• Title, Summary, Keyword: logistic curve

Search Result 253, Processing Time 0.068 seconds

Analysis of Hematological Factor to Predict Plaque of the Carotid Artery in Ultrasound Images (경동맥초음파에서 죽상경화반을 예측하는 혈액학적 수치의 분석)

  • Yang, Sung Hee;Kang, Se Sik;Lee, Jinsoo
    • Journal of the Korean Society of Radiology
    • /
    • v.10 no.3
    • /
    • pp.187-193
    • /
    • 2016
  • In this study, we performed the carotid artery ultrasound targeting 140 subjects who have conducted to evaluate the changes in intima-media thickness(IMT) and plaque correlated with the presence or absence of a hematological test of the carotid artery. Considering that the IMT thickness more than 1mm is abnormal based on the carotid artery ultrasound to assess the presence or absence of plaque, and examined the correlation by classifying the blood lipid value and the fasting blood glucose level through the serum test. Consequently, the fasting blood glucose level is being analyzed as independent predictors of causing dental plaque(p=0.033), cut off value was determined as 126 mg/dL(sensitivity 56.25%, specificity 68.38%) in ROC curve analysis. Furthermore, the odds ratio appeared 1.01 times the value in the Logistic regression. Therefore, it seemed that the necessity to prospective studies in a number of subjects are considered, and also taking into account a number of blood test values along with the sonography of the carotid artery as a valuable part for effective primary prevention and follow-up observation of the cardiac and brain vascular disease is highly recommended.

Presence of Carotid Plaque Is Associated with Rapid Renal Function Decline in Patients with Type 2 Diabetes Mellitus and Normal Renal Function

  • Seo, Da Hea;Kim, So Hun;Song, Joon Ho;Hong, Seongbin;Suh, Young Ju;Ahn, Seong Hee;Woo, Jeong-Taek;Baik, Sei Hyun;Park, Yongsoo;Lee, Kwan Woo;Kim, Young Seol;Nam, Moonsuk
    • Diabetes and Metabolism Journal
    • /
    • v.43 no.6
    • /
    • pp.840-853
    • /
    • 2019
  • Background: Recent evidences indicate that early rapid renal function decline is closely associated with the development and progression of diabetic kidney disease. We have investigated the association between carotid atherosclerosis and rapid renal function decline in patients with type 2 diabetes mellitus and preserved renal function. Methods: In a prospective, multicenter cohort, a total of 967 patients with type 2 diabetes mellitus and preserved renal function were followed for 6 years with serial estimated glomerular filtration rate (eGFR) measurements. Common carotid intima-media thickness (CIMT) and presence of carotid plaque were assessed at baseline. Rapid renal function decline was defined as an eGFR decline >3.3% per year. Results: Over a median follow-up of 6 years, 158 participants (16.3%) developed rapid renal function decline. While there was no difference in CIMT, the presence of carotid plaque in rapid decliners was significantly higher than in non-decliners (23.2% vs. 12.2%, P<0.001). In multivariable logistic regression analysis, presence of carotid plaque was an independent predictor of rapid renal function decline (odds ratio, 2.33; 95% confidence interval, 1.48 to 3.68; P<0.0001) after adjustment for established risk factors. The model including the carotid plaque had better performance for discrimination of rapid renal function decline than the model without carotid plaque (area under the receiver operating characteristic curve 0.772 vs. 0.744, P=0.016). Conclusion: Close monitoring of renal function and early intensive management may be beneficial in patients with type 2 diabetes mellitus and carotid plaques.

