Identification of Secondary Crash Risk Factors using Penalized Logistic Regression Model

2019 ◽  
Vol 2673 (11) ◽  
pp. 901-914 ◽  
Author(s):  
Angela E. Kitali ◽  
Priyanka Alluri ◽  
Thobias Sando ◽  
Wensong Wu
Keyword(s):  
Logistic Regression ◽  
Regression Model ◽  
Real Time ◽  
Logistic Regression Model ◽  
Risk Model ◽  
Predictive Accuracy ◽  
Mitigation Strategies ◽  
Study Results ◽  
Highly Correlated ◽  
Penalized Logistic Regression

Secondary crashes (SCs) have increasingly been recognized as a major problem leading to reduced capacity and additional traffic delays. However, the limited knowledge on the nature and characteristics of SCs has largely impeded their mitigation strategies. There are two main issues with analyzing SCs. First, relevant variables are unknown, but, at the same time, most of the variables considered in the models are highly correlated. Second, only a small proportion of incidents results in SCs, making it an imbalanced classification problem. This study developed a reliable SC risk prediction model using the Least Absolute Shrinkage and Selection Operator (LASSO) penalized logistic regression model with Synthetic Minority Oversampling TEchnique-Nominal Continuous (SMOTE-NC). The proposed model is considered to improve the predictive accuracy of the SC risk model because it accounts for the asymmetric nature of SCs, performs variable selection, and removes highly correlated variables. The study data were collected on a 35-mi I-95 section for 3 years in Jacksonville, Florida. SCs were identified based on real-time speed data. The results indicated that real-time traffic variables and primary incident characteristics significantly affect the likelihood of SCs. The most influential variables included mean of detector occupancy, coefficient of variation of equivalent hourly volume, mean of speed, primary incident type, percentage of lanes closed, incident occurrence time, shoulder blocked, number of responding agencies, incident impact duration, incident clearance duration, and roadway alignment. The study results can be used by agencies to develop SC mitigation strategies, and therefore improve the operational and safety performance of freeways.

Relevance of Brain Regions’ Eloquence Assessment in Patients With a Large Ischemic Core Treated With Mechanical Thrombectomy

Neurology ◽  
2021 ◽  
pp. 10.1212/WNL.0000000000012863
Author(s):  
Basile Kerleroux ◽  
Joseph Benzakoun ◽  
Kévin Janot ◽  
Cyril Dargazanli ◽  
Dimitri Daly Eraya ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Random Forest ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Mechanical Thrombectomy ◽  
Predictive Accuracy ◽  
Unmet Need ◽  
C Statistic ◽  
Ischemic Core ◽  
Functional Relevance

ObjectiveIndividualized patient selection for mechanical thrombectomy (MT) in patients with acute ischemic stroke (AIS) and large ischemic core (LIC) at baseline is an unmet need.We tested the hypothesis, that assessing the functional relevance of both the infarcted and hypo-perfused brain tissue, would improve the selection framework of patients with LIC for MT.MethodsMulticenter, retrospective, study of adult with LIC (ischemic core volume > 70ml on MR-DWI), with MRI perfusion, treated with MT or best medical management (BMM).Primary outcome was 3-month modified-Rankin-Scale (mRS), favourable if 0-3. Global and regional-eloquence-based core-perfusion mismatch ratios were derived. The predictive accuracy for clinical outcome of eloquent regions involvement was compared in multivariable and bootstrap-random-forest models.ResultsA total of 138 patients with baseline LIC were included (MT n=96 or BMM n=42; mean age±SD, 72.4±14.4years; 34.1% females; mRS=0-3: 45.1%). Mean core and critically-hypo-perfused volume were 100.4ml±36.3ml and 157.6±56.2ml respectively and did not differ between groups. Models considering the functional relevance of the infarct location showed a better accuracy for the prediction of mRS=0-3 with a c-Statistic of 0.76 and 0.83 for logistic regression model and bootstrap-random-forest testing sets respectively. In these models, the interaction between treatment effect of MT and the mismatch was significant (p=0.04). In comparison in the logistic regression model disregarding functional eloquence the c-Statistic was 0.67 and the interaction between MT and the mismatch was insignificant.ConclusionConsidering functional eloquence of hypo-perfused tissue in patients with a large infarct core at baseline allows for a more precise estimation of treatment expected benefit.

