• Geomechanics and Engineering
• /
• v.34 no.3
• /
• pp.267-284
• /
• 2023

Landslides are one of the most dangerous phenomena and natural disasters. Landslides cause many human and financial losses in most parts of the world, especially in mountainous areas. Due to the climatic conditions and topography, people in the northern and western regions of Iran live with the risk of landslides. One of the measures that can effectively reduce the possible risks of landslides and their crisis management is to identify potential areas prone to landslides through multi-criteria modeling approach. This research aims to model landslide potential area in the Oshvand watershed using a support vector machine algorithm. For this purpose, evidence maps of seven effective factors in the occurrence of landslides namely slope, slope direction, height, distance from the fault, the density of waterways, rainfall, and geology, were prepared. The maps were generated and weighted using the continuous fuzzification method and logistic functions, resulting values in zero and one range as weights. The weighted maps were then combined using the support vector machine algorithm. For the training and testing of the machine, 81 slippery ground points and 81 non-sliding points were used. Modeling procedure was done using four linear, polynomial, Gaussian, and sigmoid kernels. The efficiency of each model was compared using the area under the receiver operating characteristic curve; the root means square error, and the correlation coefficient . Finally, the landslide potential model that was obtained using Gaussian's kernel was selected as the best one for susceptibility of landslides in the Oshvand watershed.

• Journal of Preventive Medicine and Public Health
• /
• v.41 no.2
• /
• pp.107-114
• /
• 2008

Objectives : The aim of this study is to investigate the association between obesity indices(body mass index, weight, waist-hip ratio and waist circumference) in adolescents and the carotid intima-media thickness (C-IMT) in early adulthood. We also wanted to identify the best predictor for C-IMT among these obesity indices. Methods : This study used community-based prospective cohort study, known as the Kangwha Study, and the data we used were from subjects who were 16-years old in 1996 (defined as "adolescence") and 25 years-old in 2005 (defined as "early adulthood"). The 256 subjects (113 men and 143 women) who were used for analysis participated in both follow-ups, and they underwent B-mode ultrasonography of the carotid arteries at the early adulthood follow-up. Obesity indices were defined as the body mass index, weight, waist-hip ratio and waist circumference. The C-IMT was defined as the mean of the maximal IMT of each common carotid artery. The C-IMT and obesity indices associations were evaluated via multivariable regression, logistic regression and the receiver-operator characteristic curve analyses. Results : In men, all the obesity indices in adolescence were showed to have statistically significant positive association with C-IMT in early adulthood. However, no such relationship was showed in women. On multiple regression and logistic regression analysis, the waist-hip ratio showed the biggest relationship with the C-IMT among the 4 obesity indices. However, there were no statistical significant differences and no best predictor was found. For the women, the obesity incidences and C-IMT showed no relationships. Conclusions : This study suggested that obesity in adolescence was related to an increase C-IMT in healthy young Korean men.

• Journal of Trauma and Injury
• /
• v.22 no.2
• /
• pp.154-160
• /
• 2009

Purpose: This study aimed to determine new criteria for detecting independent factors with high sensitivity in cases of cervical spine injury. We compared the sensitivity, the specificity, and the false negative predictive value (NPV) of plain radiographs with those of computed tomography for cervical spine injury in patients with minor head injury. Methods: We retrospectively reviewed the cases of 357 patients who underwent both cervical plain radiographs and computer tomography from January 2006, to September 2008. Patients were divided into two groups: the cervical spine injury group and the no cervical spine injury group. New criteria were organized based on variables that had significant differences in the logistic regression test. Results: Among the 357 patients, 78 patients had cervical spine injuries. The average age was $43.9{\pm}15.2$ yrs old, and the male-to-female ratio was 1.90. The most common mechanism of injury was motor vehicle accidents. There was a significant difference in loss of consciousness, Glasgow Coma Scale (GCS)=14, neurologic deficit, posterior neck tenderness, and abnormality of the cervical plain radiographs between the two groups on the logistic regression test. New criteria included the above five variables. If a patient has at least variable, the area under the ROC curve of the new criteria was 0.850, and the sensitivity and the false NPV were 87.2% and 5.2%, respectively. Conclusion: New criteria included loss of consciousness, GCS=14, neurologic deficit, posterior neck tenderness, and abnormality of the cervical plain radiographs. If the patient had at least 1 variable, he or she could have a of cervical spine injury with a sensitivity of 87.2% and a false NPV of 5.2%.