Productivity and Density Control of Stands of Japanese Larch (일본잎갈나무 임분(林分)의 생산력(生產力)과 밀도관리(密度管理)에 관(關)한 연구(硏究))

  • Ma, Sang Kyu
    • Journal of Korean Society of Forest Science
    • /
    • v.34 no.1
    • /
    • pp.21-30
    • /
    • 1977
  • Japanese larch (Larix leptolepis) is one of main timber species in Korea that could find much plantation and growing stands on all over the country. It is thought to be in meaningful that a guiding diagram for density control of Japanese larch stands is made to estimate easily the density conditions in the quantitaive, ecological and economic viewpoint. Sample plots for this study are selected from the stands that have not been thinned in recent years, and mean height, mean diameter, dominant height, tree numbers per hectare and stem volume of mean tree are calculated from the each sample plots among total 165 plots In this study, especially, the theory of slenderness of mean tree are applied, that have been identified through the results of the spacing trial. Relative growth characteristics of this species are calculated from the general logistic curve and its formula is $Y=ax^b$. Relatwion between the measured items are found out as follows: 1. Relation between the mean height and tree numbers per hectare by slender class is showing the high correlation as table 1 and fig. 2, and between mean diameter and tree numbers per hectare is also high correlation as table 1 and fig 3. 2. The stem volume can be correctly estimated from height in case that slender class may be known, as showing in table 3 and fig. 4. 3. The stem volume can be more correctly estimated from the relation with $D^2H$ as formula, $Log_e\;V=0.9569\;Log_eD^2H-9.8431$, and relation between stem volume of single tree or volume per hectare and tree numbers per hectare are as following formulas: $Log_e$ stem volume=9.5026-1.6800 $Log_e$ tree numbers per hectare $Log_e$ stem volume per hectare=9.4911-0.6784 $Log_e$ tree numbers per hectare. Stem volume of mean tree, tree numbers per hectare and stem volume per hectare correspond to the mean tree height are calculated to slender class as table 5, 6, 7. Through the above steps, the diagram for density control of Japanese larch are produced as fig. 9. It is thought that this diagram could be applied to control the density of Japanese larch stands.

  • PDF

Stand Growth Estimation Using Nonlinear Growth Equations (비선형(非線型) 생장함수(生長函數)를 이용(利用)한 임분생장(林分生長) 추정(推定))

  • Son, Yeong Mo;Lee, Kyeong Hak;Chung, Young Gyo
    • Journal of Korean Society of Forest Science
    • /
    • v.86 no.2
    • /
    • pp.135-145
    • /
    • 1997
  • This study aimed at evaluating one curvilinear equation and nine non-linear equations for estimating stand growth characteristics(mean dbh, mean height and volume per ha) for the plantations of Pinus koraiensis and the natural stands of Quercus mongolica. The data were collected from 92 plots in Pines koraiensis stands and 83 plots in Quercus mongolica stands, and the site index of all the stands is 14. The curvilinear equation, $Y=at^be^{-c/t}$, used in preparing the yield tables was well fitted within the range of data, but was likely to give overestimates when extrapolating in old stage due to the tendency of linear increase. Among the non-linear equations, logistic equation and Sloboda equation gave overestimates in young stands and reached the asymptotic status early which means underestimates in old stage. Extrapolating in old stage, Hossfeld equation generally gave larger values than others due to its large estimates of parameter a, the maximum value. On the other hand, Bertalanffy equation gave underestimates in young and old stands and overestimates in middle-aged stands. The estimates with Korf equation was relatively low for Pinus koraiensis stands, and this tendency was more obvious in dbh growth of Quercus mongolica stands. Ueno-Ohzaki equation was liable to give over or underestimates depending on the value of parameter b when extrapolating in old stands. Considering the accuracy of estimates and the biological base of the growth equations, Gompertz equation, Chapman-Richards equation and Weibull equation were generally applicable for estimating the stand growth characteristics of both species in the whole range of stand ages including extrapolated range. To get more accurate and precise parameter estimates, more data, especially in old stands, should be required in further study.

