Purpose: This study aimed to develop and compare machine learning models for predicting prediabetes in young adults in Korea using dietary intake data and to identify the most effective model. Methods: Data from the ninth Korea National Health and Nutrition Examination Survey were used, with 823 participants aged 19–35 years selected after excluding those with missing data. Logistic regression, k-nearest neighbors, and random forest models were applied to predict prediabetes, and the analysis was conducted using the Orange 3.5 program. Five-fold cross-validation was performed to reduce performance variability, and test data were used for final model validation. Results: In the dataset, 14%–15% of participants were classified as having prediabetes. The random forest model showed the highest performance in terms of classification accuracy, harmonic mean of precision and recall, and precision. Logistic regression had the highest performance regarding the model’s ability to distinguish between individuals with and without prediabetes. Age, thiamine intake, and water intake emerged as the most important predictors. Conclusion This study demonstrated the utility of using dietary intake data to predict prediabetes in young adults. The random forest model provided the highest prediction accuracy, supporting early detection and intervention, which could help to reduce unnecessary treatment. This highlights nurses’ important role in educating patients about lifestyle changes and implementing preventive care. Future studies should incorporate additional factors, such as psychological and lifestyle variables, to improve the model's performance.

Purpose: This study aimed to develop and compare machine learning models for predicting prediabetes in young adults in Korea using dietary intake data and to identify the most effective model. Methods: Data from the ninth Korea National Health and Nutrition Examination Survey were used, with 823 participants aged 19–35 years selected after excluding those with missing data. Logistic regression, k-nearest neighbors, and random forest models were applied to predict prediabetes, and the analysis was conducted using the Orange 3.5 program. Five-fold cross-validation was performed to reduce performance variability, and test data were used for final model validation. Results: In the dataset, 14%–15% of participants were classified as having prediabetes. The random forest model showed the highest performance in terms of classification accuracy, harmonic mean of precision and recall, and precision. Logistic regression had the highest performance regarding the model’s ability to distinguish between individuals with and without prediabetes. Age, thiamine intake, and water intake emerged as the most important predictors. Conclusion This study demonstrated the utility of using dietary intake data to predict prediabetes in young adults. The random forest model provided the highest prediction accuracy, supporting early detection and intervention, which could help to reduce unnecessary treatment. This highlights nurses’ important role in educating patients about lifestyle changes and implementing preventive care. Future studies should incorporate additional factors, such as psychological and lifestyle variables, to improve the model's performance.

Purpose: This study aimed to develop and compare machine learning models for predicting prediabetes in young adults in Korea using dietary intake data and to identify the most effective model. Methods: Data from the ninth Korea National Health and Nutrition Examination Survey were used, with 823 participants aged 19–35 years selected after excluding those with missing data. Logistic regression, k-nearest neighbors, and random forest models were applied to predict prediabetes, and the analysis was conducted using the Orange 3.5 program. Five-fold cross-validation was performed to reduce performance variability, and test data were used for final model validation. Results: In the dataset, 14%–15% of participants were classified as having prediabetes. The random forest model showed the highest performance in terms of classification accuracy, harmonic mean of precision and recall, and precision. Logistic regression had the highest performance regarding the model’s ability to distinguish between individuals with and without prediabetes. Age, thiamine intake, and water intake emerged as the most important predictors. Conclusion This study demonstrated the utility of using dietary intake data to predict prediabetes in young adults. The random forest model provided the highest prediction accuracy, supporting early detection and intervention, which could help to reduce unnecessary treatment. This highlights nurses’ important role in educating patients about lifestyle changes and implementing preventive care. Future studies should incorporate additional factors, such as psychological and lifestyle variables, to improve the model's performance.

Purpose: This study aimed to develop and compare machine learning models for predicting prediabetes in young adults in Korea using dietary intake data and to identify the most effective model. Methods: Data from the ninth Korea National Health and Nutrition Examination Survey were used, with 823 participants aged 19–35 years selected after excluding those with missing data. Logistic regression, k-nearest neighbors, and random forest models were applied to predict prediabetes, and the analysis was conducted using the Orange 3.5 program. Five-fold cross-validation was performed to reduce performance variability, and test data were used for final model validation. Results: In the dataset, 14%–15% of participants were classified as having prediabetes. The random forest model showed the highest performance in terms of classification accuracy, harmonic mean of precision and recall, and precision. Logistic regression had the highest performance regarding the model’s ability to distinguish between individuals with and without prediabetes. Age, thiamine intake, and water intake emerged as the most important predictors. Conclusion This study demonstrated the utility of using dietary intake data to predict prediabetes in young adults. The random forest model provided the highest prediction accuracy, supporting early detection and intervention, which could help to reduce unnecessary treatment. This highlights nurses’ important role in educating patients about lifestyle changes and implementing preventive care. Future studies should incorporate additional factors, such as psychological and lifestyle variables, to improve the model's performance.

