• 문화기술의 융합
• /
• 제5권4호
• /
• pp.413-420
• /
• 2019

본 연구의 목적은 기존의 body fat mass 변수와 고콜레스테롤혈증의 연관성연구를 벗어나, 머신러닝기법을 기반으로 body fat mass 변수들의 조합을 이용하여 고콜레스테롤혈증 예측 모델을 개발하는 것이다. 이러한 연구를 위하여 국민건강영양조사 데이터를 기반으로 두 가지 variable selection 메소드와 머신러닝 알고리즘을 이용하여 총 6개의 모델을 생성하였고 질병 예측력을 비교분석하였다. 여러 body fat mass 관련 변수들 중에서 몸통지방량 변수가 고콜레스테롤혈증 예측력이 가장 우수한 변수인 것을 밝혀내었고, 머신러닝 기반 예측모델들 중에서 correlation-based feature subset selection 기반 naive Bayes 알고리즘을 이용한 모델이 0.739의 the area under the receiver operating characteristic curve 값과 0.36의 Matthews correlation coefficient 값을 얻었다. 이러한 연구의 결과는 향후 국내외 대규모 스크리닝 및 대중보건 연구에서 질병예측분야의 중요정보로 활용될 것으로 예상한다.

• Safety and Health at Work
• /
• 제1권1호
• /
• pp.69-79
• /
• 2010

Objectives: Various cytokines induced by inhalation of coal dust may mediate inflammation and lead to tissue damage or fibrosis, such as coal workers' pneumoconiosis (CWP). Methods: To investigate the relevance of serum cytokines in CWP, the levels of serum interleukin-8 (IL-8) and tumor necrosis factor-alpha (TNF-${\alpha}$) as CWP biomarkers in 110 retired coal miners (22 controls and 88 CWP subjects) were related to cross sectional findings and 1-year progressive changes of the pneumoconiosis. Progressive changes of CWP were evaluated by paired comparison of chest radiographs. Analysis by a receiver operating characteristic curve assessed the biomarker potential of each cytokine. Results: The mean serum IL-8 level was significantly higher in CWP compared to controls and IL-8 levels correlated with the degree of CWP. The median serum TNF-${\alpha}$ level was significantly higher in subjects with progressive CWP compared to subjects without CWP progression. The area under the ROC curve for IL-8 (0.70) and TNF-${\alpha}$ (0.72) for CWP identification and progression, respectively, indicated the biomarker potential of the two cytokines. Serum cutoff values of IL-8 and TNF-${\alpha}$ were 11.63 pg/mL(sensitivity, 69%; specificity, 64%) and 4.52 pg/mL (sensitivity, 67%; specificity, 79%), respectively. Conclusion: The results suggest that high levels of serum IL-8 are associated with the presence of CWP and those of serum TNF-${\alpha}$ are associated with the progression of CWP.

• 융합정보논문지
• /
• 제10권12호
• /
• pp.146-155
• /
• 2020

본 연구는 대사증후군을 예측하는 대리 표지자로서 감마 글루타밀 전이효소(gamma glutamyl transferase, GGT)의 유용성을 평가하고자 하였다. 20세 이상의 비만하지 않은 남성 7,155명을 연구대상자로 하였다. 대사증후군 진단기준은 NCEP-ATP III (National Cholesterol Education Program - Third Adult Treatment Panel) 기준을 적용하였다. GGT에 따른 대사증후군 발병 위험도는 로지스틱 회귀분석을 적용하였으며, GGT의 대사증후군 위험 예측능력을 확인하기 위해 ROC (receiver operating characteristic) 곡선을 구하였다. 연령과 체질량지수와 무관하게 GGT 1사분위수보다 4사분위수에서 대사증후군 발병위험이 7.09배 높게 나타났다(p<0.001). 대사증후군 진단을 위한 GGT의 곡선아래면적(area under the curve)은 0.715였으며, GGT의 절단값(cut-off value)은 40.0 U/L, 민감도는 65.0%, 특이도 70.2%로 나타났다. 따라서 GGT는 대사증후군을 진단하기 위한 유용한 진단 지표로 판단된다.