  • PDF

Differentiation of True Recurrence from Delayed Radiation Therapy-related Changes in Primary Brain Tumors Using Diffusion-weighted Imaging, Dynamic Susceptibility Contrast Perfusion Imaging, and Susceptibility-weighted Imaging (확산강조영상, 역동적조영관류영상, 자화율강조영상을 이용한 원발성 뇌종양환자에서의 종양재발과 지연성 방사선치료연관변화의 감별)

  • Kim, Dong Hyeon;Choi, Seung Hong;Ryoo, Inseon;Yoon, Tae Jin;Kim, Tae Min;Lee, Se-Hoon;Park, Chul-Kee;Kim, Ji-Hoon;Sohn, Chul-Ho;Park, Sung-Hye;Kim, Il Han
    • Investigative Magnetic Resonance Imaging
    • /
    • v.18 no.2
    • /
    • pp.120-132
    • /
    • 2014
  • Purpose : To compare dynamic susceptibility contrast imaging, diffusion-weighted imaging, and susceptibility-weighted imaging (SWI) for the differentiation of tumor recurrence and delayed radiation therapy (RT)-related changes in patients treated with RT for primary brain tumors. Materials and Methods: We enrolled 24 patients treated with RT for various primary brain tumors, who showed newly appearing enhancing lesions more than one year after completion of RT on follow-up MRI. The enhancing-lesions were confirmed as recurrences (n=14) or RT-changes (n=10). We calculated the mean values of normalized cerebral blood volume (nCBV), apparent diffusion coefficient (ADC), and proportion of dark signal intensity on SWI (proSWI) for the enhancing-lesions. All the values between the two groups were compared using t-test. A multivariable logistic regression model was used to determine the best predictor of differential diagnosis. The cutoff value of the best predictor obtained from receiver-operating characteristic curve analysis was applied to calculate the sensitivity, specificity, and accuracy for the diagnosis. Results: The mean nCBV value was significantly higher in the recurrence group than in the RT-change group (P=.004), and the mean proSWI was significantly lower in the recurrence group (P<.001). However, no significant difference was observed in the mean ADC values between the two groups. A multivariable logistic regression analysis showed that proSWI was the only independent variable for the differentiation; the sensitivity, specificity, and accuracy were 78.6% (11 of 14), 100% (10 of 10), and 87.5% (21 of 24), respectively. Conclusion: The proSWI was the most promising parameter for the differentiation of newly developed enhancing-lesions more than one year after RT completion in brain tumor patients.

Association between Sleep Duration, Dental Caries, and Periodontitis in Korean Adults: The Korea National Health and Nutrition Examination Survey, 2013~2014 (한국 성인에서 수면시간과 영구치 우식증 및 치주질환과의 관련성: 2013~2014 국민건강영양조사)

  • Lee, Da-Hyun;Lee, Young-Hoon
    • Journal of dental hygiene science
    • /
    • v.17 no.1
    • /
    • pp.38-45
    • /
    • 2017
  • We evaluated the association between sleep duration, dental caries, and periodontitis by using representative nationwide data. We examined 8,356 subjects aged ${\geq}19$ years who participated in the sixth Korea National Health and Nutrition Examination Survey (2013~2014). Sleep duration were grouped into ${\leq}5$, 6, 7, 8, and ${\geq}9$ hours. Presence of dental caries was defined as caries in ${\geq}1$ permanent tooth on dental examination. Periodontal status was assessed by using the community periodontal index (CPI), and a CPI code of ${\geq}3$ was defined as periodontitis. A chi-square test and multiple logistic regression analysis were used to determine statistical significance. Model 1 was adjusted for age and sex, model 2 for household income, educational level, and marital status plus model 1, and model 3 for smoking status, alcohol consumption, blood pressure level, fasting blood glucose level, total cholesterol level, and body mass index plus model 2. The prevalence of dental caries according to sleep duration showed a U-shaped curve of 33.4%, 29.4%, 28.4%, 29.4%, and 31.8% with ${\leq}5$, 6, 7, 8, and ${\geq}9$ hours of sleep, respectively. In the fully adjusted model 3, the risk of developing dental caries was significantly higher with ${\leq}5$ than with 7 hours of sleep (odds ratio, 1.23; 95% confidence interval, 1.06~1.43). The prevalence of periodontitis according to sleep duration showed a U-shaped curve of 34.4%, 28.6%, 28.1%, 31.3%, and 32.5%, respectively. The risk of periodontitis was significantly higher with ${\geq}9$ than with 7 hours of sleep in models 1 and 2, whereas the significant association disappeared in model 3. In a nationally representative sample, sleep duration was significantly associated with dental caries formation and weakly associated with periodontitis. Adequate sleep is required to prevent oral diseases such as dental caries and periodontitis.