• Journal of Trauma and Injury
• /
• v.35 no.1
• /
• pp.25-33
• /
• 2022

Purpose: The scoring system for traumatic liver injury (SSTLI) was developed in 2015 to predict mortality in patients with polytraumatic liver injury. This study aimed to validate the SSTLI as a prognostic factor in patients with polytrauma and liver injury through a generalized estimating equation analysis. Methods: The medical records of 521 patients with traumatic liver injury from January 2015 to December 2019 were reviewed. The primary outcome variable was in-hospital mortality. All the risk factors were analyzed using multivariate logistic regression analysis. The SSTLI has five clinical measures (age, Injury Severity Score, serum total bilirubin level, prothrombin time, and creatinine level) chosen based on their predictive power. Each measure is scored as 0-1 (age and Injury Severity Score) or 0-3 (serum total bilirubin level, prothrombin time, and creatinine level). The SSTLI score corresponds to the total points for each item (0-11 points). Results: The areas under the curve of the SSTLI to predict mortality on post-traumatic days 0, 1, 3, and 5 were 0.736, 0.783, 0.830, and 0.824, respectively. A very good to excellent positive correlation was observed between the probability of mortality and the SSTLI score (γ=0.997, P<0.001). A value of 5 points was used as the threshold to distinguish low-risk (<5) from high-risk (≥5) patients. Multivariate analysis using the generalized estimating equation in the logistic regression model indicated that the SSTLI score was an independent predictor of mortality (odds ratio, 1.027; 95% confidence interval, 1.018-1.036; P<0.001). Conclusions: The SSTLI was verified to predict mortality in patients with polytrauma and liver injury. A score of ≥5 on the SSTLI indicated a high-risk of post-traumatic mortality.

• Journal of Preventive Medicine and Public Health
• /
• v.55 no.3
• /
• pp.297-306
• /
• 2022

Objectives: The incidence of cardiovascular disease (CVD) mortality is increasing in developing countries. This study aimed to decompose the socioeconomic inequality of CVD in Iran. Methods: This cross-sectional population-based study was conducted on 20 519 adults who enrolled in the Ardabil Non-Communicable Disease cohort study. Principal component analysis and multivariable logistic regression were used, respectively, to estimate socioeconomic status and to describe the relationships between CVD prevalence and the explanatory variables. The relative concentration index, concentration curve, and Blinder-Oaxaca decomposition model were used to measure and decompose the socioeconomic inequality. Results: The overall age-adjusted prevalence of CVD was 8.4% in northwest Iran. Multivariable logistic regression showed that older adults, overweight or obese adults, and people with hypertension and diabetes were more likely to have CVD. Moreover, people with low economic status were 38% more likely to have CVD than people with high economic status. The prevalence of CVD was mainly concentrated among the poor (concentration index, -0.077: 95% confidence interval, -0.103 to -0.060), and 78.66% of the gap between the poorest and richest groups was attributed to differences in the distribution of the explanatory variables included in the model. Conclusions: The most important factors affecting inequality in CVD were old age, chronic illness (hypertension and diabetes), marital status, and socioeconomic status. This study documented stark inequality in the prevalence of CVD, wherein the poor were more affected than the rich. Therefore, it is necessary to implement policies to monitor, screen, and control CVD in poor people living in northwest Iran.

• Journal of the Korean Society of Radiology
• /
• v.11 no.3
• /
• pp.131-137
• /
• 2017

This study investigated the risk factor of Gallbladder stone in Busan and Kyungnam area. The subjects of the experiment was performed with patients by abdominal ultrasonography among the patients who came to the P hospital from June 2016 to December 2016. Among them, risk factors were analyzed on 353 people at the same time when abdominal ultrasonography and hematological test. The statistical analysis of risk factors related to the Gallbladder stone was performed by independent t-test and chi-square test. In consider of difference verification result for calculations odds ratio about independent variables, multiple logistic regression analysis to conduct verify adequacy by calculating forecasting model from variable. As a result, Gallbladder stone risk factors have relevance to age ${\gamma}GTP$ with probability model and values to calculated. Age was showed sensitivity 49.7%, specificity 82.2%, receiver operating characteristic area under curve 0.724. Forecasting probability sensitivity 69.3%, specificity 62.4%, receiver operating characteristic area under curve 0.699 showed, ${\gamma}GTP$ confirmed validity of forecasting model.

• Genomics & Informatics
• /
• v.17 no.4
• /
• pp.47.1-47.12
• /
• 2019

The achievements of genome-wide association studies have suggested ways to predict diseases, such as type 2 diabetes (T2D), using single-nucleotide polymorphisms (SNPs). Most T2D risk prediction models have used SNPs in combination with demographic variables. However, it is difficult to evaluate the pure additive contribution of genetic variants to classically used demographic models. Since prediction models include some heritable traits, such as body mass index, the contribution of SNPs using unmatched case-control samples may be underestimated. In this article, we propose a method that uses propensity score matching to avoid underestimation by matching case and control samples, thereby determining the pure additive contribution of SNPs. To illustrate the proposed propensity score matching method, we used SNP data from the Korea Association Resources project and reported SNPs from the genome-wide association study catalog. We selected various SNP sets via stepwise logistic regression (SLR), least absolute shrinkage and selection operator (LASSO), and the elastic-net (EN) algorithm. Using these SNP sets, we made predictions using SLR, LASSO, and EN as logistic regression modeling techniques. The accuracy of the predictions was compared in terms of area under the receiver operating characteristic curve (AUC). The contribution of SNPs to T2D was evaluated by the difference in the AUC between models using only demographic variables and models that included the SNPs. The largest difference among our models showed that the AUC of the model using genetic variants with demographic variables could be 0.107 higher than that of the corresponding model using only demographic variables.