• 한국항행학회논문지
• /
• 제25권1호
• /
• pp.96-101
• /
• 2021

본 논문은 빅데이터를 이용하여 심방세동 환자의 뇌졸중 발병을 예측하는 기계 학습 모델을 제시한다. 학습 데이터로는 국민 건강 보험공단에서 제공하는 대한민국 전수에 해당하는 심방세동 환자의 정보를 수집하였다. 수집된 정보는 인구사회학, 과거 병력, 건강검진을 포함한 68개 독립변수로 구성된다. 본 연구의 목표는 기존 심방세동 환자의 뇌졸중 위험도 예측에 사용되던 통계적 모델 (CHADS2, CHA2DS2-VASc)의 성능을 검증하고 기계 학습 모델을 적용하여 기존 모델보다 높은 정확도를 가지는 모델을 제시하는 것이다. 제안하는 모델의 정확도, AUROC (area under the receiver operating characteristic)를 검증한 결과 제안하는 기계 학습 기반의 모형이 심방세동 환자의 뇌졸중 위험도를 사용한 모델이 기존의 통계적 모델보다 높은 정확도, 민감도, 특이도를 가지는 것을 확인할 수 있었다.

• 대한통합의학회지
• /
• 제10권3호
• /
• pp.107-117
• /
• 2022

Purpose : The purpose of this study was to establish a model of the predictive factors for success or failure of examinees undertaking the Korean physical therapist licensing examination (KPTLE). Additionally, we assessed the pass/fail cut-off point. Methods : We analyzed the results of 10,881 examinees who undertook the KPTLE, using data provided by the Korea Health Personnel Licensing Examination Institute. The target variable was the test result (pass or fail), and the input variables were: sex, age, test subject, and total score. Frequency analysis, chi-square test, descriptive statistics, independent t-test, correlation analysis, binary logistic regression, and receiver operating characteristic (ROC) curve analyses were performed on the data. Results : Sex and age were not significant predictors of attaining a pass (p>.05). The test subjects with the highest probability of passing were, in order, medical regulation (MR) (Odds ratio (OR)=2.91, p<.001), foundations of physical therapy (FPT) (OR=2.86, p<.001), diagnosis and evaluation for physical therapy (DEPT) (OR=2.74, p<.001), physical therapy intervention (PTI) (OR=2.66, p<.001), and practical examination (PE) (OR=1.24, p<.001). The cut-off points for each subject were: FPT, 32.50; DEPT, 29.50; PTI, 44.50; MR, 14.50; and PE, 50.50. The total score (TS) was 164.50. The sensitivity, specificity, and the classification accuracy of the prediction model was 99 %, 98 %, and 99 %, respectively, indicating high accuracy. Area under the curve (AUC) values for each subject were: FPT, .958; DEPT, .968; PTI, .984; MR, .885; PE, .962; and TS, .998, indicating a high degree of fit. Conclusion : In our study, the predictive factors for passing KPTLE were identified, and the optimal cut-off point was calculated for each subject. Logistic regression was adequate to explain the predictive model. These results will provide universities and examinees with useful information for predicting their success or failure in the KPTLE.

