Younghwa Baek

Mrs. Younghwa Baek

orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 April 2022 in BMC Public Health
Verified
Journal Article
Open access
PDF file
JKJunho Kim
Junho Kim
SMSujeong Mun
Sujeong Mun
SLSiwoo Lee
Siwoo Lee
KJKyoungsik Jeong
Kyoungsik Jeong
YBYounghwa Baek
Younghwa Baek
Background: Metabolic syndrome (MetS) is a complex condition that appears as a cluster of metabolic abnormalities, and is closely associated with the prevalence of various diseases. Early prediction of the risk of MetS in the middle-aged population provides greater benefits for cardiovascular disease-related health outcomes. This study aimed to apply the latest machine learning techniques to find the optimal MetS prediction model for the middle-aged Korean population. Methods: We retrieved 20 data types from the Korean Medicine Daejeon Citizen Cohort, a cohort study on a community-based population of adults aged 30–55 years. The data included sex, age, anthropometric data, lifestyle-related data, and blood indicators of 1991 individuals. Participants satisfying two (pre-MetS) or ≥ 3 (MetS) of the five NECP-ATP III criteria were included in the MetS group. MetS prediction used nine machine learning models based on the following algorithms: Decision tree, Gaussian Naïve Bayes, K-nearest neighbor, eXtreme gradient boosting (XGBoost), random forest, logistic regression, support vector machine, multi-layer perceptron, and 1D convolutional neural network. All analyses were performed by sequentially inputting the features in three steps according to their characteristics. The models’ performances were compared after applying the synthetic minority oversampling technique (SMOTE) to resolve data imbalance. Results: MetS was detected in 33.85% of the subjects. Among the MetS prediction models, the tree-based random forest and XGBoost models showed the best performance, which improved with the number of features used. As a measure of the models’ performance, the area under the receiver operating characteristic curve (AUC) increased by up to 0.091 when the SMOTE was applied, with XGBoost showing the highest AUC of 0.851. Body mass index and waist-to-hip ratio were identified as the most important features in the MetS prediction models for this population. Conclusions: Tree-based machine learning models were useful in identifying MetS with high accuracy in middle-aged Koreans. Early diagnosis of MetS is important and requires a multidimensional approach that includes self-administered questionnaire, anthropometric, and biochemical measurements.

19 February 2019 in BMC Gastroenterology
Verified
Journal Article
Open access
PDF file
MHMin Kyung Hyun
Min Kyung Hyun
YBYounghwa Baek
Younghwa Baek
SLSiwoo Lee
Siwoo Lee
This study was conducted to analyze the association between digestive symptoms and sleep disturbance, and to determine if any digestive symptoms are related to sleep disturbance. This was a cross-sectional study of 5792 subjects surveyed in a community-based cohort. Subjects provided information regarding the quality of sleep as assessed by the Pittsburgh Sleep Quality Index (PSQI), as well as digestive symptoms as assessed by the Gastrointestinal Symptom Rating Scale (GSRS). Logistic regressions were used to examine factors associated with sleep quality. The mean PSQI global score of the no sleep disturbances group (n = 4948) was 3.92 (SD = 2.14), while that of the sleep disturbance group (n = 844) was 11.18 (SD = 2.17). The association between digestive symptoms and sleep disturbance was evaluated by logistic regression after adjusting for cofounding factors. The results revealed that sleep disturbances were associated with digestive symptoms (aOR = 1.29, 95% CI = 1.22–1.36), especially abdominal pains (aOR = 1.63, 95% CI = 1.19–2.25), acid regurgitation (aOR = 1.48, 95% CI = 1.17–1.86), abdominal distension (aOR = 1.80, 95% CI = 1.42–2.28), and eructation (aOR = 1.59, 95% CI = 1.24–2.03). Digestive symptoms and sleep disturbances seem to be associated. These results will help medical professionals to effectively diagnose and manage patients with sleep disturbance. Furthermore, subsequent studies using comprehensive longitudinal data should be conducted to confirm the results of the present study.

1 February 2023 in Nature and Science of Sleep
Verified
Journal Article
Open access
PDF file
SLSu Eun Lim
Su Eun Lim
HKHo Seok Kim
Ho Seok Kim
SLSi Woo Lee
Si Woo Lee
KBKwang-Ho Bae
Kwang-Ho Bae
YBYounghwa Baek
Younghwa Baek
Purpose: The commercialization of sleep activity tracking devices has made it possible to manage sleep quality at home. However, it is necessary to verify the reliability and accuracy of wearable devices through comparison with polysomnography (PSG), which is the standard for tracking sleep activity. This study aimed to monitor overall sleep activity using Fitbit Inspire 2™ (FBI2) and to evaluate its performance and effectiveness through PSG under the same conditions. Patients and Methods: We compared the FBI2 and PSG data of nine participants (four male and five female participants; average age, 39 years) without severe sleeping problems. The participants wore FBI2 continuously for 14 days, considering the period of adaptation to the device. FBI2 and PSG sleep data were compared using paired t-tests, Bland–Altman plots, and epoch-by-epoch analysis for 18 samples by pooling data from two replicates. Results: The average values for each sleep stage obtained from FBI2 and PSG showed significant differences in the total sleep time (TST), deep sleep, and rapid eye motion (REM). In the Bland–Altman analysis, TST (P = 0.02), deep sleep (P = 0.05), and REM (P = 0.03) were significantly overstated in FBI2 compared to PSG. In addition, time in bed, sleep efficiency, and wake after sleep onset were overestimated, while light sleep was underestimated. However, these differences were not statistically significant. FBI2 showed a high sensitivity (93.9%) and low specificity (13.1%), with an accuracy of 76%. The sensitivity and specificity of each sleep stage was 54.3% and 62.3%, respectively, for light sleep, 84.8% and 50.1%, respectively, for deep sleep, and 86.4% and 59.1%, respectively for REM sleep. Conclusion: The use of FBI2 as an objective tool for measuring sleep in daily life can be considered appropriate. However, further research is warranted on its application in participants with sleep-wake problems.