Data Mining Medical Information

2011 ◽  
pp. 92-107
Author(s):  
Thomas Chesney ◽  
Kay Penny ◽  
Peter Oakley ◽  
Simon Davies ◽  
David Chesney ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Medical Information ◽  
Predictive Accuracy ◽  
Outcome Analysis ◽  
Audit Data ◽  
Patient Will ◽  
Artificial Neural Network Ann ◽  
Dissemination Of Results

Trauma audit is intended to develop effective care for injured patients through process and outcome analysis, and dissemination of results. The system records injury details such as the patient’s sex and age, the mechanism of the injury, various measures of the severity of the injury, initial management and subsequent management interventions, and the outcome of the treatment including whether the patient lived or died. Ten years’ worth of trauma audit data from one hospital are modelled as an Artificial Neural Network (ANN) in order to compare the results with a more traditional logistic regression analysis. The output was set to be the probability that a patient will die. The ANN models and the logistic regression model achieve roughly the same predictive accuracy, although the ANNs are more difficult to interpret than the logistic regression model, and neither logistic regression nor the ANNs are particularly good at predicting death. For these reasons, ANNs are not seen as an appropriate tool to analyse trauma audit data. Results do suggest, however, the usefulness of using both traditional and non-traditional analysis techniques together and of including as many factors in the analysis as possible.

Data Mining Medical Information

2011 ◽  
pp. 2218-2231
Author(s):  
Thomas Chesney ◽  
Kay Penny ◽  
Peter Oakley ◽  
Simon Davies ◽  
David Chesney ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Medical Information ◽  
Predictive Accuracy ◽  
Outcome Analysis ◽  
Audit Data ◽  
Patient Will ◽  
Artificial Neural Network Ann ◽  
Dissemination Of Results

Trauma audit is intended to develop effective care for injured patients through process and outcome analysis, and dissemination of results. The system records injury details such as the patient’s sex and age, the mechanism of the injury, various measures of the severity of the injury, initial management and subsequent management interventions, and the outcome of the treatment including whether the patient lived or died. Ten years’ worth of trauma audit data from one hospital are modelled as an Artificial Neural Network (ANN) in order to compare the results with a more traditional logistic regression analysis. The output was set to be the probability that a patient will die. The ANN models and the logistic regression model achieve roughly the same predictive accuracy, although the ANNs are more difficult to interpret than the logistic regression model, and neither logistic regression nor the ANNs are particularly good at predicting death. For these reasons, ANNs are not seen as an appropriate tool to analyse trauma audit data. Results do suggest, however, the usefulness of using both traditional and non-traditional analysis techniques together and of including as many factors in the analysis as possible.

scholarly journals LogSum + L2 penalized logistic regression model for biomarker selection and cancer classification

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Xiao-Ying Liu ◽  
Sheng-Bing Wu ◽  
Wen-Quan Zeng ◽  
Zhan-Jiang Yuan ◽  
Hong-Bo Xu
Keyword(s):  
Logistic Regression ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Cancer Classification ◽  
Classification Problems ◽  
Proposed Model ◽  
Different Types ◽  
Penalized Logistic Regression ◽  
Biomarker Selection

AbstractBiomarker selection and cancer classification play an important role in knowledge discovery using genomic data. Successful identification of gene biomarkers and biological pathways can significantly improve the accuracy of diagnosis and help machine learning models have better performance on classification of different types of cancer. In this paper, we proposed a LogSum + L2 penalized logistic regression model, and furthermore used a coordinate decent algorithm to solve it. The results of simulations and real experiments indicate that the proposed method is highly competitive among several state-of-the-art methods. Our proposed model achieves the excellent performance in group feature selection and classification problems.

scholarly journals Two Level Logistic Regression Model of Factors Influencing in Early Childbearing and its Consequences on Nutritional Status of Bangladeshi Mothers: Nationally Representative Data

2021 ◽  
Vol 10 ◽  
pp. 97-106
Author(s):  
Khirujjaman Sumon ◽  
Md. Abu Sayem ◽  
Abu Sayed Md. Al Mamun ◽  
Premananda Bharati ◽  
Suman Chakrabarty ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Nutritional Status ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Household Wealth ◽  
Medical Problem ◽  
Early Marriage ◽  
Early Childbearing ◽  
Modifiable Factors ◽  
Study Results

