• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1191-1205
• /
• 2022

Particulate matter(PM) among air pollutants with complex and widespread causes is classified according to particle size. Among them, PM_2.5 is very small in size and can cause diseases in the human respiratory tract or cardiovascular system if inhaled by humans. In order to prepare for these risks, state-centered management and preventable monitoring and forecasting are important. This study tried to predict PM_2.5 in Seoul, where high concentrations of fine dust occur frequently, using two ensemble models, random forest (RF) and extreme gradient boosting (XGB) using 15 local data assimilation and prediction system (LDAPS) weather-related factors, aerosol optical depth (AOD) and 4 chemical factors as independent variables. Performance evaluation and factor importance evaluation of the two models used for prediction were performed, and seasonal model analysis was also performed. As a result of prediction accuracy, RF showed high prediction accuracy of R² = 0.85 and XGB R² = 0.91, and it was confirmed that XGB was a more suitable model for PM_2.5 prediction than RF. As a result of the seasonal model analysis, it can be said that the prediction performance was good compared to the observed values with high concentrations in spring. In this study, PM_2.5 of Seoul was predicted using various factors, and an ensemble-based PM_2.5 prediction model showing good performance was constructed.

• Proceedings of the KAIS Fall Conference
• /
• 2009.05a
• /
• pp.114-118
• /
• 2009

주요 일간지와 KBS 1 9시 뉴스에서 다루고 있는 건강관련 기사의 내용을 분석하여, 건강관련 정보의 경향을 파악하여, 건강 예보제 실시를 위한 현황 분석을 위해 본 연구를 실시하였다. 1. 일간지 건강정보 내용분석 결과요약: 기사 보도 분야에서는 생활건강(47.8%), 사회(14.6%), 종합(7.7%), 국제(4.7%), 경제(1.5%) 순이었고, 3/4분기에서만 국제와 경제 분야가 종합분야 보다 많이 보도 되었으며, 기타 분야가 22.9%로 많은 비율을 차지하였다. 건강정보를 대상 성별별로 분류 하였을 시 남녀 모두에 해당되는 자료가 대다수였고(87.9%), 여성이 대상인 정보(8.0%)가 남성(4.1%)보다 많았으며, 생애 주기별 대상으로 분류 하였을 시에 역시 특별히 구분되지 않은 모든 연령층에 해당 정보가 가장 많았고(60.8%), 성인(19.8%), 학동기 어린이(7.3%), 청소년 (4.9%), 노인(4.9%), 영유아(3.3%) 순이었다. 일간지별 기사의 주제를 조사한 결과 두 일간지의 총합은 병의 원인 및 위험인자(15.5%)가 가장 많이 보도 되었는데, 조선일보는 건강증진, 치료 및 술기, 투약, 기타의 순이었고, 한겨레신문은 건강증진, 행정, 치료 및 술기, 투약 순이었으며 각 주제별로 분기별로 약간의 차이를 나타내었다. 예측성에 관한 내용분석을 보면 예보성은 있는 경우(76.2%)가 없는 경우보다 많았고, 예보성의 정보는 알림성, 예측성, 행사성의 순이었고 예측성의 경우 건강형태가 가장 많았으나 한겨레 신문의 경우 기타에 속하는 경우가 가장 많았다. 사 ICD-10 체계, 21대 분류로 질병에 관한 기사를 분류한 결과 신생물(14.5%), 특정 감염성 및 기생충성 질환(13.6%), 정신 및 행동장애(9.5%)의 순이었으며 두 일간지간의 차이를 보였다. 2. TV 뉴스 건강정보 내용분석 결과요약: 건강정보의 대상 특징 성별은 모두 해당되는 경우가 265회 중 238회 (89.8%)로 가장 많았고, 생애주기별 대상으로 보면 모든 연령층에 해당 되는 것이 154회(58.1%)로 가장 많았다. 건강정보의 주제에 대해서 조사한 결과 병의 원인 및 위험인자가 73회(27.5%), 역학(역학조사 및 보도성)이 64회 (24.2%), 행정이 30회(11.3%), 증상 및 호소가 27회(10.2%) 등의 빈도순으로 조사 되었다. 건강정보의 내용의 분야를 보면 대분류로는 질병관리 분야가 102회(38.5%), 보건의료제도 및 행정 분야가 52회(19.6%), 보건행태 및 기타 42회(15.8%), 생활환경분야 39회(14.7%)의 빈도순으로 나타났다. 건강정보 내용을 질병의 분류 ICD-10 체계로 분석한 결과는 특정감염성 및 기생충성 질환 48회(26.8%), 소화기계의 질환, 손산, 중독 및 외인에 의한 특정기타 결과, 건강상태 및 보건서비스 접촉에 주는 요인 등의 빈도순으로 조사되었다.