2 February 2024 in BMJ Open
Verified
Journal Article
Open access
PDF file
EAEun Kyoung Ahn
Eun Kyoung Ahn
YBYounghwa Baek
Younghwa Baek
JPJi-Eun Park
Ji-Eun Park
SLSiwoo Lee
Siwoo Lee
HJHee-Jeong Jin
Hee-Jeong Jin
Objectives This study used National Health Insurance claims data from Korea to report the prevalence of sleep disorders and treatment status, including traditional Korean medicine, in the last 10 years. Methods This is a retrospective cohort study in Korea. All diagnosis and prescription data, including herbal medicine claims, from the Health Insurance Review and Assessment Service from 2011 to 2020 were reviewed. Prevalence estimation, direct medical expenses and prescribed amounts for sleep disorders were recorded. Results The prevalence of sleep disorders increased from 3 867 975 (7.62%) in 2011 to 7 446 846 (14.41%) in 2020, nearly doubling over 10 years. Insomnia was observed in 91.44% (n=9 011 692) of the patients. The mean number of hospital visits per patient for sleep disorders was 11.5 (±26.62). Benzodiazepines are the most commonly prescribed medications for sleep disorders, and gamma-isoyosan is the most frequently prescribed herbal medicine. Conclusions Sleep disorders are continuously increasing, as is the use of medical services—personal and social medical expenses are also increasing accordingly. Sleep disorders should be recognised as a significant health problem that needs to be actively addressed to improve quality of life.

2 April 2013 in BMC Complementary and Alternative Medicine
Verified
Journal Article
Open access
PDF file
EJEunsu Jang
Eunsu Jang
YBYounghwa Baek
Younghwa Baek
KPKihyun Park
Kihyun Park
SLSiwoo Lee
Siwoo Lee
Abdominal obesity (AO) is a medical condition in which excess body fat accumulates in the abdomen. It may cause adverse effects on health and result in reduced life expectancy or increased health problems. While various genetic approaches have explained the risks of AO in Western society, the Sasang constitution (SC) has been identified as a risk factor in Korean medicine. Different SC types are associated with different fat distribution, body shapes and susceptibility to diseases. We evaluated whether the SC type could be a risk for AO in a cross-sectional study among Koreans.

10 March 2015 in BMC Complementary and Alternative Medicine
Verified
Journal Article
Open access
PDF file
HJHee-Jeong Jin
Hee-Jeong Jin
YBYounghwa Baek
Younghwa Baek
HKhoseok kim
hoseok kim
JRJonghyang Ryu
Jonghyang Ryu
SLSiwoo Lee
Siwoo Lee
Biobanks are more important in medical area because they can give researchers data for demonstrating and validating their research. In this study, we developed a biobank called the Korea Constitutional Multicenter Bank (KCMB) based on Sasang Constitutional Medicine (SCM). The aim of the KCMB was a foundation to providing the scientific basis of SCM. The KCMB has been constructed since 2006 in 24 Korean medical clinics with collection of questionnaire data, physical measurements and biological information comprised the results from blood test and DNA analyses. All participants were prescribed Sasang Constitution (SC)-specific herbal remedies for the treatment, and showed improvement of original symptoms as confirmed by Korean medicine doctor. Collected data went through de-identification process using the electronic case report form system. For calculation of several SC type specific tendencies, we used the direct standardization and Chi-square tests. The KCMB collected clinical information from 3,711 study participants (1,353 men and 2,358 women) aged more than 10 years. The mean age (± standard deviation) was 47.1 (±16.6) and 47.7 (±15.8) years for men and women respectively. After applying the direct standardization, the estimated constitutional distributions for the SC types were as follows: 39.2% for Tae-eumin(TE), 27.1% for Soeumin(SE), 33.7% for Soyangyin(SY), and non-zero but below 0.1% for Taeyangyin(TY). The estimated distribution of TE was about 10% less, while that of SY and SE were slightly more than the distribution reported by Jema Lee established the SCM. Based on the participants’ medical history within the KCMB, each SC type had notably different frequencies for some diseases such as hypertension, diabetes, hyperlipidemia, stroke, and obesity (P < 0.001). The KCMB may serve to verify and validate SCM theories and practices. It may also provide new insights into SCM mechanisms. The results from many studies using the KCMB data are of great importance and value for making decisions in healthcare policy and developing novel therapies.