Background: Early marriage and early pregnancy is a social as well as a medical problem in developing countries, which may have an impact on the health and nutritional status of teenage mothers. Therefore, the objective of this study was to determine the influencing factors of early childbearing (ECB) and its consequences on the nutritional status of Bangladeshi mothers. Methods: Data was extracted from Bangladesh Demographic and Health Survey (BDHS-2014). Women who delivered their first baby before the age of 20 years are considered ECB mothers. Nutritional status was measured by body mass index (BMI). Chi-square test and both univariable and multivariable logistic regressions, and z-proportional test were used in this study. Results: The prevalence of ECB among currently non-pregnant mothers in Bangladesh was 83%. The logistic regression model provided the following six risk factors of ECB: (i) living location (division) (p<0.01), (ii) respondents’ education (p<0.05), (iii) husbands’ education (p<0.05), (iv) household wealth quintiles (p<0.01), (v) respondents’ age at first marriage (p<0.05), and (vi) number of family members (p<0.05). Still, 17.6% of mothers were undernourished in Bangladesh; among them, 18.5% and 13.4% were ECB and non- ECB mothers respectively. ECB mothers had a greater risk to be undernourished than non-ECB mothers [COR=1.26, 95% CI: 1.11-1.43; p<0.01]. Conclusions: In this study, some modifiable factors were found as predictors of ECB in Bangladesh. ECB mothers were more prone to become under-nourished. These findings can be considered to reduce the number of ECB mothers in Bangladesh consequently improve their nutritional status.

Study on Early Warning of Enterprise Financial Distress — Based on Partial Least-squares Logistic Regression

2015 ◽  
Vol 65 (s2) ◽  
pp. 3-16 ◽  
Author(s):  
Kun Xu ◽  
Qilan Zhao ◽  
Xinzhong Bao
Keyword(s):  
Logistic Regression ◽  
Regression Model ◽  
Least Squares ◽  
Partial Least Squares ◽  
Early Warning ◽  
Financial Distress ◽  
Logistic Model ◽  
Logistic Regression Model ◽  
Warning System ◽  
Study Results

Establishment of an effective early warning system can make the company operators make relevant decisions as soon as possible when finding the crisis, improve the operating results and financial condition of enterprise, and can also make investors avoid or reduce investment losses. This paper applies the partial least-squares logistic regression model for the analysis on early warning of enterprise financial distress in consideration of quite sensitive characteristics of common logistic model for the multicollinearity. The data of real estate industry listed companies in China are used to compare and analyze the early warning of financial distress by using the logistic model and the partial least-squares logistic model, respectively. The study results show that compared with the common logistic regression model, the applicability of partial least-squares logistic model is stronger due to its eliminating multicollinearity problem among various early warning indicators.

Does micronutrients intake modulate the risk of coronary heart disease?

2019 ◽  
Vol 49 (3) ◽  
pp. 368-380 ◽  
Author(s):  
Mohammed Azab ◽  
Abdel-Ellah Al-Shudifat ◽  
Lana Agraib ◽  
Sabika Allehdan ◽  
Reema Tayyem
Keyword(s):  
Coronary Heart Disease ◽  
Logistic Regression ◽  
Heart Disease ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Multinomial Logistic Regression ◽  
Daily Intake ◽  
Dietary Intakes ◽  
Content Type ◽  
Study Results

Purpose The purpose of this study was to examine the relationship between micronutrient intake and coronary heart disease (CHD) in middle-aged Jordanian participants. Design/methodology/approach A case-control study was conducted among patients referring for elective coronary angiography. A total of 400 patients were enrolled in this study. Face-to-face interview was used to complete food frequency questionnaire from which the authors derived usual daily intake of micronutrients. The mean age of participates was 52 years and their average BMI was 30.7 kg/m2. Multinomial logistic regression model and linear logistic regression model were used to calculate odd ratios (OR) and its 95 per cent confidence interval (CI) and p-value for trend, respectively. The association between the risk of CHD and micronutrients intake was adjusted for the age, gender, BMI, smoking, physical activity, total energy intake, occupation, education level, marital status and family history. Findings The study results showed no significant differences between cases and controls for dietary intakes of micronutrients, except for the intake of calcium (p < 0.005), magnesium (p < 0.025), phosphorus (p < 0.023) and potassium (p < 0.006) which were lower in cases than controls. Although no significant trend was observed between most of the dietary intake of micronutrients and the risk of developing CHD, a significant protective effect of magnesium [OR 0.52; 95 per cent CI (0.29-0.95)], phosphorus [OR 0.44; 95 per cent CI (0.24-0.80)] and potassium [OR 0.41; 95 per cent CI (0.22-0.74)] against the risk of CHD was detected. Originality/value The findings from this study provide strong evidence that the intake of micronutrients such as calcium, magnesium, phosphorus and potassium has no significant associations with the risk of CHD.

Sign in / Sign up

Export Citation Format

Share Document