• Title/Summary/Keyword: receiver operating characteristics (ROC)

Search Result 99, Processing Time 0.122 seconds

Bayesian Model for the Classification of GPCR Agonists and Antagonists

  • Choi, In-Hee;Kim, Han-Jo;Jung, Ji-Hoon;Nam, Ky-Youb;Yoo, Sung-Eun;Kang, Nam-Sook;No, Kyoung-Tai
    • Bulletin of the Korean Chemical Society
    • /
    • v.31 no.8
    • /
    • pp.2163-2169
    • /
    • 2010
  • G-protein coupled receptors (GPCRs) are involved in a wide variety of physiological processes and are known to be targets for nearly 50% of drugs. The various functions of GPCRs are affected by their cognate ligands which are mainly classified as agonists and antagonists. The purpose of this study is to develop a Bayesian classification model, that can predict a compound as either human GPCR agonist or antagonist. Total 6627 compounds experimentally determined as either GPCR agonists or antagonists covering all the classes of GPCRs were gathered to comprise the dataset. This model distinguishes GPCR agonists from GPCR antagonists by using chemical fingerprint, FCFP_6. The model revealed distinctive structural characteristics between agonistic and antagonistic compounds: in general, 1) GPCR agonists were flexible and had aliphatic amines, and 2) GPCR antagonists had planar groups and aromatic amines. This model showed very good discriminative ability in general, with pretty good discriminant statistics for the training set (accuracy: 90.1%) and a good predictive ability for the test set (accuracy: 89.2%). Also, receiver operating characteristic (ROC) plot showed the area under the curve (AUC) to be 0.957, and Matthew's Correlation Coefficient (MCC) value was 0.803. The quality of our model suggests that it could aid to classify the compounds as either GPCR agonists or antagonists, especially in the early stages of the drug discovery process.

MicroRNAs as Promising Biomarkers for Tumor-staging: Evaluation of MiR21 MiR155 MiR29a and MiR92a in Predicting Tumor Stage of Rectal Cancer

  • Yang, Yun;Peng, Wei;Tang, Tian;Xia, Lin;Wang, Xiao-Dong;Duan, Bao-Feng;Shu, Ye
    • Asian Pacific Journal of Cancer Prevention
    • /
    • v.15 no.13
    • /
    • pp.5175-5180
    • /
    • 2014
  • Objective: In this study, tumor-stage predictive abilities of miR21, miR155, miR29a and miR92a were evaluated in rectal cancer (RC). Methods: Expression of miR21, miR155, miR29a and miR92a was detected and quantitated in tumor tissue and in adjacent normal tissue from 40 patients by TaqMan MicroRNA assay. Results: Significant overexpression of miR21, miR155, miR29a and miR92a was observed in RC tissues. While high expression of miR21, miR155 and miR29a in N1-2 and C-D stages presented a potential correlation with N and Duke stages, partial correlation analysis suggested that only miR155 rather than miR21 and miR29a played a greater influencing role. Receiver operating characteristics (ROC) curve analysis showed that miR155 could discriminate N0 from N1-2 with 85.0% sensitivity and 85.0% specificity, N2 from N0-1 with 90.0% sensitivity and 96.7% specificity, and C-D stage from A-B stage with 81.0% sensitivity and 84.2% specificity. Conclusions: Increase in expression of miR155 might represent a novel predictor for RC N and Dukes staging.

Comparison of nomograms designed to predict hypertension with a complex sample (고혈압 예측을 위한 노모그램 구축 및 비교)

  • Kim, Min Ho;Shin, Min Seok;Lee, Jea Young
    • The Korean Journal of Applied Statistics
    • /
    • v.33 no.5
    • /
    • pp.555-567
    • /
    • 2020
  • Hypertension has a steadily increasing incidence rate as well as represents a risk factors for secondary diseases such as cardiovascular disease. Therefore, it is important to predict the incidence rate of the disease. In this study, we constructed nomograms that can predict the incidence rate of hypertension. We use data from the Korean National Health and Nutrition Examination Survey (KNHANES) for 2013-2016. The complex sampling data required the use of a Rao-Scott chi-squared test to identify 10 risk factors for hypertension. Smoking and exercise variables were not statistically significant in the Logistic regression; therefore, eight effects were selected as risk factors for hypertension. Logistic and Bayesian nomograms constructed from the selected risk factors were proposed and compared. The constructed nomograms were then verified using a receiver operating characteristics curve and calibration plot.