The Prognostic Role of B-type Natriuretic Peptide in Acute Exacerbation of Chronic Obstructive Pulmonary Disease (만성폐쇄성폐질환의 급성 악화시 예후 인자로서의 혈중 B-type Natriuretic Peptide의 역할)

  • Lee, Ji Hyun;Oh, So Yeon;Hwang, Iljun;Kim, Okjun;Kim, Hyun Kuk;Kim, Eun Kyung;Lee, Ji-Hyun
    • Tuberculosis and Respiratory Diseases
    • /
    • v.56 no.6
    • /
    • pp.600-610
    • /
    • 2004
  • Background : The plasma B-type natriuretic peptide(BNP) concentration increases with the degree of pulmonary hypertension in patients with chronic respiratory disease. The aim of this study was to examine the prognostic role of BNP in the acute exacerbation of chronic obstructive lung disease (COPD). Method : We selected 67 patients who were admitted our hospital because of an acute exacerbation of COPD. Their BNP levels were checked on admission at the Emergency Department. Their medical records were analyzed retrospectively. The patients were divided into two groups according to their in-hospital mortality. The patients' medical history, comobidity, exacerbation type, blood gas analysis, pulmonary function, APACHE II severity score and plasma BNP level were compared. Results : Multiple logistic regression analysis identified three independent predictors of mortality: $FEV_1$, APACHE II score and plasma BNP level. The decedents group showed a lower $FEV_1$($28{\pm}7$ vs. $37{\pm}15%$, p=0.005), a higher APACHE II score($22.4{\pm}6.1$ vs. $15.8{\pm}4.7$, p=0.000) and a higher BNP level ($201{\pm}116$ vs. $77{\pm}80pg/mL$, p=0.000) than the sSurvivors group. When the BNP cut-off level was set to 88pg/mL using the receiver operating characteristic curve, the sensitivity was 90% and the specificity was 75% in differentiating between the survivors and decedents. On Fisher's exact test, the odds ratio for mortality was 21.2 (95% CI 2.49 to 180.4) in the patients with a BNP level > 88pg/mL. Conclusion : The plasma BNP level might be a predictor of mortality in an acute exacerbation of COPD as well as the $FEV_1$ and APACHE II score.

Correlation between Carotid Intima-media Thickness and Risk Factors for Atherosclerosis (경동맥 내중막 두께에 따른 죽상경화반의 위험요인과의 상관관계)

