Landslide Geo-Hazard Risk Mapping Using Logistic Regression Modeling in Guixi, Jiangxi, China

Reliable prediction of landslide occurrence is important for hazard risk reduction and prevention. Taking Guixi in northeast Jiangxi as an example, this research aimed to conduct such a landslide risk assessment using a multiple logistic regression (MLR) algorithm. Field-investigated landslides and non-landslide sites were converted into polygons. We randomly generated 50,000 sampling points to intersect these polygons and the intersected points were divided into two parts, a training set (TS) and a validation set (VT) in a ratio of 7 to 3. Thirteen geo-environmental factors, including elevation, slope, and distance from roads were employed as hazard-causative factors, which were intersected by the TS to create the random point (RP)-based dataset. The next step was to compute the certainty factor (CF) of each factor to constitute a CF-based dataset. MLR was applied to the two datasets for landslide risk modeling. The probability of landslides was then calculated in each pixel, and risk maps were produced. The overall accuracy of these two models versus VS was 91.5% and 90.4% with a Kappa coefficient of 0.814 and 0.782, respectively. The RP-based MLR modeling achieved more reliable predictions and its risk map seems more plausible for providing technical support for implementing disaster prevention measures in Guixi.

Download Full-text

Mapping Landslide Hazard Risk Using Random Forest Algorithm in Guixi, Jiangxi, China

ISPRS International Journal of Geo-Information ◽

10.3390/ijgi9110695 ◽

2020 ◽

Vol 9 (11) ◽

pp. 695

Author(s):

Yang Zhang ◽

Weicheng Wu ◽

Yaozu Qin ◽

Ziyu Lin ◽

Guiliang Zhang ◽

...

Keyword(s):

Human Life ◽

Landslide Hazard ◽

Landslide Risk ◽

Disaster Prevention ◽

Risk Modeling ◽

Prevention Measures ◽

Training Set ◽

Hazard Risk ◽

Calculated Probability ◽

Validation Set

Landslide hazards affect the security of human life and property. Mapping the spatial distribution of landslide hazard risk is critical for decision-makers to implement disaster prevention measures. This study aimed to predict and zone landslide hazard risk, using Guixi County in eastern Jiangxi, China, as an example. An integrated dataset composed of 21 geo-information layers, including lithology, rainfall, altitude, slope, distances to faults, roads and rivers, and thickness of the weathering crust, was used to achieve the aim. Non-digital layers were digitized and assigned weights based on their landslide propensity. Landslide locations and non-risk zones (flat areas) were both vectorized as polygons and randomly divided into two groups to create a training set (70%) and a validation set (30%). Using this training set, the Random Forests (RF) algorithm, which is known for its accurate prediction, was applied to the integrated dataset for risk modeling. The results were assessed against the validation set. Overall accuracy of 91.23% and Kappa Coefficient of 0.82 were obtained. The calculated probability for each pixel was consequently graded into different zones for risk mapping. Hence, we conclude that landslide risk zoning using the RF algorithm can serve as a pertinent reference for local government in their disaster prevention and early warning measures.

Download Full-text

Landslide risk zoning in Ruijin, Jiangxi, China

10.5194/nhess-2020-270 ◽

2020 ◽

Cited By ~ 1

Author(s):

Xiaoting Zhou ◽

Weicheng Wu ◽

Ziyu Lin ◽

Guiliang Zhang ◽

Renxiang Chen ◽

...

Keyword(s):

Environmental Data ◽

Landslide Risk ◽

Human Society ◽

Training Set ◽

Linear Feature ◽

Causative Factors ◽

Machine Learning Approach ◽

Weathered Crust ◽

Efficient Machine ◽

Validation Set

Abstract. Landslides are one of the major geohazards threatening human society. This study was aimed at conducting such a hazard risk prediction and zoning based on an efficient machine learning approach, Random Forest (RF), for Ruijin, Jiangxi, China. Multiple geospatial and geo-environmental data such as land cover, NDVI, landform, rainfall, stratigraphic lithology, proximity to faults, to roads and to rivers, depth of the weathered crust, etc., were utilized in this research. After pre-processing, including digitization, linear feature buffering and value assignment, 19 hazard-causative factors were eventually produced and converted into raster to constitute a 19-band geo-environmental dataset. 155 observed landslides that had truly taken places in the past 10 years were utilized to establish a vector layer. 70 % of the disaster sites (points) were randomly selected to compose a training set (TS) and the remained 30 % to form a validation set (VS). A number of non-risk samples were identified in low slope (

