scholarly journals Construction and Verification of a Radiation Pneumonia Prediction Model Based on Multiple Parameters

2021 ◽  
Vol 28 ◽  
pp. 107327482110266
Author(s):  
Liu Yafeng ◽  
Wu Jing ◽  
Zhou Jiawei ◽  
Xing Yingru ◽  
Zhang Xin ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Regression Analysis ◽  
Platelet Count ◽  
Radiation Dose ◽  
Prediction Model ◽  
Regression Model ◽  
Clinical Data ◽  
Stepwise Regression ◽  
Training Set ◽  
Radiation Pneumonia

Objective: Patients with lung cancer are at risk of radiation pneumonia (RP) after receiving radiotherapy. We established a prediction model according to the critical indicators extracted from radiation pneumonia patients. Materials and Methods: 74 radiation pneumonia patients were involved in the training set. Firstly, the clinical data, hematological and radiation dose parameters of the 74 patients were screened by Logistics regression univariate analysis according to the level of radiation pneumonia. Next, Stepwise regression analysis was utilized to construct the regression model. Then, the influence of continuous variables on RP was tested by smoothing function. Finally, the model was externally verified by 30 patients in validation set and visualized by R code. Results: In the training set, there was 40 patients suffered≥ level 2 acute radiation pneumonia. Clinical data (diabetes), blood indexes (lymphocyte percentage, basophil percentage, platelet count) and radiation dose (V15 > 40%, V20 > 30%, V35 >18%, V40 > 15%) were related to radiation pneumonia ( P < 0.05). Particularly, stepwise regression analysis indicated that the history of diabetes, the basophils percentage, platelet count and V20 could be the best combination used for predicting radiation pneumonia. The column chart was obtained by fitting the regression model with the combined indicator. The receiver operating characteristic (ROC) curve showed that the AUC in the development term was 0.853, the AUC was 0.656 in the validation term. And calibration curves of both groups showed the high stability in efficiently diagnostic. Furthermore, the DCA curve showed that the model had a satisfactory positive net benefit. Conclusion: The combination of the basophils percentage, platelet count and V20 is available to build a predictive model of radiation pneumonia for patients with advanced lung cancer.

Research on Related Problems of PM2.5 in Air

2014 ◽  
Vol 644-650 ◽  
pp. 5319-5324
Author(s):  
Tian Jiu Leng
Keyword(s):  
Regression Analysis ◽  
Boundary Conditions ◽  
Regression Model ◽  
Multiple Regression ◽  
Stepwise Regression ◽  
Multiple Regression Model ◽  
Stepwise Regression Analysis ◽  
Spatial Evolution ◽  
Analysis Method ◽  
Relevant Factors

In this paper, the relevant factors of PM2.5 and the degree of correlation between them were analyzed.The multiple regression model was established using stepwise regression analysis method and the temporal spatial evolution of PM2.5 was obtained by setting the initial and boundary conditions.

scholarly journals A novel ferroptosis-related genes model for prognosis prediction of lung adenocarcinoma

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Fei Li ◽  
Dongcen Ge ◽  
Shu-lan Sun
Keyword(s):  
Regression Analysis ◽  
High Risk ◽  
Prediction Model ◽  
Cox Regression ◽  
Risk Group ◽  
Training Set ◽  
Cox Regression Analysis ◽  
Key Genes ◽  
Validation Set ◽  
Prognostic Prediction

