• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.357-358
• /
• 2022

이 논문은 Deep Learning 을 이용해 의사의 진단의 도움을 줄 수 있는 Clinic Decision Support System(CDSS) Framework 를 제안한다. 당뇨병, 고혈압, 고지혈증 같은 대사질환은 증상이 있는 경우도 있지만 없는 경우가 대부분이다.[1] 그렇기 때문에 원격으로 진료할 경우 대사질환에 대한 부분을 놓칠 수 있다. 이러한 부분을 챗봇이 의사에게 Deep Neural Network(DNN)으로 예측된 정보를 제공해 도움을 준다.

• Clinical and Experimental Pediatrics
• /
• v.46 no.6
• /
• pp.585-590
• /
• 2003

Purpose : This study is designed to determine the prevalence of cardiovascular autonomic neuropathy and its relationship to risk factors in adolescents with diabetes mellitus(DM). Methods : Ninety-two diabetic patients(80 with type 1 DM and 12 with type 2 DM), ranging from eight to 26 years of age, were studied for cardiovascular autonomic function, and the relationship to age, duration of diabetes, glycated hemoglobin(HbA1c), urinary albumin excretion, and the presence of diabetic retinopathy and abnormal nerve conduction velocities(NCV) were analysed. Autonomic function was assessed by measuring heart rate variation during valsalva manoeuvre, deep breathing and standing from a lying position(30 : 15 ratio), and postural hypotension. Results : Among patients with type 1 DM, 22.5% had early, 8.7% had definite, and 1.3% had severe autonomic dysfunction, and among patients with type 2 DM, 16.7% had early, 8.3% had definite, and 8.3% had severe autonomic dysfunction. On logistic regression analysis including both type 1 and type 2 diabetic patients, the age of the patient(OR=1.133(1.003-1.279), P<0.05) and duration of diabetes(OR=1.148(1.009-1.307), P<0.05) significantly predicted cardiovascular autonomic dysfunction while HbA1c, blood pressure, urinary albumin excretion, and presence of diabetic retinopathy and abnormal NCV did not. The valsalva ratio was borderline or abnormal in 31.5% of patients, the heart rate variation on deep breathing in 41.3%, the 30 : 15 ratio in 14.1%, and postural hypotension in 9.8% of patients. The valsalva ratio and the heart rate variation on deep breathing significantly predicted cardiovascular autonomic dysfunction, but the 30 : 15 ratio and postural hypotension did not. Conclusion : Cardiovascular autonomic dysfunction was found in 32.6% of diabetic patients and 10.8 % of patients had definite or severe involvement. The risk of cardiovascular autonomic dysfunction increased with the patient's age and the duration of DM. This study suggests that the valsalva ratio and the heart rate variation on deep breathing are the most useful tests in evaluating the cardiovascular autonomic function in children and adolescents with DM.

• Journal of Digital Convergence
• /
• v.21 no.3
• /
• pp.33-39
• /
• 2023

This study is a performance evaluation of a blood sugar monitoring system that combines a PPG sensor, which is an evaluation device for blood glucose monitoring, and a DNN algorithm when monitoring capillary blood glucose. The study is a researcher-led clinical trial conducted on participants from September 2023 to November 2023. PPG-BGMS compared predicted blood sugar levels for evaluation using 1-minute heart rate and heart rate variability information and the DNN prediction algorithm with capillary blood glucose levels measured with a blood glucose meter of the standard personal blood sugar management system. Of the 100 participants, 50 had type 2 diabetes (T2DM), and the average age was 67 years (range, 28 to 89 years). It was found that 100% of the predicted blood sugar level of PPG-BGMS was distributed in the A+B area of the Clarke error grid and Parker(Consensus) error grid. The MARD value of PPG-BGMS predicted blood glucose is 5.3 ± 4.0%. Consequentially, the non-blood-based PPG-BGMS was found to be non-inferior to the instantaneous blood sugar level of the clinical standard blood-based personal blood glucose measurement system.