Download Full-text

Endoscopic third ventriculostomy in the treatment of childhood hydrocephalus in Uganda: report of a scoring system that predicts success

Journal of Neurosurgery Pediatrics ◽

10.3171/2009.9.peds09196 ◽

2010 ◽

Vol 5 (2) ◽

pp. 143-148 ◽

Cited By ~ 94

Author(s):

Benjamin C. Warf ◽

John Mugamba ◽

Abhaya V. Kulkarni

Keyword(s):

Logistic Regression ◽

Regression Model ◽

Logistic Regression Model ◽

Endoscopic Third Ventriculostomy ◽

Successful Outcome ◽

Third Ventriculostomy ◽

P Value ◽

Training Set ◽

Childhood Hydrocephalus ◽

Validation Set

Object In Uganda, childhood hydrocephalus is common and difficult to treat. In some children, endoscopic third ventriculostomy (ETV) can be successful and avoid dependence on a shunt. This can be especially beneficial in Uganda, because of the high risk of infection and long-term failure associated with shunting. Therefore, the authors developed and validated a model to predict the chances of ETV success, taking into account the unique characteristics of a large sub-Saharan African population. Methods All children presenting with hydrocephalus at CURE Children's Hospital of Uganda (CCHU) between 2001 and 2007 were offered ETV as first-line treatment and were prospectively followed up. A multivariable logistic regression model was built using ETV success at 6 months as the outcome. The model was derived on 70% of the sample (training set) and validated on the remaining 30% (validation set). Results Endoscopic third ventriculostomy was attempted in 1406 patients. Of these, 427 were lost to follow-up prior to 6 months. In the remaining 979 patients, the ETV was aborted in 281 due to poor anatomy/visibility and in 310 the ETV failed during the first 6 months. Therefore, a total of 388 of 979 (39.6% and [55.6% of completed ETVs]) procedures were successful at 6 months. The mean age at ETV was 12.6 months, and 57.8% of cases were postinfectious in origin. The authors' logistic regression model contained the following significant variables: patient age at ETV, cause of hydrocephalus, and whether choroid plexus cauterization was performed. In the training set (676 patients) and validation set (303 patients), the model was able to accurately predict the probability of successful ETV (Hosmer-Lemeshow p value > 0.60 and C statistic > 0.70). The authors developed the simplified CCHU ETV Success Score that can be used in the field to predict the probability of ETV success. Conclusions The authors' model will allow clinicians to accurately identify children with a good chance of successful outcome with ETV, taking into account the unique characteristics and circumstances of the Ugandan population.

Download Full-text

A nomogram based on pretreatment CT radiomics features for predicting complete response to chemoradiotherapy in patients with esophageal squamous cell cancer

10.21203/rs.3.rs-41188/v2 ◽

2020 ◽

Author(s):

Hesan Luo ◽

Shao-Fu Huang ◽

Hong-Yao Xu ◽

Xu-Yuan Li ◽

Sheng-Xi Wu ◽

...

Keyword(s):