Abstract Background Ferroptosis is a newly discovered form of cell death characterized by iron-dependent lipid peroxidation. This study aims to investigate the potential correlation between ferroptosis and the prognosis of lung adenocarcinoma (LUAD). Methods RNA-seq data were collected from the LUAD dataset of The Cancer Genome Atlas (TCGA) database. Based on ferroptosis-related genes, differentially expressed genes (DEGs) between LUAD and paracancerous specimens were identified. The univariate Cox regression analysis was performed to screen key genes associated with the prognosis of LUAD. LUAD patients were divided into the training set and validation set. Then, we screened out key genes and built a prognostic prediction model involving 5 genes using the least absolute shrinkage and selection operator (LASSO) regression with tenfold cross-validation and the multivariate Cox regression analysis. After dividing LUAD patients based on the median level of risk score as cut-off value, the generated prognostic prediction model was validated in the validation set. Moreover, we analyzed the somatic mutations, and estimated the scores of immune infiltration in the high-risk and low-risk groups. Functional enrichment analysis of DEGs was performed as well. Results High-risk scores indicated the worse prognosis of LUAD. The maximum area under curve (AUC) of the training set and the validation set in this study was 0.7 and 0.69, respectively. Moreover, we integrated the age, gender, and tumor stage to construct the composite nomogram. The charts indicated that the AUC of LUAD cases with the survival time of 1, 3 and 5 years was 0.698, 0.71 and 0.73, respectively. In addition, the mutation frequency of LUAD patients in the high-risk group was significantly higher than that in the low-risk group. Simultaneously, DEGs were mainly enriched in ferroptosis-related pathways by analyzing the functional results. Conclusions This study constructs a novel LUAD prognosis prediction model involving 5 ferroptosis-related genes, which can be used as a promising tool for decision-making of clinical therapeutic strategies of LUAD.

scholarly journals Integrating proteomic, sociodemographic and clinical data to predict future depression diagnosis in subthreshold symptomatic individuals

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Sung Yeon Sarah Han ◽  
Jason D. Cooper ◽  
Sureyya Ozcan ◽  
Nitin Rustogi ◽  
Brenda W.J.H. Penninx ◽  
...  
Keyword(s):  
Prediction Model ◽  
Patient Group ◽  
Clinical Data ◽  
Serum Proteins ◽  
Reference Group ◽  
Sociodemographic Factors ◽  
First Episode ◽  
Training Set ◽  
Test Set ◽  
Increased Risk

Abstract Individuals with subthreshold depression have an increased risk of developing major depressive disorder (MDD). The aim of this study was to develop a prediction model to predict the probability of MDD onset in subthreshold individuals, based on their proteomic, sociodemographic and clinical data. To this end, we analysed 198 features (146 peptides representing 77 serum proteins (measured using MRM-MS), 22 sociodemographic factors and 30 clinical features) in 86 first-episode MDD patients (training set patient group), 37 subthreshold individuals who developed MDD within two or four years (extrapolation test set patient group), and 86 subthreshold individuals who did not develop MDD within four years (shared reference group). To ensure the development of a robust and reproducible model, we applied feature extraction and model averaging across a set of 100 models obtained from repeated application of group LASSO regression with ten-fold cross-validation on the training set. This resulted in a 12-feature prediction model consisting of six serum proteins (AACT, APOE, APOH, FETUA, HBA and PHLD), three sociodemographic factors (body mass index, childhood trauma and education level) and three depressive symptoms (sadness, fatigue and leaden paralysis). Importantly, the model demonstrated a fair performance in predicting future MDD diagnosis of subthreshold individuals in the extrapolation test set (AUC = 0.75), which involved going beyond the scope of the model. These findings suggest that it may be possible to detect disease indications in subthreshold individuals up to four years prior to diagnosis, which has important clinical implications regarding the identification and treatment of high-risk individuals.

Temperature Character Analysis of RCC Based on Stepwise Regression Model

2012 ◽  
Vol 238 ◽  
pp. 268-271
Author(s):  
Yu Qing Zhao
Keyword(s):  
Regression Analysis ◽  
Regression Model ◽  
Stepwise Regression ◽  
Stepwise Regression Analysis ◽  
Gravity Dam ◽  
Practical Calculation ◽  
Analysis Model ◽  
Related Factors ◽  
Reservoir Water ◽  
Basic Principles

The basic principles and ways of stepwise regression analysis is explained, taking the case of Jiangya gravity dam. On the basis of the temperature monitoring data, the optimal regression equation of the dam temperature is established gradually by the dam bedrock temperature, air temperature and reservoir water temperature and other related factors. It is proved that stepwise regression analysis model is reasonable and the simulation is fairly well with high precision. The stepwise regression model can be used to analyze the concrete temperature. The work provides the practical calculation basis for the monitoring of dam safety running.