• Journal of Korean Academy of Nursing
• /
• v.41 no.4
• /
• pp.491-499
• /
• 2011

Purpose: The study was conducted to develop and test a hypothetical model which explains self-care behavior in patients with type 2 diabetes was established based on the Self-Determination Theory. Methods: The participants were 218 patients with type 2 diabetes mellitus enrolled in an outpatient clinic of one endocrine center in Korea. The data were collected using questionnaires from April 5 through May 7, 2010. The descriptive and correlation statistics were analyzed using the SPSS/WIN 15.0 and the structural equation modeling procedure was performed using the AMOS 7.0 program. Results: The results of this study showed that competence and autonomous motivation were the strong factors influencing self-care behavior in patients in this sample. Support from health provider for autonomy was a significant indirect factor on self-care behavior. These factors explained 64.9% of variance in the participants' self care behavior. The proposed model was concise and extensive in predicting self-care behavior of the participants. Conclusion: Findings may provide useful assistance in developing effective nursing interventions for maintaining and promoting self-care behavior in patients with type 2 diabetes.

• Korean Journal of Adult Nursing
• /
• v.18 no.3
• /
• pp.426-435
• /
• 2006

Purpose: The purpose of this study was to explore the predictors of cardiovascular risk factors among type 2 diabetic patients. Method: Data were collected from November, 2003 to June, 2004 using a physiological index and questionnaires. Patients(N=159) aged 40 and above were conveniently recruited from health care centers in B city. Data were analyzed with descriptive statistics, Pearson correlation and stepwise multiple regression using SPSS WIN 10.0 program. Results: The cardiovascular risk factors were negatively related with female gender, household monthly income, educational experience about diabetes, physical activity, self-care, self-efficacy and problem oriented coping, while positively related with the duration of diabetes, diabetic family history and depression. Self-care, diabetic family history, female gender, monthly household income, self-efficacy, affective-oriented coping and physical activity predicted 41.5% of the variance in cardiovascular risk factors of diabetic patients. Conclusion: According to the findings of this study, we concluded that cardiovascular risk factors of type 2 diabetic patients are related to the modifiable and non-modifiable variables. Self-care, self-efficacy, affective oriented coping, and physical activity were identified as modifiable variables. Intervention programs to increase those variables are warranted to reduce cardiovascular risk factors among type 2 diabetic patients.

• Journal of Korean Biological Nursing Science
• /
• v.22 no.1
• /
• pp.36-44
• /
• 2020

Purpose: The purpose of this study was to predict measuring site suited for abdominal skin fold thickness (ASFT) by measuring the distribution of abdominal subcutaneous fat thickness (AScFT) and ascertain the correlations among obesity indicators. Methods: The size of analysis materials was 124 secondary data measured by ultrasonic device, bioelectrical impedance analyzer and caliper. Data were analyzed using t-test, and Pearson's correlation. Results: The average of AScFT was 10.63± 6.79mm with its range 1.39-36.16 mm, and AScFT of female and of central parts were thicker than those of male and outer parts in the abdomen. The average of ASFT was 29.26±12.59 mm. Site 5 on Figure 1 was most similar to the average of AScFT in both sexes. Body mass index (BMI) and waist hip ratio (WHR) were 23.65±3.98 and 0.88±0.05 respectively. The body weight, BMI, WHR, visceral fat, ASFT vs AScFT revealed in significant correlation (r= .29, r= .55, r= .39, r= .33. r= .29). Conclusion: BMI and WHR seem more useful than other obesity indicators, when obesity control is necessary for Type 2 diabetes patients. Site 5 on Figure 1 is most suitable site to measure ASFT.

