Purpose: The objective of this study was to develop a predictive model for the sexual experiences of adolescents using the random forest method and to identify the “variable importance.” Methods: The study utilized data from the 2019 to 2021 Korea Youth Risk Behavior Web-based Survey, which included 86,595 man and 80,504 woman participants. The number of independent variables stood at 44. SPSS was used to conduct Rao-Scott χ2 tests and complex sample t-tests. Modeling was performed using the random forest algorithm in Python. Performance evaluation of each model included assessments of precision, recall, F1-score, receiver operating characteristics curve, and area under the curve calculations derived from the confusion matrix. Results: The prevalence of sexual experiences initially decreased during the COVID-19 pandemic, but later increased. “Variable importance” for predicting sexual experiences, ranked in the top six, included week and weekday sedentary time and internet usage time, followed by ease of cigarette purchase, age at first alcohol consumption, smoking initiation, breakfast consumption, and difficulty purchasing alcohol. Conclusion Education and support programs for promoting adolescent sexual health, based on the top-ranking important variables, should be integrated with health behavior intervention programs addressing internet usage, smoking, and alcohol consumption. We recommend active utilization of the random forest analysis method to develop high-performance predictive models for effective disease prevention, treatment, and nursing care.

Stroke is a leading cause of adult disability and the second-leading cause of death in Korea. It is also the third-leading cause of death in the United States, leading to a serious demand for new interventions to improve the quality of life in stroke survivors. To this end, direct cortical stimulation using an epidural electrode has been reported with promising results in animal and human studies, showing the potential for enhancing the recovery in chronic stroke patients. For optimal results, doctors must be able to modify the stimulation pattern as frequently as needed over a period of time for a given patient. However, severe aftereffects caused by stroke limit patients' activities, making regular doctor visits for treatment difficult. This study aims to develop a prototype of a telemedicine system to enhance stroke recovery by using a ZigBee-based wireless neuro-stimulator. The ZigBee is a stable platform for many low-power wireless applications. To allow stroke patients to remotely obtain neuro-stimulation treatments from their doctors, we connected the ZigBee to the internet. The system also allows doctors to personalize treatment based on the history of the stimulation parameters. The system developed here can also be beneficial as a common platform for a wide range of brain diseases and clinical care for which electric stimulation is used.
Adult ; Animals ; Brain Diseases ; Cause of Death ; Electric Stimulation ; Electrodes ; Humans ; Internet ; Korea ; Quality of Life ; Stroke ; Survivors ; Telemedicine ; United States

OBJECTIVE: We developed a Revised Korean version of the Geriatric Depression Scale (GDS-KR) and examined its reliability, validity, and factor structures. We also estimated its optimal cutoff scores for major depressive disorder (MDD) and minor depressive disorder (MnDD) stratified by age and education. METHODS: The GDS-KR was administered to 888 subjects (61 MDD patients, 45 MnDD patients, and 782 normal elders). Its internal consistency and test-retest reliability were examined. Its concurrent validity was evaluated using Pearson correlation coefficients with the Korean version of the Center for Epidemiologic Studies Depression Scale (CES-D-K) and Hamilton Depression Rating Scale (HAM-D). The mean GDS-KR scores of the MDD patients, MnDD patients and normal elders were compared to evaluate its discriminant validity. To evaluate its construct validity, a principal component analysis with varimax rotation was performed. Receiver operator characteristic (ROC) curve analyses were performed to evaluate its diagnostic ability. RESULTS: Chronbach's coefficient alpha for the GDS-KR was 0.90 and the test-retest reliability was 0.91 (p<0.01). The Pearson correlation coefficients of the GDS-KR scores with the CES-D-K and HAM-D scores were 0.63 (p<0.01) and 0.56 (p<0.01), respectively. The GDS-KR consisted of 5 factors. The optimal cut-off scores of the GDS-KR were 16/17 for MDD only and 15/16 for both MDD and MnDD. The optimal cutoff scores of the GDS-KR were higher in the less educated and younger subjects. The diagnostic accuracy for MDD of the GDS-KR was higher than that of the CES-D. CONCLUSION: The GDS-KR was found to be a reliable and valid questionnaire for screening MDD and MnDD in late life.
Depression* ; Depressive Disorder ; Depressive Disorder, Major ; Education ; Epidemiologic Studies ; Factor Analysis, Statistical ; Humans ; Mass Screening ; Principal Component Analysis ; Surveys and Questionnaires