PURPOSE: This study is the narrative investigating research to comprehend the climacteric symptoms, depression and health promoting behavior of the male workers and to develop the nursing intervention. METHODS: The research was done from August to September 2011, and the subjects were the middle-aged males between 40 and 64 working in capital cities of Chungcheongnamdo. Among the 220 questionnaires, 189 were retrieved and used for the analysis. The data analysis was done by chi2-test, and t-test using the SPSS/WIN 19.0 program. RESULTS: The 70.9% of the subjects showed male climacterium and among them, those in their 40s showed high rate to the change in the body and emotions whereas those in their 50s showed high rate to the sexual function-related symptoms. Also, having the climacteric symptoms showed significant changes in depression and health promoting behavior. CONCLUSION: To promote health of the middle-aged male workers and the nursing intervention for those who show depression, verifying whether these males have climacteric symptoms is necessary.
Climacteric ; Depression ; Health Promotion ; Humans ; Male ; Surveys and Questionnaires ; Statistics as Topic

PURPOSE: This study attempted to develop a scale that measures the level of patients' recognition of the nurses' care, based on Watson's caring theory, and confirmed its reliability and validity. METHODS: The items were developed through a literature review and an expert content validity test. The questionnaires were administered to 285 inpatients of internal medicine and surgical units at two general hospitals. Construct validity was tested using exploratory and confirmatory factor analysis, and reliability was tested using Cronbach's alpha. RESULTS: This process resulted in a preliminary scale composed of 34 items; We used item analysis and five exploratory factor analyses, and consequently selected 14 items composed of three factors (respect, genuineness, and relationality). The confirmatory factor analysis verified the model fit and convergent and discriminant validity of the final items; criterion validity was confirmed with the positive correlation with the measurement scale of the patient-perceived quality of nursing . The overall scale reliability had a Cronbach's alpha of .92, which indicated internal consistency and reliability. CONCLUSION The developed scale showed content, construct, and criterion validity, and reliability, as well as convergent validity for each item and discriminant validity between the factors. This makes it suitable for use in a diverse range of future studies on nurse communication using structural equation models.

PURPOSE: The purpose of this study was to analyze the validity and reliability of the personality measurement tool for nursing college students. METHODS: Questionnaires were issued to 300 nursing students, with 275 eventually collected. The items were confirmed by validity experts. Construct validity was tested using exploratory factor analysis and confirmatory factor analysis. Reliability analysis was tested using Cronbach's α. Criterion validity was tested by analyzing correlation with the college adjustment scale. RESULTS: Eight factors were confirmed by exploratory factor analysis. Confirmatory factor analysis was used to confirm the model fit (Root-mean-square residual .03; Root-mean-square error of approximation .06; Comparative fit index .92); and convergent validity and discriminant validity were confirmed. In addition, the criterion validity was confirmed through correlation (r=.64, p<.001) with the college adjustment scale. The reliability of this tool was Cronbach's α .94. CONCLUSION: This tool can be used to measure personality in nursing education and can be used to develop and evaluate personality programs.
Education ; Education, Nursing ; Factor Analysis, Statistical ; Humans ; Nursing ; Reproducibility of Results ; Students, Nursing

PURPOSE: This study attempted to develop a scale that measures the level of patients' recognition of the nurses' care, based on Watson's caring theory, and confirmed its reliability and validity. METHODS: The items were developed through a literature review and an expert content validity test. The questionnaires were administered to 285 inpatients of internal medicine and surgical units at two general hospitals. Construct validity was tested using exploratory and confirmatory factor analysis, and reliability was tested using Cronbach's alpha. RESULTS: This process resulted in a preliminary scale composed of 34 items; We used item analysis and five exploratory factor analyses, and consequently selected 14 items composed of three factors (respect, genuineness, and relationality). The confirmatory factor analysis verified the model fit and convergent and discriminant validity of the final items; criterion validity was confirmed with the positive correlation with the measurement scale of the patient-perceived quality of nursing . The overall scale reliability had a Cronbach's alpha of .92, which indicated internal consistency and reliability. CONCLUSION: The developed scale showed content, construct, and criterion validity, and reliability, as well as convergent validity for each item and discriminant validity between the factors. This makes it suitable for use in a diverse range of future studies on nurse communication using structural equation models.
Factor Analysis, Statistical ; Hospitals, General ; Humans ; Inpatients ; Internal Medicine ; Nursing ; Reproducibility of Results

Purpose: A descriptive survey-based study was undertaken to determine how emotional intelligence mediates the relationship between social support and resilience by clinical nurses, thereby providing primary data for improving resilience. Methods: This study involved a descriptive survey of 202 nurses working in four general hospitals. Using SPSS/WIN 26.0, frequency analysis, descriptive statistics, and multiple regression analyses were conducted. Results: Social support had a statistically significant positive correlation with emotional intelligence (β=.49, p<.001) and resilience (β=.47, p<.001). Emotional intelligence showed a statistically significant positive correlation with resilience (β=.66, p<.001). Emotional intelligence was found to have a partial mediation effect on the relationship between social support and resilience (z=5.76, p<.001). Conclusion The study also discovered that social support and emotional intelligence are factors influencing clinical nurses' resilience. Furthermore, it evident that emotional intelligence has a partial mediating effect on the relationship between social support and resilience. Therefore, it is necessary to consider nurses’ emotional intelligence at the individual level to effectively improve resilience through social support.

Purpose: This study aimed to investigate the mediating effects of health promotion behavior (HPB) in the relationship between anxiety and quality of life (QoL) in young adults living in the post-pandemic era. Methods: A cross-sectionaldescriptiveonlinesurveydesign was utilized. Data on anxiety, QoL, HPB, and demographic characteristics were collected from 213 adults aged 19–35 years in Korea via an online survey in January 2024. The collected data were analyzed using SPSS 27.0 and PROCESS MACRO 4.2 software. Results: Strong correlations were observed among anxiety, QoL, and post-pandemic HPB (PP-HPB) in young adults, andanxiety and PP-HPB were identified as significant predictors of QoL. The total effect of anxiety on QoL was significant (B = −1.40, bootstrapped SE = 0.10), with both the direct effect (B = −0.70, bootstrapped SE = 0.09) and the indirect effect (B = −0.70, bootstrapped SE = 0.11) being significant. This suggests that PP-HPB partially mediated the relationship between anxiety and QoL. Conclusion This study highlights the importance of strengthening HPB with consideration of life changes since the coronavirus disease 2019 pandemic to improve QoL among young adults with anxiety.