  • An, Hyun;Lee, Hyo Yeong
    • Journal of the Korean Society of Radiology
    • /
    • v.13 no.3
    • /
    • pp.339-348
    • /
    • 2019
  • The purpose of this study was to investigate the effect of carotid artery ultrasound Respectively. The carotid intima-media thickness is known to have a significant correlation with cardiovascular disease and cerebrovascular disease. We investigated the relationship between carotid intima - media thickness, body mass index, waist circumference, the blood lipid value, fasting blood glucose, glycated hemoglobin, and blood pressure using carotid artery ultrasound. The carotid artery ultrasound was considered to be abnormality of IMT thickness over 0.8 mm and the presence or absence of atherosclerotic plaque was evaluated. Serological tests were used to compare the geologic value, fasting blood glucose level, and glycated hemoglobin. As a result, waist circumference (=.022), low density cholesterol (=.004), fasting blood glucose level (.019), and glycemic index (.002) were analyzed as predictors of atherosclerosis. In the ROC curve analysis, sensitivity was 87.80% (95% CI: 73.8-95.9), specificity was 41.67% (95% CI: 30.2-53.9), sensitivity was 78.05% (95% CI: 62.4-89.4) in low density lipoprotein, Specificity was 50.00% (95% CI: 38.0-62.0), sensitivity was 73.11% (95% CI: 57.1-85.8), specificity was 61.11 (95% CI: 48.9-72.4) and sensitivity was 82.93%-91.8) and a specificity of 43.06% (31.4-55.3). In logistic regression analysis, the risk of atherosclerosis was 0.248 times at waist circumference (WC)> 76 cm, 3.475 times at low-density lipoprotein (LDL-C) ${\geq}124mg/dL$, 0.618 at HbA1c> 5.4% It appeared as a times. We suggest that prospective study of carotid artery ultrasound should be performed for the effective prevention of cardiovascular diseases.

Comparison of Deep Learning Frameworks: About Theano, Tensorflow, and Cognitive Toolkit (딥러닝 프레임워크의 비교: 티아노, 텐서플로, CNTK를 중심으로)

  • Chung, Yeojin;Ahn, SungMahn;Yang, Jiheon;Lee, Jaejoon
    • Journal of Intelligence and Information Systems
    • /
    • v.23 no.2
    • /
    • pp.1-17
    • /
    • 2017
  • The deep learning framework is software designed to help develop deep learning models. Some of its important functions include "automatic differentiation" and "utilization of GPU". The list of popular deep learning framework includes Caffe (BVLC) and Theano (University of Montreal). And recently, Microsoft's deep learning framework, Microsoft Cognitive Toolkit, was released as open-source license, following Google's Tensorflow a year earlier. The early deep learning frameworks have been developed mainly for research at universities. Beginning with the inception of Tensorflow, however, it seems that companies such as Microsoft and Facebook have started to join the competition of framework development. Given the trend, Google and other companies are expected to continue investing in the deep learning framework to bring forward the initiative in the artificial intelligence business. From this point of view, we think it is a good time to compare some of deep learning frameworks. So we compare three deep learning frameworks which can be used as a Python library. Those are Google's Tensorflow, Microsoft's CNTK, and Theano which is sort of a predecessor of the preceding two. The most common and important function of deep learning frameworks is the ability to perform automatic differentiation. Basically all the mathematical expressions of deep learning models can be represented as computational graphs, which consist of nodes and edges. Partial derivatives on each edge of a computational graph can then be obtained. With the partial derivatives, we can let software compute differentiation of any node with respect to any variable by utilizing chain rule of Calculus. First of all, the convenience of coding is in the order of CNTK, Tensorflow, and Theano. The criterion is simply based on the lengths of the codes and the learning curve and the ease of coding are not the main concern. According to the criteria, Theano was the most difficult to implement with, and CNTK and Tensorflow were somewhat easier. With Tensorflow, we need to define weight variables and biases explicitly. The reason that CNTK and Tensorflow are easier to implement with is that those frameworks provide us with more abstraction than Theano. We, however, need to mention that low-level coding is not always bad. It gives us flexibility of coding. With the low-level coding such as in Theano, we can implement and test any new deep learning models or any new search methods that we can think of. The assessment of the execution speed of each framework is that there is not meaningful difference. According to the experiment, execution speeds of Theano and Tensorflow are very similar, although the experiment was limited to a CNN model. In the case of CNTK, the experimental environment was not maintained as the same. The code written in CNTK has to be run in PC environment without GPU where codes execute as much as 50 times slower than with GPU. But we concluded that the difference of execution speed was within the range of variation caused by the different hardware setup. In this study, we compared three types of deep learning framework: Theano, Tensorflow, and CNTK. According to Wikipedia, there are 12 available deep learning frameworks. And 15 different attributes differentiate each framework. Some of the important attributes would include interface language (Python, C ++, Java, etc.) and the availability of libraries on various deep learning models such as CNN, RNN, DBN, and etc. And if a user implements a large scale deep learning model, it will also be important to support multiple GPU or multiple servers. Also, if you are learning the deep learning model, it would also be important if there are enough examples and references.