scholarly journals Development and validation of a model to estimate the risk of acute ischemic stroke in geriatric patients with primary hypertension

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Xifeng Zheng ◽  
Fang Fang ◽  
Weidong Nong ◽  
Dehui Feng ◽  
Yu Yang
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
Ischemic Stroke ◽  
Prediction Model ◽  
Acute Ischemic Stroke ◽  
Logistic Regression Analysis ◽  
Geriatric Patients ◽  
Primary Hypertension ◽  
Multivariable Logistic Regression Analysis ◽  
Training Set

Abstract Objectives This study aimed to construct and validate a prediction model of acute ischemic stroke in geriatric patients with primary hypertension. Methods This retrospective file review collected information on 1367 geriatric patients diagnosed with primary hypertension and with and without acute ischemic stroke between October 2018 and May 2020. The study cohort was randomly divided into a training set and a testing set at a ratio of 70 to 30%. A total of 15 clinical indicators were assessed using the chi-square test and then multivariable logistic regression analysis to develop the prediction model. We employed the area under the curve (AUC) and calibration curves to assess the performance of the model and a nomogram for visualization. Internal verification by bootstrap resampling (1000 times) and external verification with the independent testing set determined the accuracy of the model. Finally, this model was compared with four machine learning algorithms to identify the most effective method for predicting the risk of stroke. Results The prediction model identified six variables (smoking, alcohol abuse, blood pressure management, stroke history, diabetes, and carotid artery stenosis). The AUC was 0.736 in the training set and 0.730 and 0.725 after resampling and in the external verification, respectively. The calibration curve illustrated a close overlap between the predicted and actual diagnosis of stroke in both the training set and testing validation. The multivariable logistic regression analysis and support vector machine with radial basis function kernel were the best models with an AUC of 0.710. Conclusion The prediction model using multiple logistic regression analysis has considerable accuracy and can be visualized in a nomogram, which is convenient for its clinical application.

The Empirical Study for National Determinant of Coffee Consumption

2014 ◽  
Vol 962-965 ◽  
pp. 1275-1278
Author(s):  
Chao Cheng Chung ◽  
Sze Ting Chen ◽  
Yen Yen Chen ◽  
Chung Yi Chung
Keyword(s):  
Regression Analysis ◽  
Regression Model ◽  
Multivariate Regression ◽  
Stepwise Regression ◽  
Electricity Consumption ◽  
Coffee Consumption ◽  
Economic Factor ◽  
Multivariate Regression Analysis ◽  
Average Life ◽  
Average Life Expectancy

This study analysis the national determinant in the coffee consumption. The final dataset includes 136 countries and nine variables, coffee consumption, GDP, the number of vehicles per capita, and electricity consumption, education, tourism spending, literacy, drinking water quality population density, and the average life expectancy which are all collected from global international independent institutes. In our research, we use the regression model to interpret what the determinant can predict the coffee consumption in a country. We further discussed our research in descriptive statistics analysis, stepwise regression analysis, control some variables, and also multivariate regression analysis. The result showed that the economic factor, i.e. the GDP, play the most important role in the coffee consumption and significantly. The R-Sq (Adj) for this regression model was 59.1%.

scholarly journals Analysis of hospitalization expenditure and its influencing factors for lung cancer patients in China: a research based on the “System of Health Accounts 2011”

2020 ◽  
Author(s):  
Le Pan ◽  
Zhaolin Meng ◽  
Yuanyi Cai ◽  
Huazhang Wu
Keyword(s):  
Lung Cancer ◽  
Regression Analysis ◽  
Length Of Stay ◽  
Path Analysis ◽  
Influencing Factors ◽  
Economic Burden ◽  
Stepwise Regression ◽  
Insurance Status ◽  
Hospital Type ◽  
Multiple Stepwise Regression Analysis