Logistic Regression ◽

Squamous Cell ◽

Cell Cancer ◽

Complete Response ◽

Clinical Staging ◽

Training Set ◽

Simple Method ◽

Validation Set ◽

The Impact ◽

Radiomics Signature

Abstract Purpose: To develop and validate a nomogram model to predict complete response (CR) after concurrent chemoradiotherapy (CCRT) in esophageal squamous cell carcinoma (ESCC) patients using pretreatment CT radiomic features. Methods: Data of patients diagnosed as ESCC and treated with CCRT in Shantou Central Hospital during the period from January 2013 to December 2015 were retrospectively collected. Eligible patients were included in this study and randomize divided into a training set and a validation set after successive screening. The least absolute shrinkage and selection operator (LASSO) with logistic regression to select radiomics features calculating Rad-score in the training set. The logistic regression analysis was performed to identify the predictive clinical factors for developing a nomogram model. The area under the receiver operating characteristic curves (AUC) was used to assess the performance of the predictive nomogram model and decision curve was used to analyze the impact of the nomogram model on clinical treatment decisions. Results: A total of 226 patients were included and randomly divided into two groups, 160 patients in training set and 66 patients in validation set. After LASSO analysis, seven radiomics features were screened out to develop a radiomics signature Rad-score. The AUC of Rad-score was 0.812 (95%CI: 0.742-0.869, p<0.001) in the training set and 0.744 (95%CI: 0.632-0.851, p=0.003) in the validation set. Multivariate analysis showed that Rad-score and clinical staging were independent predictors of CR status, with P values of 0.035 and 0.023, respectively. A nomogram model incorporating Rad-socre and clinical staging was developed and validated, with an AUC of 0.844 (95％CI: 0.779-0.897) in the training set and 0.807 (95％CI: 0.691-0.894) in the validation set．Delong test showed that the nomogram model was significantly superior to the clinical staging, with P<0.001 in the training set and P=0.026 in the validation set. The decision curve showed that the nomogram model was superior to the clinical staging when the risk threshold was greater than 25%. Conclusion: We developed and validated a nomogram model for predicting CR status of ESCC patients after CCRT. The nomogram model was combined radiomics signature Rad-score and clinical staging. This model provided us with an economical and simple method for evaluating the response of chemoradiotherapy for patients with ESCC.

Download Full-text

A nomogram based on pretreatment CT radiomics features for predicting complete response to chemoradiotherapy in patients with esophageal squamous cell cancer

10.21203/rs.3.rs-41188/v1 ◽

2020 ◽

Author(s):

Hesan Luo ◽

Shao-Fu Huang ◽

Hong-Yao Xu ◽

Xu-Yuan Li ◽

Sheng-Xi Wu ◽

...

Keyword(s):

Logistic Regression ◽

Squamous Cell ◽

Cell Cancer ◽

Complete Response ◽

Clinical Staging ◽

Training Set ◽

Simple Method ◽

Validation Set ◽

The Impact ◽

Radiomics Signature

Abstract Purpose To develop and validate a nomogram model to predict complete response (CR) after concurrent chemoradiotherapy (CCRT) in esophageal squamous cell carcinoma (ESCC) patients using pretreatment CT radiomic features. Methods Data of patients diagnosed as ESCC and treated with CCRT in Shantou Central Hospital during the period from January 2013 to December 2015 were retrospectively collected. Eligible patients were included in this study and randomize divided into a training set and a validation set after successive screening. The least absolute shrinkage and selection operator (LASSO) with logistic regression to select radiomics features calculating Rad-score in the training set. The logistic regression analysis was performed to identify the predictive clinical factors for developing a nomogram model. The area under the receiver operating characteristic curves (AUC) was used to assess the performance of the predictive nomogram model and decision curve was used to analyze the impact of the nomogram model on clinical treatment decisions. Results A total of 226 patients were included and randomly divided into two groups, 160 patients in training set and 66 patients in validation set. After LASSO analysis, seven radiomics features were screened out to develop a radiomics signature Rad-score. The AUCs of Rad-score was 0.812 (95%CI: 0.742–0.869) in the training set and 0.744 (95%CI: 0.632–0.851) in the validation set. Multivariate analysis showed that Rad-score and clinical staging were independent predictors of CR status, with P values of 0.035 and 0.023, respectively. A nomogram model incorporating Rad-socre and clinical staging was developed and validated, with an AUC of 0.844 (95%CI: 0.779–0.897) in the training set and 0.807 (95༅CI: 0.691–0.894) in the validation set༎Delong test showed that the nomogram model was significantly superior to the clinical staging, with P < 0.001 in the training set and P = 0.026 in the validation set. The decision curve showed that the nomogram model was superior to the clinical staging when the risk threshold was greater than 25%. Conclusion We developed and validated a nomogram model for predicting CR status of ESCC patients after CCRT. The nomogram model was combined radiomics signature Rad-score and clinical staging. This model provided us with an economical and simple method for evaluating the response of chemoradiotherapy for patients with ESCC.