Validation of Adult Fall Assessment Scale Korean Version for Adult Patients in General Hospitals in Korea (한국형 낙상 위험 사정도구의 타당성 평가연구)

  • Choi, Eun Hee;Ko, Mi Suk;Lee, Shin Ae;Park, Jung Ha
    • Journal of Korean Clinical Nursing Research
    • /
    • v.26 no.2
    • /
    • pp.265-273
    • /
    • 2020
  • Purpose: The purpose of this study was to test the predictive validity of the Fall Assessment Scale-Korean version (FAS-K) and to find the most appropriate cutoff score to screen high-risk fall groups in adult patients in general hospitals in Korea. Methods: We performed a prospective evaluation study in medical and surgical ward patients at two major general hospitals in Seoul. Data were collected from Nov. 1, 2018 to Feb. 28, 2019, nurses performed 651 observation series. The researcher measured the fall risk assessment score by applying FAS-K, MFS (Morse Fall Scale), and JHFRAT (Johns Hopkins Hospital Fall Risk Assessment tool) to the patients twice a week between 10 am and 12 noon. Data were analyzed using Pearson's corelation coefficients, and the sensitivity, specificity, predictive value, and the area under the curve (AUC) of the three tools. Results: The FAS-K was positively correlated with the MFS (r=.70, p<.001) and the JHFRAT (r=.82, p<.001). According to the receiver operating characteristics (ROC) curve analysis of the FAS-K, sensitivity, specificity, and positive and negative prediction values were 85.3%, 49.4%, 8.5%, and 98.4%, respectively, when the FAS-K score was 4. Therefore, the cut-off score of the FAS-K to identify groups with high fall risk was 4. Conclusion: The FAS-K is a valid tool for measuring fall risk in adult inpatients. In addition, the FAS-K score, 4, can be used to identify high-risk fall groups and know specific points in time to provide active interventions to prevent falls.

The prognostic value of median nerve thickness in diagnosing carpal tunnel syndrome using magnetic resonance imaging: a pilot study

  • Lee, Sooho;Cho, Hyung Rae;Yoo, Jun Sung;Kim, Young Uk
    • The Korean Journal of Pain
    • /
    • v.33 no.1
    • /
    • pp.54-59
    • /
    • 2020
  • Background: The median nerve cross-sectional area (MNCSA) is a useful morphological parameter for the evaluation of carpal tunnel syndrome (CTS). However, there have been limited studies investigating the anatomical basis of median nerve flattening. Thus, to evaluate the connection between median nerve flattening and CTS, we carried out a measurement of the median nerve thickness (MNT). Methods: Both MNCSA and MNT measurement tools were collected from 20 patients with CTS, and from 20 control individuals who underwent carpal tunnel magnetic resonance imaging (CTMRI). We measured the MNCSA and MNT at the level of the hook of hamate on CTMRI. The MNCSA was measured on the transverse angled sections through the whole area. The MNT was measured based on the most compressed MNT. Results: The mean MNCSA was 9.01 ± 1.94 ㎟ in the control group and 6.58 ± 1.75 ㎟ in the CTS group. The mean MNT was 2.18 ± 0.39 mm in the control group and 1.43 ± 0.28 mm in the CTS group. Receiver operating characteristics curve analysis demonstrated that the optimal cut-off value for the MNCSA was 7.72 ㎟, with 75.0% sensitivity, 75.0% specificity, and an area under the curve (AUC) of 0.82 (95% confidence interval [CI], 0.69-0.95). The best cut off-threshold of the MNT was 1.76 mm, with 85% sensitivity, 85% specificity, and an AUC of 0.94 (95% CI, 0.87-1.00). Conclusions: Even though both MNCSA and MNT were significantly associated with CTS, MNT was identified as a more suitable measurement parameter.