Dynamic forecasts of bankruptcy with Recurrent Neural Network model (RNN(Recurrent Neural Network)을 이용한 기업부도예측모형에서 회계정보의 동적 변화 연구)

  • Kwon, Hyukkun;Lee, Dongkyu;Shin, Minsoo
    • Journal of Intelligence and Information Systems
    • /
    • v.23 no.3
    • /
    • pp.139-153
    • /
    • 2017
  • Corporate bankruptcy can cause great losses not only to stakeholders but also to many related sectors in society. Through the economic crises, bankruptcy have increased and bankruptcy prediction models have become more and more important. Therefore, corporate bankruptcy has been regarded as one of the major topics of research in business management. Also, many studies in the industry are in progress and important. Previous studies attempted to utilize various methodologies to improve the bankruptcy prediction accuracy and to resolve the overfitting problem, such as Multivariate Discriminant Analysis (MDA), Generalized Linear Model (GLM). These methods are based on statistics. Recently, researchers have used machine learning methodologies such as Support Vector Machine (SVM), Artificial Neural Network (ANN). Furthermore, fuzzy theory and genetic algorithms were used. Because of this change, many of bankruptcy models are developed. Also, performance has been improved. In general, the company's financial and accounting information will change over time. Likewise, the market situation also changes, so there are many difficulties in predicting bankruptcy only with information at a certain point in time. However, even though traditional research has problems that don't take into account the time effect, dynamic model has not been studied much. When we ignore the time effect, we get the biased results. So the static model may not be suitable for predicting bankruptcy. Thus, using the dynamic model, there is a possibility that bankruptcy prediction model is improved. In this paper, we propose RNN (Recurrent Neural Network) which is one of the deep learning methodologies. The RNN learns time series data and the performance is known to be good. Prior to experiment, we selected non-financial firms listed on the KOSPI, KOSDAQ and KONEX markets from 2010 to 2016 for the estimation of the bankruptcy prediction model and the comparison of forecasting performance. In order to prevent a mistake of predicting bankruptcy by using the financial information already reflected in the deterioration of the financial condition of the company, the financial information was collected with a lag of two years, and the default period was defined from January to December of the year. Then we defined the bankruptcy. The bankruptcy we defined is the abolition of the listing due to sluggish earnings. We confirmed abolition of the list at KIND that is corporate stock information website. Then we selected variables at previous papers. The first set of variables are Z-score variables. These variables have become traditional variables in predicting bankruptcy. The second set of variables are dynamic variable set. Finally we selected 240 normal companies and 226 bankrupt companies at the first variable set. Likewise, we selected 229 normal companies and 226 bankrupt companies at the second variable set. We created a model that reflects dynamic changes in time-series financial data and by comparing the suggested model with the analysis of existing bankruptcy predictive models, we found that the suggested model could help to improve the accuracy of bankruptcy predictions. We used financial data in KIS Value (Financial database) and selected Multivariate Discriminant Analysis (MDA), Generalized Linear Model called logistic regression (GLM), Support Vector Machine (SVM), Artificial Neural Network (ANN) model as benchmark. The result of the experiment proved that RNN's performance was better than comparative model. The accuracy of RNN was high in both sets of variables and the Area Under the Curve (AUC) value was also high. Also when we saw the hit-ratio table, the ratio of RNNs that predicted a poor company to be bankrupt was higher than that of other comparative models. However the limitation of this paper is that an overfitting problem occurs during RNN learning. But we expect to be able to solve the overfitting problem by selecting more learning data and appropriate variables. From these result, it is expected that this research will contribute to the development of a bankruptcy prediction by proposing a new dynamic model.