEV) in 1 second (FEV1; p < 0.001), FEV1 percent predicted (p = 0.038), FEV in 6 seconds (p < 0.001), and peak expiratory flow (p < 0.001). Furthermore, individuals with a high combined intake of vegetables, fruits, meat, and fish demonstrated a 0.261-fold lower COPD prevalence than those without such intake (p = 0.039). The dietary inflammatory index (DII) was significantly lower among participants without COPD than among those with COPD (mean DII = −3.6947, p = 0.002), indicating that a diet rich in anti-inflammatory nutrients can help reduce COPD risk. These findings suggest that vegetable consumption supports improved respiratory function, and a composite dietary pattern incorporating various food groups may help reduce the prevalence of COPD in the adult population.
The prevalence of metabolic syndrome (MetS) and its cost are increasing due to lifestyle changes and aging. This study aimed to develop a deep neural network model for prediction and classification of MetS according to nutrient intake and other MetS-related factors. This study included 17,848 individuals aged 40–69 years from the Korea National Health and Nutrition Examination Survey (2013–2018). We set MetS (3–5 risk factors present) as the dependent variable and 52 MetS-related factors and nutrient intake variables as independent variables in a regression analysis. The analysis compared and analyzed model accuracy, precision and recall by conventional logistic regression, machine learning-based logistic regression and deep learning. The accuracy of train data was 81.2089, and the accuracy of test data was 81.1485 in a MetS classification and prediction model developed in this study. These accuracies were higher than those obtained by conventional logistic regression or machine learning-based logistic regression. Precision, recall, and F1-score also showed the high accuracy in the deep learning model. Blood alanine aminotransferase (β = 12.2035) level showed the highest regression coefficient followed by blood aspartate aminotransferase (β = 11.771) level, waist circumference (β = 10.8555), body mass index (β = 10.3842), and blood glycated hemoglobin (β = 10.1802) level. Fats (cholesterol [β = −2.0545] and saturated fatty acid [β = −2.0483]) showed high regression coefficients among nutrient intakes. The deep learning model for classification and prediction on MetS showed a higher accuracy than conventional logistic regression or machine learning-based logistic regression.
Citations
Stroke patients often experience a walking dysfunction caused by decreased mobility, weakened muscular strength, abnormal posture control, and cognitive dysfunction. Anxiety/depression is the most important and prevalent neuropsychiatric complication of stroke survivors. Brain injury and the presence of malnutrition after stroke contribute to metabolic status and clinical outcome of patients. We examined the level of nutrition intake in stroke patients according to their degree of anxiety/depression. The data were obtained from 2013 to 2015 through the Korea National Health and Nutrition Examination Survey (KNHANES). Study subjects were categorized to either a group having no problem of anxiety/depression (n = 274) or a group having a problem of anxiety or depression (n = 104). The EuroQoL-5 Dimensions Health Questionnaire (EQ-5D) index score was derived from the first description of an individual health status based on the EQ-5D classification system, including mobility, self-care, usual daily activities, pain/discomfort, and anxiety/depression. The mean age was 67.4 years in the normal group and 68.0 years in the anxiety or depression group. In the anxiety or depression group, 39.4% were men vs. 53.3% in the normal group. The total energy intake (p = 0.013), riboflavin (p = 0.041), and niacin (p = 0.038) was significantly higher in stroke patients with no anxiety/depression than those in stroke patients with having an anxiety/depression. The group having no problem of anxiety/depression had significantly higher EQ-5D index compared to the group having a problem of anxiety/depression group (p < 0.001) had. The results suggest the association between nutrition intake, usual activities and pain/discomfort status in the stroke patients with having an anxiety/depression.
Citations
The aims of this study were to develop strategies and algorithms of calculating food commodity intake suitable for exposure assessment of residual chemicals by using the food intake database of Korea National Health and Nutrition Examination Survey (KNHANES). In this study, apples and their processed food products were chosen as a model food for accurate calculation of food commodity intakes uthrough the recently developed Korea food commodity intake calculation (KFCIC) software. The average daily intakes of total apples in Korea Health Statistics were 29.60 g in 2008, 32.40 g in 2009, 34.30 g in 2010, 28.10 g in 2011, and 24.60 g in 2012. The average daily intakes of apples by KFCIC software was 2.65 g higher than that by Korea Health Statistics. The food intake data in Korea Health Statistics might have less reflected the intake of apples from mixed and processed foods than KFCIC software has. These results can affect outcome of risk assessment for residual chemicals in foods. Therefore, the accurate estimation of the average daily intake of food commodities is very important, and more data for food intakes and recipes have to be applied to improve the quality of data. Nevertheless, this study can contribute to the predictive estimation of exposure to possible residual chemicals and subsequent analysis for their potential risks.
Citations
First
Prev