Relationships of the Vitamin D and Platelet Indices in Sjögren's Syndrome

  • Gunay, Nahide Ekici;Bugday, Irfan;Akalin, Tayfun
    • Korean Journal of Clinical Laboratory Science
    • /
    • v.50 no.4
    • /
    • pp.484-491
    • /
    • 2018
  • Primer $Sj{\ddot{o}}gren's$ Syndrome (pSS) is an autoimmune/inflammatory illness. The platelet indices (PIs) indicate the inflammatory response and activity/severity of many diseases. A vitamin D deficiency is accompanied by the increased tendency of autoimmune diseases. This study investigated whether the vitamin D levels are related to the altered platelet indices in pSS. A total of 261 individuals were included in this analytical cross-sectional study. The laboratory data of pSS patients were evaluated and the relationship between the PIs and vitamin D status was examined. According to these findings, in patients with pSS, the vitamin D levels were lower than the healthy control group (P<0.05). The vitamin D levels were negatively associated with PDW (P=0.012), but positively correlated with PCT (P<0.001). The cut-off point was obtained with receiver operating characteristics (ROC) curves for PDW: 12.53 (AUC 0.921, sensitivity 90%, specificity 85%), for PCT; 0.29 (AUC 0.660, sensitivity 68%, specificity 55%). In multivariate linear regression analysis, the most significant parameters for the effects of PDW are the following: vitamin D (${\beta}=-0.373$; t=-2.626; sig.=0.013) and plateletcrit (${\beta}=-0.308$; t=-2.13; sig.=0.040). A vitamin D deficiency may be accompanied by changes in PIs in pSS. A higher PDW and lower PCT supports the underlying inflammation, which may be vitamin D related useful parameters to consider in approaching to pSS.

Nomogram building to predict dyslipidemia using a naïve Bayesian classifier model (순수 베이지안 분류기 모델을 사용하여 이상지질혈증을 예측하는 노모 그램 구축)

  • Kim, Min-Ho;Seo, Ju-Hyun;Lee, Jea-Young
    • The Korean Journal of Applied Statistics
    • /
    • v.32 no.4
    • /
    • pp.619-630
    • /
    • 2019
  • Dyslipidemia is a representative chronic disease affecting Koreans that requires continuous management. It is also a known risk factor for cardiovascular disease such as hypertension and diabetes. However, it is difficult to diagnose vascular disease without a medical examination. This study identifies risk factors for the recognition and prevention of dyslipidemia. By integrating them, we construct a statistical instrumental nomogram that can predict the incidence rate while visualizing. Data were from the Korean National Health and Nutrition Examination Survey (KNHANES) for 2013-2016. First, a chi-squared test identified twelve risk factors of dyslipidemia. We used a naïve Bayesian classifier model to construct a nomogram for the dyslipidemia. The constructed nomogram was verified using a receiver operating characteristics curve and calibration plot. Finally, we compared the logistic nomogram previously presented with the Bayesian nomogram proposed in this study.

Evaluation of Risk Factors for Uterine Myoma Diagnosed by Ultrasonography (초음파로 진단된 자궁근종의 위험인자 평가)

  • Yang, Sung-Hee
    • Journal of radiological science and technology
    • /
    • v.44 no.4
    • /
    • pp.307-313
    • /
    • 2021
  • The purpose of this study was to analyze the risk factors for uterine myoma diagnosed by ultrasonography in Korea women and to evaluate the risk. Among the patients who visited the outpatient department of obstetrics and gynecology at I hospital in Busin between January 2019 and March 2021 for the purpose of examination, 98 patients in the experimental group diagnosed with uterine myoma and 163 patients in the normal control group without other diseases were retrospectively conducted. Among the general characteristics of the subjects, age, body mass index, parity, and menopause showed significant differences between the myoma group and the normal control group. ROC(receiver operating characteristic) curve analysis and logistic regression analysis were performed to obtain the cut off value and odds ratio that can predict the occurrence of uterine myoma. The cut off value for the prediction of uterine myoma was determined to be 30 years old and a body mass index of 23 kg/m2. After that adjusting for menopause, non menopausal cases with a body mass index of 23 kg/m2 and over 39 years of age had the highest odds ratio of 6.04. Therefore, premenopausal women over 40 years of age require regular checkups and thorough weight management. This study was conducted with a small number of subjects. Therefore, there is a limit to generalizing to all Korean women. However, based on this study if a large scale prospective study considering various variables is made, it can play a role as a predictive marker in early detection of uterine myoma.

Assessment of Parameters Measured with Volumetric Pulmonary Artery Catheter as Predictors of Fluid Responsiveness in Patients with Coronary Artery Occlusive Disease (관상동맥 질환을 가진 환자에서 폐동맥카테터로 측정한 전부하 지표들은 수액부하 반응을 예상할 수 있는가?)