Abstract Background At present, lung cancer is the common malignant tumor of respiratory system worldwide. The disease poses a serious health threat and a substantial economic burden to patients. The economic risks brought by lung cancer arouses widespread public concern. Therefore, the target of this research is to calculate lung cancer expenditure in China under the framework of the System of Health Account 2011 (SHA 2011). Intensive studies on working mechanism of influencing factors to lung cancer expenditure will be further explored, in order to achieve the goal of controlling lung cancer expenditure.Methods A multistage stratified sampling method was conducted in Liaoning province in China, and a total of 23559 patients were included into hospitalization expenditure analysis according to the framework of SHA 2011. The relation between the total hospitalization expenditure of lung cancer and its influencing factors including of demographic characteristics, diagnosis and treatment, and hospital condition was analyzed with the multiple stepwise regression analysis. The impact mechanism of these influencing factors was revealed through path analysis and survival analysis.Results The total hospitalization expenditure of lung cancer was $ 1581.8. Multiple stepwise regression analysis indicated that the total hospitalization expenditure was associated with length of stay, surgery, hospital level, insurance status, and hospital type, according to the sequence of standardized estimate (β). Length of stay contributed the most to the model R-square. Path analysis showed that surgery, hospital type, and insurance status not only made a direct impact on the hospitalization expenditure, but also made an indirect impact on it through the length of stay. Through survival analysis, we found self-funded patients of lung cancer were quicker to run out of the affordable money.Conclusions Lung cancer brought a heavy economic burden for patients. More efficient and stringent clinical control strategies should be conducted to limit the increase of the expenditure.

scholarly journals Survivorship of Cancer Patients in Nigeria: An Evidence for Aggressive Measures against Cancer in Developing Countries

2015 ◽  
Vol 2 (2) ◽  
pp. 289
Author(s):  
Grace O. Korter ◽  
Eghe M. Igbinehi
Keyword(s):  
Lung Cancer ◽  
Developing Countries ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Skin Cancer ◽  
South America ◽  
Prediction Model ◽  
Cancer Patients ◽  
Secondary Data ◽  
Likelihood Ratio Tests

<p><em>More than 60% of the world’s total new annual cancer cases occur in Africa, Asia and Central and South America. The aim of this study was to build a predictive model for the two possible outcomes of cancer patients and to examine which of the several types of cancer was more deadly. Secondary data of 335 patients aged 11 to 90 years who received treatment for liver, lung, colon, colorectal, prostate, breast or skin cancer at LAUTECH teaching hospital between 2004 and 2010 was used for this analysis. Logistic regression analysis was conducted. The Hosmer and Lemeshow and Likelihood Ratio tests were used to determine the fit and significance of parameters of the model. Only the type of cancer suffered by patients contributed significantly to the prediction model. The odds of dying for patients with lung cancer were about 4 times that of other types of cancer. However, the incidence of liver, lung, colon, colorectal, prostate, breast and skin cancer was prevalent across patients aged 11 and 90 years, irrespective of sex. Lung cancer was found to be more deadly than other types of cancer observed in the sample.</em></p>

scholarly journals Identification of Two Long Non-Coding RNAs AC010082.1 and AC011443.1 as Biomarkers of Coronary Heart Disease Based on Logistic Stepwise Regression Prediction Model

2021 ◽  
Vol 12 ◽  
Author(s):  
Chao Liu ◽  
Lanchun Liu ◽  
Jialiang Gao ◽  
Jie Wang ◽  
Yongmei Liu
Keyword(s):  
Coronary Heart Disease ◽  
Heart Disease ◽  
Prediction Model ◽  
Microarray Data ◽  
Stepwise Regression ◽  
Validation Cohort ◽  
Healthy Controls ◽  
Training Set ◽  
Test Set ◽  
Cerna Network