• Journal of Digital Convergence
• /
• v.17 no.12
• /
• pp.435-444
• /
• 2019

The purpose of this study was to investigate the relationship between sleep duration and muscle strength in Korean adults aged 19 years and older. The cross-sectional analysis was conducted using the 2016 National Health and Nutrition Examination Survey data and Chi square test and multiple regression analysis were used. As a result of the analysis, the grip strength of those with more than weekday average sleep duration of 9 hours was found to be -1.267kg compared with those with weekday average sleep duration of 7 hours. The grip strength of those with more than weekend average sleep duration of 9 hours was found to be -0.879kg compared with those with weekend average sleep duration of 7 hours. In model simultaneously adjusting for both the average weekday and weekend average sleep duration, weekday average sleep duration of 9 hours was found to be -1.034kg compared with those with weekday average sleep duration of 7 hours. Therefore, careful observation will be required in light of the fact that both sleep duration and grip strength can predict future health conditions.

• Journal of Hospice and Palliative Care
• /
• v.18 no.1
• /
• pp.51-59
• /
• 2015

Purpose: Predicting life expectancy of terminally ill cancer patients is very important. In many studies, ferritin is detected at higher levels in the sera of cancer patients, and higher ferritin level correlates with aggressiveness of disease and poor outcomes of patients. This study evaluated a prognostic role of serum ferritin levels in terminally ill cancer patients. Methods: This study enrolled 65 terminally ill cancer patients from March through June 2012. We assessed routine laboratory findings including serum ferritin levels as well as demographic and clinical characteristics of the patients. To examine the association between serum ferritin levels and patient's characteristics, we used Spearman's correlation analysis, Wilcoxon's rank sum test or Kruskal-Wallis test, as appropriately. For multivariate analysis, Cox's proportional hazard regression model was used to evaluate significance of serum ferritin levels as a prognostic factor. Results: A negative correlation between serum ferritin levels and survival time was found. After adjusting for sex, age, performance status, creatinine levels and white blood cell counts, serum ferritin levels were significantly associated with survival time. Conclusion: Even at the very end of life of terminal cancer patients, serum ferritin levels were an independent prognostic factor for survival.

• Journal of Life Science
• /
• v.27 no.10
• /
• pp.1215-1224
• /
• 2017

Until now, various oncogenic pathways were idenfied. The accumulation of DNA mutation induces genomic instability in the cell, and it makes cancer. The development of bioinformatics and genomics, to find the precise and reliable biomarker is available. This biomarker could be applied the early-dignosis, prediction and convalescence of cancer. Recently, Transposable elements (TEs) have been attracted as the regulator of genes, because they occupy a half of human genome, and the cause of various diseases. TEs induce DNA mutation, as well as the regulation of gene expression, that makes to cancer development. So, we confirmed the relationship between TEs and colon cancer, and provided the clue for colon cancer biomarker. First, we confirmed long interspersed nuclear element-1 (LINE-1), Alu, and long terminal repeats (LTRs) and their relationship to colon cancer. Because these elements have large composition and enormous effect to the human genome. Interestingly, colon cancer specific patterns were detected, such as the hypomethylation of LINE-1, LINE-1 insertion in the APC gene, hypo- or hypermethylation of Alu, and isoform derived from LTR insertion. Moreover, hypomethylation of LINE-1 in proto-oncogene is used as the biomarker of colon cancer metastasis, and MLH1 mutation induced by Alu is detected in familial or hereditary colon cancer. The genes, effected by TEs, were analyzed their expression patterns by in silico analysis. Then, we provided tissue- and gender-specific expression patterns. This information can provide reliable cancer biomarker, and apply to prediction and diagnosis of colon cancer.