  • Lee, Ji-Yeon;Lee, Jong-Hwa;Shim, Jae-Kwang;Yoo, Kyung-Jong;Hong, Seung-Bum;Kwak, Young-Lan
    • Journal of Chest Surgery
    • /
    • v.41 no.1
    • /
    • pp.41-48
    • /
    • 2008
  • Background: Accurate assessment of the preload and the fluid responsiveness is of great importance for optimizing cardiac output, especially in those patients with coronary artery occlusive disease (CAOD). In this study, we evaluated the relationship between the parameters of preload with the changes in the stroke volume index (SVI) after fluid loading in patients who were undergoing coronary artery bypass grafting (CABG). The purpose of this study was to find the predictors of fluid responsiveness in order to assess the feasibility of using. certain parameters of preload as a guide to fluid therapy. Material and Method: We studied 96 patients who were undergoing CABG. After induction of anesthesia, the hemodynamic parameters were measured before (T1) and 10 min after volume replacement (T2) by an infusion of 6% hydroxyethyl starch 130/0.4 (10 mL/kg) over 20 min. Result: The right ventricular end-diastolic volume index (RVEDVI), as well as the central venous pressure (CVP) and pulmonary capillary wedge pressure (PCWP), failed to demonstrate significant correlation with the changes in the SVI (%). Only the right ventricular ejection fraction (RVEF) measured at T1 showed significant correlation. with the changes of the SVI by linear regression (r=0.272, p=0.017). However, when the area under the curve of receiver operating characteristics (ROC) was evaluated, none of the parameters were over 0.7. The volume-induced increase in the SVI was 10% or greater in 31 patients (responders) and under 10% in 65 patients (non-responders). None of the parameters of preload measured at T1 showed a significant difference between the responders and non-responders, except for the RVEF. Conclusion: The conventional parameters measured with a volumetric pulmonary artery catheter failed to predict the response of SVI following fluid administration in patients suffering with CAOD.

Diagnostic Significance of TNF-$\alpha$ in Tuberculous and Non-Tuberculous Pleural Effusion (결핵성 및 비결핵성 흉막삼출액에서 TNF-$\alpha$ 농도의 진단적 의의)

  • Na, Hyun-Joo;Park, Seog-Chea;Kang, Kwang-Won;Park, Hyeong-Kwan;Kim, Young-Chul;Choi, In-Seon;Park, Kyung-Ok
    • Tuberculosis and Respiratory Diseases
    • /
    • v.44 no.3
    • /
    • pp.611-620
    • /
    • 1997
  • Objectives : The differentiation of tuberculous effusion from the other causes of exudative pleural effusion remained difficult even with aids of biochemical analyses and pleural biopsy. As the pathophysiology of tuberculous pleural effusion is an enhanced cell mediated immunity, Adenosine deaminase(ADA) and various eytokines including Inteferon-$\gamma$, tumor necrosis factor alpha(TNF-$\alpha$) are considered as useful diagnostic tools in differentiating exudative pleural effusion. The author would like to demonstrate the diagnostic usefulness of TNF-$\alpha$ in the differentiation of exudative pleural effusion, and compared the discriminating ability of TNF-$\alpha$ with ADA. Methods : Pleural fluids obtained from 80 patients (tuberculous : 39, malignant : 31, parapneumonic : 10) with exudate pleural effusions were processed for cell counts and biochemical analysis including ADA and TNF-$\alpha$. Results : Tuberculous pleural fluid showed higher levels of ADA and TNF-$\alpha$, $48.7{\pm}32.7U/L$ and $184.1{\pm}214.2pg/mL$ than that of non-tuberculous effusion $26.0{\pm}41.3U/L$ and $44.1{\pm}114.2pg/mL$, respectively (ADA, TNF-$\alpha$, p < 0.05, p < 0.01). Receiver operating characteristics(ROC) curves were generated for ADA and TNF-$\alpha$ and the best cut-off value for adenosine deaminase and TNF-$\alpha$were considered as 30U/L and 15pg/ml, respectively. Comparing the area under the ROC curves, there was no significant difference between ADA and TNF-$\alpha$. Conclusion : For the differential diagnosis of tuberculous pleural effusion from the other causes of exudative pleural effusions, TNF-$\alpha$ as well as ADA was considered as useful diagnostic method. However adding TNF-$\alpha$ to ADA has no further diagnotic benefit than ADA alone.

  • PDF