• Korean Journal of Radiology
• /
• 제22권3호
• /
• pp.435-441
• /
• 2021

Objective: To evaluate the usefulness of the ventricular volume percentage quantified using three-dimensional (3D) brain computed tomography (CT) data for interpreting serial changes in hydrocephalus. Materials and Methods: Intracranial and ventricular volumes were quantified using the semiautomatic 3D threshold-based segmentation approach for 113 brain CT examinations (age at brain CT examination ≤ 18 years) in 38 patients with hydrocephalus. Changes in ventricular volume percentage were calculated using 75 serial brain CT pairs (time interval 173.6 ± 234.9 days) and compared with the conventional assessment of changes in hydrocephalus (increased, unchanged, or decreased). A cut-off value for the diagnosis of no change in hydrocephalus was calculated using receiver operating characteristic curve analysis. The reproducibility of the volumetric measurements was assessed using the intraclass correlation coefficient on a subset of 20 brain CT examinations. Results: Mean intracranial volume, ventricular volume, and ventricular volume percentage were 1284.6 ± 297.1 cm³, 249.0 ± 150.8 cm³, and 19.9 ± 12.8%, respectively. The volumetric measurements were highly reproducible (intraclass correlation coefficient = 1.0). Serial changes (0.8 ± 0.6%) in ventricular volume percentage in the unchanged group (n = 28) were significantly smaller than those in the increased and decreased groups (6.8 ± 4.3% and 5.6 ± 4.2%, respectively; p = 0.001 and p < 0.001, respectively; n = 11 and n = 36, respectively). The ventricular volume percentage was an excellent parameter for evaluating the degree of hydrocephalus (area under the receiver operating characteristic curve = 0.975; 95% confidence interval, 0.948-1.000; p < 0.001). With a cut-off value of 2.4%, the diagnosis of unchanged hydrocephalus could be made with 83.0% sensitivity and 100.0% specificity. Conclusion: The ventricular volume percentage quantified using 3D brain CT data is useful for interpreting serial changes in hydrocephalus.

• Communications for Statistical Applications and Methods
• /
• 제14권1호
• /
• pp.169-182
• /
• 2007

Receive operating characteristic (ROC) approach can be employed to rank candidate genes from a microarray experiment, in particular, for the biomarker development with the purpose of population screening of a cancer. In the cancer microarray experiment based on n patients the researcher often wants to compare the tumor tissue with the normal tissue within the same individual using a common reference RNA. Ideally, this experiment produces n pairs of microarray data. However, it is often the case that there are missing values either in the normal or tumor tissue data. Practically, we have $n_1$ pairs of complete observations, $n_2$ "normal only" and $n_3$ "tumor only" data for the microarray. We refer to this data set as a mixed data set. We develop a ROC approach on the mixed data set to rank candidate genes for the biomarker development for the colorectal cancer screening. It turns out that the correlation between two ranks in terms of ROC and t statistics based on the top 50 genes of ROC rank is less than 0.6. This result indicates that employing a right approach of ranking candidate genes for the biomarker development is important for the allocation of resources.

• Journal of Preventive Medicine and Public Health
• /
• 제32권3호
• /
• pp.361-373
• /
• 1999

ROC곡선의 AUC는 측전도구의 기준 타당도를 나타내는 가장 일반화된 지표다. 본 연구는 ROC분석법을 이용하여 현행의 근로자건강진단에서 업무관련성 근골격계 질환의 고위험군을 변별하는 표준 설문지를 개발하고자 하였다. 컴퓨터를 이용하는 선박 설계업 종사자 89명, 전화번호 안내원 113명, 일반 직업 여성 79명, 주부 89명 등 총 370명의 일차 연구대상군에 대한 재활의 학과 전문의의 최종 진단결과를 기준으로 1996년에 개발된 '근로자의 신체 증상에 관한 설문지'의 응답결과를 비교하였다. 근골격계 질환과의 관련성이 높은 문항조합을 선정하고 문항별 가중치를 산출하기 위해 로짓회귀분석, 상관분석 등을 실시하였으며, 문항조합 및 가중치 산출방법이 서로 다른 4가지 설문모형에 따른 AUC를 비교 하였다. 또한, 국내 모 자동차조립공장 근로자 225명의 설문결과와 산업의학 전문의의 진단결과 자료를 이용하여 4가지 설문모형의 AUC 재현도를 확인하였다. 분석 결과, 통계적으로 유의 한 차이는 없었으나 문항수를 줄여도 문항별 응답수준별 가중치를 부여하면 AUC가 일관되게 증가함을 확인하였다. 증상문항 4개와 신체부위문항 7개를 통합한 11개 문항에 가중치를 부여하는 모형이 변별력, 재현도, 편의성 측면에서 우수한 것으로 나타나, 이를 기준으로 새로운 업무관련성 근골격계 질환 설문지를 설계할 수 있었다. 문항수가 적으면서도 타당도는 높은 설문지를 개발하고, 상대적인 비교평가에 쓰일 수 있는 정량적 가중치를 제시한 것이 본 연구의 주요성과라 할 수 있다. 본 연구는 전문의 사이의 진단기준 차이를 고려하지 못한 점, 다양한 인구집단에 적용할만한 절대적인 참고치를 제시하지 못한 점 등에서 한계가 있다. 그러나, '측정 도구의 정량적 타당도 검증을 통한 질병 감시용 도구 개발'이라는 본 연구의 기본 취지 및 접근방법은 향후 조직적인 질병 예방활동에 활용될 여지가 있을 것이다.