Coronary heart disease (CHD) is a global health concern with high morbidity and mortality rates. This study aimed to identify the possible long non-coding RNA (lncRNA) biomarkers of CHD. The lncRNA- and mRNA-related data of patients with CHD were downloaded from the Gene Expression Omnibus database (GSE113079). The limma package was used to identify differentially expressed lncRNAs and mRNAs (DElncRNAs and DEmRNAs, respectively). Then, miRcode, TargetScan, miRDB, and miRTarBase databases were used to form the competing endogenous RNA (ceRNA) network. Furthermore, SPSS Modeler 18.0 was used to construct a logistic stepwise regression prediction model for CHD diagnosis based on DElncRNAs. Of the microarray data, 70% was used as a training set and 30% as a test set. Moreover, a validation cohort including 30 patients with CHD and 30 healthy controls was used to verify the hub lncRNA expression through real-time reverse transcription-quantitative PCR (RT-qPCR). A total of 185 DElncRNAs (114 upregulated and 71 downregulated) and 382 DEmRNAs (162 upregulated and 220 downregulated) between CHD and healthy controls were identified from the microarray data. Furthermore, through bioinformatics prediction, a 38 lncRNA-21miRNA-40 mRNA ceRNA network was constructed. Next, by constructing a logistic stepwise regression prediction model for 38 DElncRNAs, we screened two hub lncRNAs AC010082.1 and AC011443.1 (p &lt; 0.05). The sensitivity, specificity, and area under the curve were 98.41%, 100%, and 0.995, respectively, for the training set and 93.33%, 91.67%, and 0.983, respectively, for the test set. We further verified the significant upregulation of AC010082.1 (p &lt; 0.01) and AC011443.1 (p &lt; 0.05) in patients with CHD using RT-qPCR in the validation cohort. Our results suggest that lncRNA AC010082.1 and AC011443.1 are potential biomarkers of CHD. Their pathological mechanism in CHD requires further validation.

scholarly journals Nomogram for Predicting the Postoperative Venous Thromboembolism in Spinal Metastasis Tumor: A Multicenter Retrospective Study

2021 ◽  
Vol 11 ◽  
Author(s):  
Hao-ran Zhang ◽  
Ming-you Xu ◽  
Xiong-gang Yang ◽  
Feng Wang ◽  
Hao Zhang ◽  
...  
Keyword(s):  
Risk Factors ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Venous Thromboembolism ◽  
Prediction Model ◽  
Regression Model ◽  
Logistic Regression Model ◽  
Multivariate Logistic Regression Model ◽  
Multivariate Logistic Regression ◽  
Independent Risk Factors

IntroductionVenous thromboembolism can be divided into deep vein thrombosis and pulmonary embolism. These diseases are a major factor affecting the clinical prognosis of patients and can lead to the death of these patients. Unfortunately, the literature on the risk factors of venous thromboembolism after surgery for spine metastatic bone lesions are rare, and no predictive model has been established.MethodsWe retrospectively analyzed 411 cancer patients who underwent metastatic spinal tumor surgery at our institution between 2009 and 2019. The outcome variable of the current study is venous thromboembolism that occurred within 90 days of surgery. In order to identify the risk factors for venous thromboembolism, a univariate logistic regression analysis was performed first, and then variables significant at the P value less than 0.2 were included in a multivariate logistic regression analysis. Finally, a nomogram model was established using the independent risk factors.ResultsIn the multivariate logistic regression model, four independent risk factors for venous thromboembolism were further screened out, including preoperative Frankel score (OR=2.68, 95% CI 1.78-4.04, P=0.001), blood transfusion (OR=3.11, 95% CI 1.61-6.02, P=0.041), Charlson comorbidity index (OR=2.01, 95% CI 1.27-3.17, P=0.013; OR=2.29, 95% CI 1.25-4.20, P=0.017), and operative time (OR=1.36, 95% CI 1.14-1.63, P=0.001). On the basis of the four independent influencing factors screened out by multivariate logistic regression model, a nomogram prediction model was established. Both training sample and validation sample showed that the predicted probability of the nomogram had a strong correlation with the actual situation.ConclusionThe prediction model for postoperative VTE developed by our team provides clinicians with a simple method that can be used to calculate the VTE risk of patients at the bedside, and can help clinicians make evidence-based judgments on when to use intervention measures. In clinical practice, the simplicity of this predictive model has great practical value.

Sign in / Sign up

Export Citation Format

Share Document