Download Full-text

A Nomogram Based on Clinical Characteristics for Predicting Multiple Organ Dysfunction Syndrome(MODS) Following Multiple Trauma Patients

10.21203/rs.3.rs-78104/v1 ◽

2020 ◽

Author(s):

ZhenJun Miao ◽

Faxing Wei ◽

Feng Zhou

Keyword(s):

Logistic Regression ◽

Multiple Trauma ◽

Clinical Characteristics ◽

Area Under The Curve ◽

Trauma Patients ◽

Multivariate Logistic Regression ◽

Training Set ◽

Lemeshow Test ◽

Validation Set ◽

Multiple Trauma Patients

Abstract BackgroundMultiple organ dysfunction syndrome (MODS) is the one of common complications,and the leading cause of late mortality in multiple trauma patients.The present study aims to develop and validate a nomogram based on clinical characteristics in order to identify the patients with multiple trauma who were at risk of developing MODS.MethodsAn retrospective cohort study was performed with data from January 2011 to December 2019,totally 770 patients with multiple trauma were enrolled in our study.They were randomly categorized into training set (n=514) and validation set (n=256).The univariate and multivariate logistic regression analyses were used to screen the predictors for multiple trauma patients who were at risk of developing MODS from training set data.Then we established a nomogram based on these above predictors.The discriminative capacity was assessed by receiver operating characteristic (ROC) curve area under the curve (AUC), and the predictive precision was depicted by calibration plot.The Hosmer-Lemeshow test was used to evaluate the the model’s goodness of fit.ResultsOur study showed that age,ISS,hemorrhagic shock,heart rate,blood glucose,D-dimer and APTT were independent risk factors for MODS in patients with multiple trauma by multivariate logistic regression analysis.A nomogram was established on basis of these above risk factors.The area under the curve (AUC) was 0.868 (95% confidence interval [CI]:0.829-0.908) in the training set and 0.884 (95% confidence interval [CI]:0.833-0.935) in the validation set.The Hosmer-Lemeshow test has a p value of 0.227 in training set and 0.554 in validation set respectively,which confirm the model’s goodness of fit.Calibration plot showed that the predicted and actual incidence of MODS probability were fitted well on both internal and external validations.ConclusionsThe present nomogram had a well predictive precision and discrimination capacity,which can facilitate improved screening and early identification of multiple trauma patients who were at high risk of developing MODS.

Download Full-text

Factors Defining the Development of Severe Illness in Patients with COVID-19: A Single-Center, Retrospective, Observational Study

10.21203/rs.3.rs-137222/v1 ◽

2020 ◽

Author(s):

Xiong Yibai ◽

Tian Yaxin ◽

Liu Bin ◽

Ruan Lianguo ◽

Lu Cheng ◽

...

Keyword(s):

Risk Factors ◽

Logistic Regression ◽

Lactate Dehydrogenase ◽

Critical Illness ◽

Observational Study ◽

Risk Score ◽

Severe Illness ◽

Single Center ◽

Training Set ◽

Validation Set

Abstract Objective Early triage of patients with coronavirus disease 2019 (COVID-19) is pivotal in managing the disease. However, data on the risk factors for the development of severe disease remains scant. Here, we report a clinical risk score system for severe illness and highlight possible protective factors, which might inform proper treatment strategies.Methods We conducted a retrospective, single-center, observational study at the JinYinTan Hospital from January 24,2020 to March 31, 2020. We evaluated the demographic, clinical, and laboratory data and performed a 3-fold cross-validation to split the data into training set and validation set. We then screened the prognostic factors for severe illness using the Least Absolute Shrinkage and Selection Operator (LASSO) and logistic regression, and finally conducted a risk score to estimate the probability of critical illness in the training set. Data from the validation set were used to validate the score. Furthermore, the clinical factors of those patients who recovered were compared with those who did not recover from the rapidly worsened illness. We then employed logistic regression tools to delineate the possible protective factors.Results A total of 302 patients were included. From 47 potential risk factors, 6 variables were measured as the risk score: sex(female) (OR, 0.372; 95%CI, 0.211-0.655), Chest Computed Tomography abnormality (OR, 1.90; 95%CI, 1.36-2.66), neutrophil value (OR, 1.33; 95%CI, 1.18-1.50), neutrophil to lymphocyte ratio (OR, 1.23; 95%CI, 1.14-1.34), lactate dehydrogenase (OR, 1.01; 95%CI, 1.006-1.012), albumin (OR, 0.77; 95%CI, 0.71-0.84). The mean AUC of development cohort was 0.82 (95% CI, 0.81-0.92) and the AUC of validation cohort was 0.894 (95% CI, 0.78-0.95). Our comparison data from patients who rapidly worsened but recovered with those who did not showed that 4 variables were predictive factors: Prealbumin (OR, 1.028; 95%CI, 1.010-1.057), percentage of lymphocytes (OR, 1.213; 95%CI, 1.062-1.385), lactate dehydrogenase (OR, 0.984; 95%CI, 0.973-0.996), Prothrombin ativity (OR, 1.065; 95%CI, 1.018-1.115).Conclusion and Relevance In this study, we developed a predictive risk score and highlight 4 factors that might predict recovery from suddenly worsened illness. This report may help define the potential of developing critical illness and recovery prospects in patients with rapidly worsened condition.