• Korean Journal of Applied Biomechanics
• /
• v.31 no.1
• /
• pp.1-15
• /
• 2021

Objective: The aim of this study was to investigate 1) the difference in static lower extremity alignment (SLEA) according to a history of lateral ankle sprain (LAS), 2) to identify SLEA factors affecting LAS, and 3) to present the cut-off value and 4) the usefulness and limitations of the SLEA measurement. Method: This case-control study recruited 88 men (age: 27.78±4.69 yrs) and 39 women (age: 24.62±4.20 yrs) subjects with and without LAS. SLEA measurement protocol included Q angle, tibiofemoral angle, genu recurvatum, rear foot (RF) angle, tibal varum and torsion, navicular drop, ankle dorsiflexion range of motion (DF ROM). Independent t-test, logistic regression and receiver operating characteristic (ROC) curve were used for statistical analysis. Results: Men with a history of LAS had significantly smaller Q angles both in standing and in supine position, while women with a history of LAS had significantly greater DF ROM in non-weight bearing (NWB; p < 0.05). Logistic regression model suggests tibial varum (OR = 0.779, p = 0.021) and WB DF ROM (OR = 1.067, p = 0.045) were associated with LAS in men. In case of women, there were no significant SLEA factors for LAS, however, ROC curve analysis revealed standing RF angle (AUC = 0.647, p = 0.028) and NWB DF ROM (AUC = 0.648, p = 0.026) could be affecting factors for LAS. Conclusion: There are differences in SLEA according to the history of LAS, furthermore, the identified items were different by sex. In case of men, tibial varum and WB DF ROM affect LAS occurrence. Standing RF angle and NWB DF ROM of women could be a predictor for LAS. However, since the sensitivity and specificity in most of the SLEA measurements are low, kinematic in dynamic tasks should be considered together for a more accurate evaluation of LAS risk.

• Journal of Biomedical Engineering Research
• /
• v.33 no.3
• /
• pp.148-154
• /
• 2012

Hemorrhagic shock is a primary cause of deaths resulting from injury in the world. Although many studies have tried to diagnose accurately hemorrhagic shock in the early stage, such attempts were not successful due to compensatory mechanisms of humans. The objective of this study was to construct a survival prediction model of rats in acute hemorrhagic shock using a random forest (RF) model. Heart rate (HR), mean arterial pressure (MAP), respiration rate (RR), lactate concentration (LC), and peripheral perfusion (PP) measured in rats were used as input variables for the RF model and its performance was compared with that of a logistic regression (LR) model. Before constructing the models, we performed 5-fold cross validation for RF variable selection, and forward stepwise variable selection for the LR model to examine which variables were important for the models. For the LR model, sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (ROC-AUC) were 0.83, 0.95, 0.88, and 0.96, respectively. For the RF models, sensitivity, specificity, accuracy, and AUC were 0.97, 0.95, 0.96, and 0.99, respectively. In conclusion, the RF model was superior to the LR model for survival prediction in the rat model.

• Journal of Korean Neurosurgical Society
• /
• v.59 no.5
• /
• pp.478-484
• /
• 2016

Objective : To assess the clinical and radiological factors as predictors for successful outcomes in lumbar disc herniation (LDH) treatment. Methods : Two groups of patients with single level LDH (L4-5) requiring treatment were retrospectively studied. The surgery group (SG) included 34 patients, and 30 patients who initially refused the surgery were included in the nerve blocks group (NG). A visual analogue scale (VAS) for leg and back pain and motor deficit were initially evaluated before procedures, and repeated at 1, 6, and 12 months. Radiological factors including the disc herniation length, disc herniation area, canal length-occupying ratio, and canal area-occupying ratio were measured and compared. Predicting factors of successful outcomes were determined with multivariate logistic regression analysis after the optimal cut off values were established with a receiver operating characteristic curve. Results : There was no significant demographic difference between two groups. A multivariate logistic regression analysis with radiological and clinical (12 months follow-up) data revealed that the high disc herniation length with cutoff value 6.31 mm [odds ratio (OR) 2.35; confidence interval (CI) 1.21-3.98] was a predictor of successful outcomes of leg pain relief in the SG. The low disc herniation length with cutoff value 6.23 mm (OR 0.05; CI 0.003-0.89) and high baseline VAS leg (OR 12.63; CI 1.64-97.45) were identified as predictors of successful outcomes of leg pain relief in the NG. Conclusion : The patients with the disc herniation length larger than 6.31 mm showed successful outcomes with surgery whereas the patients with the disc herniation length less than 6.23 mm showed successful outcomes with nerve block. These results could be considered as a radiological criteria in choosing optimal treatment options for LDH.