• Child Health Nursing Research
• /
• v.25 no.4
• /
• pp.449-457
• /
• 2019

Purpose: The purpose of this study was to identify predictors of eating disorders in adolescents with type 1 diabetes, with the goal of providing data in support of nursing interventions to improve their health. Methods: A total of 136 adolescents aged 13-18 years with type 1 diabetes completed the Diabetes Eating Problem Survey-Revised, Rosenberg Self-Esteem Scale, and the Beck Depression Inventory-II, using structured self-reported questionnaires. The collected data were analyzed using the t-test, $x^2$ test, and binominal logistic regression with SPSS version 23.0 for Windows. Results: The prevalence of eating disorders in adolescents with type 1 diabetes was 39%. Four significant predictors of eating disorders were identified; absence of body satisfaction (odds ratio [OR]=3.87, 95% confidence interval [CI]=1.55~9.65), depression (OR=2.87, 95% CI=1.13~7.28), female gender (OR=2.67, 95% CI=1.09~6.54), and glycosylated hemoglobin type A1c levels (OR=1.47, 95% CI=1.10~1.97). Conclusion: In order to prevent eating disorders among adolescents with type 1 diabetes, programs for managing adolescents' depression and improving their body satisfaction should be developed. Futhermore, more attention should be directed towards programs aiming to prevent eating disorders in female adolescents.

• The Korean Journal of Applied Statistics
• /
• v.31 no.5
• /
• pp.573-585
• /
• 2018

In this study, we fit the logistic regression model and naïve Bayesian classifier model using 11 risk factors to predict the incidence rate probability for type 2 diabetes mellitus. We then introduce how to construct a nomogram that can help people visually understand it. We use data from the 2013-2015 Korean National Health and Nutrition Examination Survey (KNHANES). We take 3 interactions in the logistic regression model to improve the quality of the analysis and facilitate the application of the left-aligned method to the Bayesian nomogram. Finally, we compare the two nomograms and examine their utility. Then we verify the nomogram using the ROC curve.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.6
• /
• pp.324-333
• /
• 2018

The aim of this study was to investigate the latent classes and predictors of chronic diseases such as hypertension, dyslipidemia, arthritis, thyroid disease, depression, atopy, allergy, and diabetes. The subjects of this study were Korean citizens who participated in the Korea National Health and Nutrition Examination Survey in 2014. Stratified cluster sampling method was used with a sample size of 7,550. Latent hierarchy analysis was applied to this data. Four classes were identified. Class 1 consisted of participants with hypertension and diabetes. Class 2 consisted of participants with atopy and allergies. Class 3 consisted of participants with dyslipidemia, arthritis, thyroid disease, and depression. Class 4 consisted of participants without any chronic diseases. In comparing Class 1 to Class 4, age, physical activity, self-management, obesity, and presence of high cholesterol were found to be significant. In comparing Class 2 to Class 4, gender, age, and education level were significant. When Class 3 was compared to Class 4, gender, age, pain and discomfort, as well as high cholesterol were found to be significant. Diabetes and hypertension should be treated as comorbid conditions, applying integrated treatments involving effective drug treatment, diet, and physical activity programs. Atopy was found to be strongly correlated with allergies. Thyroid disease was found to coexist with dyslipidemia and arthritis, along with having a strong correlation to depression. Age-appropriate preventive measures can help reduce the risk of chronic diseases.

• Journal of Convergence for Information Technology
• /
• v.9 no.8
• /
• pp.248-253
• /
• 2019

Early diagnosis of mild cognitive impairment (MCI) can reduce the incidence of dementia. This study developed the MCI prediction model for the elderly in Korea. The subjects of this study were 3,240 elderly (1,502 men, 1,738 women) aged 65 and over who participated in the Korean Longitudinal Survey of Aging (KLoSA) in 2012. Outcome variables were defined as MCI prevalence. Explanatory variables were age, marital status, education level, income level, smoking, drinking, regular exercise more than once a week, average participation time of social activities, subjective health, hypertension, diabetes Respectively. The prediction model was developed using Restricted Boltzmann Machine (RBM) neural network. As a result, age, sex, final education, subjective health, marital status, income level, smoking, drinking, regular exercise were significant predictors of MCI prediction model of rural elderly people in Korea using RBM neural network. Based on these results, it is required to develop a customized dementia prevention program considering the characteristics of high risk group of MCI.