Download Full-text

Preoperative Evaluation of Perineural Invasion in Cervical Cancer: Development and Independent Validation of a Novel Predictive Nomogram

Frontiers in Oncology ◽

10.3389/fonc.2021.774459 ◽

2021 ◽

Vol 11 ◽

Author(s):

Ting Wan ◽

Guangyao Cai ◽

Shangbin Gao ◽

Yanling Feng ◽

He Huang ◽

...

Keyword(s):

Cervical Cancer ◽

Logistic Regression ◽

Cancer Patients ◽

Perineural Invasion ◽

Preoperative Evaluation ◽

False Negative ◽

Multivariate Logistic Regression ◽

Training Set ◽

Surgical Strategies ◽

Validation Set

BackgroundPerineural invasion (PNI) is associated with a poor prognosis for cervical cancer and influences surgical strategies. However, a preoperative evaluation that can determine PNI in cervical cancer patients is lacking.MethodsAfter 1:1 propensity score matching, 162 cervical cancer patients with PNI and 162 cervical cancer patients without PNI were included in the training set. Forty-nine eligible patients were enrolled in the validation set. The PNI-positive and PNI-negative groups were compared. Multivariate logistic regression was performed to build the PNI prediction nomogram.ResultsAge [odds ratio (OR), 1.028; 95% confidence interval (CI), 0.999–1.058], adenocarcinoma (OR, 1.169; 95% CI, 0.675–2.028), tumor size (OR, 1.216; 95% CI, 0.927–1.607), neoadjuvant chemotherapy (OR, 0.544; 95% CI, 0.269–1.083), lymph node enlargement (OR, 1.953; 95% CI, 1.086–3.550), deep stromal invasion (OR, 1.639; 95% CI, 0.977–2.742), and full-layer invasion (OR, 5.119; 95% CI, 2.788–9.799) were integrated in the PNI prediction nomogram based on multivariate logistic regression. The PNI prediction nomogram exhibited satisfactory performance, with areas under the curve of 0.763 (95% CI, 0.712–0.815) for the training set and 0.860 (95% CI, 0.758–0.961) for the validation set. Moreover, after reviewing the pathological slides of patients in the validation set, four patients initially diagnosed as PNI-negative were recognized as PNI-positive. All these four patients with false-negative PNI were correctly predicted to be PNI-positive (predicted p > 0.5) by the nomogram, which improved the PNI detection rate.ConclusionThe nomogram has potential to assist clinicians when evaluating the PNI status, reduce misdiagnosis, and optimize surgical strategies for patients with cervical cancer.

Download Full-text

A CT-Based Radiomics Nomogram for Preoperative Prediction of Lymph Node Metastasis in Periampullary Carcinomas

Frontiers in Oncology ◽

10.3389/fonc.2021.632176 ◽

2021 ◽

Vol 11 ◽

Author(s):

Lei Bi ◽

Yubo Liu ◽

Jingxu Xu ◽

Ximing Wang ◽

Tong Zhang ◽

...