• Journal of the Korean Society of Radiology
• /
• v.82 no.5
• /
• pp.1246-1257
• /
• 2021

Purpose To assess the predictive factors and describe the imaging features of mediastinal lymph node (MLN) metastases in patients with head and neck cancer. Materials and Methods We compared the clinical features and disease characteristics (sex, age, site of primary tumor, histologic type, history of prior treatments, TNM stages, and metastasis in cervical LNs) of patients with head and neck cancers between the MLN metastasis and no MLN metastasis groups. We also evaluated the chest CT (distribution and maximum dimension of the largest LN) and PET/CT (maximum standardized uptake value) features of MLN metastases based on the MLN classification. Results Of the 470 patients with head and neck cancer, 55 (11.7%) had MLN metastasis, involving 150 mediastinal stations. Hypopharynx cancer, recurrent tumor, T4 stage, N2/N3 stages, and M1 stage were found to be significant predicting factors for MLN metastasis. The most common location of MLN metastasis was ipsilateral station 2 (upper paratracheal LNs, 36.4%), followed by ipsilateral station 11 (interlobar LNs, 27.3%) and ipsilateral station 10 (hilar LNs, 25.5%). Conclusion Metastasis to MLNs should be considered in patients with head and neck cancer, especially in cases that are associated with a hypopharyngeal cancer, recurrent tumor, and high TNM stages.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2016.05a
• /
• pp.124-124
• /
• 2016

하천에서의 분변성대장균은 분변성 오염 정도를 나타내는 지표로서, 이 농도가 높을수록 오염된 하천수와의 접촉을 통한 호흡기, 소화기 및 피부 관련 질병의 발발 확률이 높다고 알려져 있다. 따라서 하천에서의 수영, 수상스키 등과 같은 입수형 친수활동을 할 때, 분변성대장균 농도가 농도 기준 이하인지를 확인하고 이러한 정보를 친수활동에 이용할 필요가 있다. 그러나 분변성대장균의 경우, 현재 자동수질측정망에서 측정되고 있는 다른 수질인자들과는 달리 실시간 측정이 불가능하다고 알려져 있다. 분변성대장균을 측정하는데 있어 최소 18시간 이상이 필요하며, 이러한 분변성대장균 측정 방식은 하천 이용자들이 안전한 친수활동을 영위하는데 있어 적절한 수질 정보를 제공하지 못한다. 그러므로 분변성대장균을 예측하는 모델을 개발하고, 이를 이용하여 실시간 분변성대장균 정보를 생성하여 하천 이용자들에게 제공할 필요가 있다. 본 연구에서는 친수활동이 활발하게 이루어지는 곳 중 하나인 북한강의 대성리 지점에 대해 데이터 기반 모델을 이용하여 분변성대장균을 예측하였다. 데이터 기반 모델은 물리 기반 모델에서 필요한 지형데이터나 비점오염원 등의 초기 오염물의 양에 대한 데이터를 필요로 하지 않고, 대신 독립변수로 사용되는 기상 및 수질데이터를 필요로 한다. 이러한 기상 및 수질데이터는 기존 기상관측소, 수질관측소에서 매일 자동으로 측정되기 때문에 데이터 기반 모델은 물리 기반 모델에 비해 입력데이터를 구성하기가 쉽다는 장점을 지닌다. 이러한 데이터 기반 모델 중 분류 모델은 회귀 모델과 달리 분변성대장균 농도가 일정 수질기준 이상을 넘는지를 바로 예측할 수 있다. 본 연구에서는 분류 모델 중 높은 예측력을 가진다고 알려진 랜덤포레스트(random forest) 기법을 이용하여 분변성대장균 예측 모델을 개발하였다. 분변성대장균 예측 모델은 주어진 기상 및 수질 조건에 대해 분변성대장균이 200 CFU/100ml가 넘는지를 예측하였다. 예측된 분변성대장균이 기준을 넘는 경우를 2등급, 넘지 않는 경우를 1등급으로 명명하였다. 모델을 개발하기 위하여 북한강 대성리 인근 측정소에서 2010년부터 2015년까지 측정된 기상 및 수질데이터를 수집하였다. 수집한 데이터를 훈련 및 검증데이터로 샘플링하였으며, 이 때 샘플링한 데이터가 기존 데이터가 가지고 있던 등급별 비율을 유지하기 위하여 층화샘플링을 하였다. 본 연구에서는 샘플링에 의한 불확실성을 줄이기 위하여 랜덤하게 50번 샘플링된 각각의 훈련데이터에 대해 모델을 개발하였다. 50개의 모델의 검증 결과를 종합한 결과, 전체 예측률은 0.139로 나타났다.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.5
• /
• pp.1203-1214
• /
• 2016