• Journal of Preventive Medicine and Public Health
• /
• 제38권3호
• /
• pp.276-282
• /
• 2005

Objectives : To evaluate the predictive validity of three scoring systems; the acute physiology and chronic health evaluation(APACHE) III, simplified acute physiology score(SAPS) II, and mortality probability model(MPM) II systems in critically ill patients. Methods : A concurrent and retrospective study conducted by collecting data on consecutive patients admitted to the intensive care unit(ICU) including surgical, medical and coronary care unit between January 1, 2004, and March 31, 2004. Data were collected on 348 patients consecutively admitted to the ICU(aged 16 years or older, no transfer, ICU stay at least 8 hours). Three models were analyzed using logistic regression. Discrimination was assessed using receiver operating characteristic(ROC) curves, sensitivity, specificity, and correct classification rate. Calibration was assessed using the Lemeshow-Hosmer goodness of fit H-statistic. Results : For the APACHE III, SAPS II and MPM II systems, the area under the receiver operating characterist ic(ROC) curves were 0.981, 0.978, and 0.941 respectively. With a predicted risk of 0.5, the sensitivities for the APACHE III, SAPS II, and MPM II systems were 81.1, 79.2 and 71.7%, the specificities 98.3, 98.6, and 98.3%, and the correct classification rates 95.7, 95.7, and 94.3%, respectively. The SAPS II and APACHE III systems showed good calibrations(chi-squared H=2.5838 p=0.9577 for SAPS II, and chi-squared H=4.3761 p=0.8217 for APACHE III). Conclusions : The APACHE III and SAPS II systems have excellent powers of mortality prediction, and calibration, and can be useful tools for the quality assessment of intensive care units(ICUs).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제7권11호
• /
• pp.2561-2576
• /
• 2013

The ship ad-hoc network (SANET) extends the coverage of the high data-rate terrestrial communications to the ships with the reduced cost in maritime communications. Cognitive radio (CR) has the ability of sensing the radio environment and dynamically reconfiguring the operating parameters, which can make SANET utilize the spectrum efficiently. However, due to the dynamic topology nature and no central entity for data fusion in SANET, the interference brought into the primary network caused by the hidden primary user requires to be carefully managed by a sort of decentralized cooperative spectrum sensing schemes. In this paper, we propose a self-weighted decentralized cooperative spectrum sensing (SWDCSS) scheme to solve such a problem. The analytical and simulation results show that the proposed SWDCSS scheme is reliable to detect the primary user in SANET. As a result, secondary network can efficiently utilize the spectrum band of primary network with little interference to primary network. Referring the complementary receiver operating characteristic (ROC) curves, we observe that with a given false alarm probability, our proposed algorithm reduces the missing probability by 27% than the traditional embedded spectrally agile radio protocol for evacuation (ESCAPE) algorithm in the best condition.