Keyword(s):

Logistic Regression ◽

Lymph Node ◽

Clinical Utility ◽

Clinical Decision Making ◽

Multivariate Logistic Regression Model ◽

Training Set ◽

Preoperative Prediction ◽

Validation Set ◽

Periampullary Carcinomas ◽

Radiomics Signature

PurposeTo establish and validate a radiomics nomogram for preoperatively predicting lymph node (LN) metastasis in periampullary carcinomas.Materials and MethodsA total of 122 patients with periampullary carcinoma were assigned into a training set (n = 85) and a validation set (n = 37). The preoperative CT radiomics of all patients were retrospectively assessed and the radiomic features were extracted from portal venous-phase images. The one-way analysis of variance test and the least absolute shrinkage and selection operator regression were used for feature selection. A radiomics signature was constructed with logistic regression algorithm, and the radiomics score was calculated. Multivariate logistic regression model integrating independent risk factors was adopted to develop a radiomics nomogram. The performance of the radiomics nomogram was assessed by its calibration, discrimination, and clinical utility with independent validation.ResultsThe radiomics signature, constructed by seven selected features, was closely related to LN metastasis in the training set (p < 0.001) and validation set (p = 0.017). The radiomics nomogram that incorporated radiomics signature and CT-reported LN status demonstrated favorable calibration and discrimination in the training set [area under the curve (AUC), 0.853] and validation set (AUC, 0.853). The decision curve indicated the clinical utility of our nomogram.ConclusionOur CT-based radiomics nomogram, incorporating radiomics signature and CT-reported LN status, could be an individualized and non-invasive tool for preoperative prediction of LN metastasis in periampullary carcinomas, which might assist clinical decision making.

Download Full-text

Development and Validation of a Radiomics Model Based on 18F-FDG PET of Primary Gastric Cancer for Predicting Peritoneal Metastasis

Frontiers in Oncology ◽

10.3389/fonc.2021.740111 ◽

2021 ◽

Vol 11 ◽

Author(s):

Beihui Xue ◽

Jia Jiang ◽

Lei Chen ◽

Sunjie Wu ◽

Xuan Zheng ◽

...

Keyword(s):

Gastric Cancer ◽

Logistic Regression ◽

Peritoneal Metastasis ◽

Fdg Pet ◽

Validation Cohort ◽

Comprehensive Model ◽

Training Set ◽

Training Cohort ◽

Model Based ◽

Validation Set

ObjectivesThe aim of this study was to develop a preoperative positron emission tomography (PET)-based radiomics model for predicting peritoneal metastasis (PM) of gastric cancer (GC).MethodsIn this study, a total of 355 patients (109PM+, 246PM-) who underwent preoperative fluorine-18-fludeoxyglucose (18F-FDG) PET images were retrospectively analyzed. According to a 7:3 ratio, patients were randomly divided into a training set and a validation set. Radiomics features and metabolic parameters data were extracted from PET images. The radiomics features were selected by logistic regression after using maximum relevance and minimum redundancy (mRMR) and the least shrinkage and selection operator (LASSO) method. The radiomics models were based on the rest of these features. The performance of the models was determined by their discrimination, calibration, and clinical usefulness in the training and validation sets.ResultsAfter dimensionality reduction, 12 radiomics feature parameters were obtained to construct radiomics signatures. According to the results of the multivariate logistic regression analysis, only carbohydrate antigen 125 (CA125), maximum standardized uptake value (SUVmax), and the radiomics signature showed statistically significant differences between patients (P<0.05). A radiomics model was developed based on the logistic analyses with an AUC of 0.86 in the training cohort and 0.87 in the validation cohort. The clinical prediction model based on CA125 and SUVmax was 0.76 in the training set and 0.69 in the validation set. The comprehensive model, which contained a rad-score and the clinical factor (CA125) as well as the metabolic parameter (SUVmax), showed promising performance with an AUC of 0.90 in the training cohort and 0.88 in the validation cohort, respectively. The calibration curve showed the actual rate of the nomogram-predicted probability of peritoneal metastasis. Decision curve analysis (DCA) also demonstrated the good clinical utility of the radiomics nomogram.ConclusionsThe comprehensive model based on the rad-score and other factors (SUVmax, CA125) can provide a novel tool for predicting peritoneal metastasis of gastric cancer patients preoperatively.

Download Full-text