Obesity is a risk factor for various diseases as well as itself a disease and associated with socioeconomic factors. The obesity proportion has been increasing in Korea over about 15 years so that investigation of the socioeconomic factors related with obesity is important in terms of preventation of obesity. In particular, the association between obesity and socioeconomic status varies with gender and has spatial dependency. In the paper, we estimate the effects of socioeconomic factors on obesity proportion by gender, considering the spatial correlation. Here, a conditional autoregressive model under the Bayesian framework is used in order to take into account the spatial dependency. For the real applicaiton, we use the obestiy proportion dataset at 25 districts of Seoul in 2010. We compare the proposed spatial model with a non-spatial model in terms of the goodness-of-fit and prediction measures so the spatial model performs well.

• Journal of the Health Care and Life Science
• /
• v.11 no.2
• /
• pp.417-424
• /
• 2023

This study aimed to analyze the association between hyperuricemia and hs-CRP in adults with hypercholesterolemia and abdominal obesity, utilizing data from the 7th Korea National Health and Nutrition Examination Survey. The subjects were classified into fourgroups based on hypercholesterolemia and abdominal obesity, and binary logistic regression analysis was conducted. The association between hyperuricemia and hs-CRP wasevident in the abdominal obesity group, with an OR 2.22 (95% CI 2.070-2.395). In thegroup with both conditions, the OR was 2.31 (95% CI 2.032-2.626). Stratified by gender, both conditions showed a higher OR in males 2.29 (95% CI 1.911-2.748), while in females, the abdominal obesity group exhibited a higher OR of 2.44 (95% CI 2.146-2.775), indicating a gender-specific difference. In conclusion, hyperuricemia and hs-CRP in adults with hypercholesterolemia and abdominal obesity demonstrated a significant association, suggesting their role as predictive factors for inflammatory responses.

• Tuberculosis and Respiratory Diseases
• /
• v.66 no.4
• /
• pp.280-287
• /
• 2009

Background: The epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKIs), became an attractive therapeutic option for advanced non-small-cell lung cancer (NSCLC). Several studies suggested that there might be some different efficacy or response predictors between gefitinib and erlotinib. We compared the efficacy and toxicity of gefitinib and erlotinib in Korean patients with advanced NSCLC and evaluated specific predictors of response for both gefitinib and erlotinib. Methods: We collected the clinical information on patients with advanced NSCLC, who were treated with gefitinib or erlotinib at the Ewha Womans University Hospital, between July 2003 and February 2009. Median survival times were calculated using the Kaplan-Meier method. Results: Eighty-six patients (52 gefitinib vs. 34 erlotinib) were enrolled. Patient median age was 64 years; 53 (62%) subjects were male. Out of the 86 patients treated, 83 received response evaluation. Of the 83 patients, 35 achieved a response and 12 experienced stable disease while 36 experienced progressive disease, resulting in a response rate of 42% and a disease control rate of 57%. After a median follow-up of 502 days, the median progression-free and overall survival time was 129 and 259 days, respectively. Comparing patients by treatment (gefitinib vs erlotinib), there were no significant differences in the overall response rate (44% vs. 39%, p=0.678), median survival time (301 days vs. 202 days, p=0.151), or time to progression (136 days vs. 92 days, p=0.672). Both EGFR-TKIs showed similar toxicity. In a multivariate analysis using Cox regression model, adenocarcinoma was an independent predictor of survival (p=0.006; hazard ratio [HR], 0.487; 95% confidence interval [CI], 0.292-0.811). Analyses of subgroups did not show any difference in response predictors between gefitinib and erlotinib. Conclusion: Comparing gefitinib to erlotinib, there were no differences in the response rate, overall survival, progression-free survival, or toxicity. No specific predictor of response to each EGFR-TKI was identified.