Logistic Regression for Gastric Cancer Classification using epidemiological risk factors in Cases and Controls

2021 ◽  
Vol 9 (2) ◽  
pp. 154-160
Author(s):  
Brindha Senthil Kumar ◽  
◽  
Harvey Vanlalpeka ◽  
John Zohmingthanga ◽  
Nachimuthu Senthil Kumar ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Logistic Regression ◽  
Gradient Descent ◽  
Missing Values ◽  
Healthy Individuals ◽  
Global Minima ◽  
Learning Classifier ◽  
Epidemiological Risk ◽  
The Cost ◽  
Number Of Iterations

The main purpose of this study is to design a machine learning classifier that can accurately classify between gastric cancer (cases) patient and healthy individuals (controls) from epidemiological and environmental factors. The dataset contains missing values which are replaced by median using imputation technique. The basic idea of this work is to reduce the cost function by applying gradient descent to detect the optimal global minima. The proposed logistic regression has utilized 29 features as the input and produces an accuracy of 98.51%. This accuracy is achieved with learning rate 0.000915 and number of iterations 150000, which are devised for training the logistic regression model.

Preoperative Circulating MiR-210, a Risk Factor for Postoperative Delirium Among Elderly Patients with Gastric Cancer Undergoing Curative Resection

2020 ◽  
Vol 26 (40) ◽  
pp. 5213-5219
Author(s):  
Yun Chen ◽  
Jinwei Zheng ◽  
Junping Chen
Keyword(s):  
Gastric Cancer ◽  
Logistic Regression ◽  
Risk Factor ◽  
Elderly Patients ◽  
Curative Resection ◽  
Postoperative Delirium ◽  
Area Under The Curve ◽  
Multivariate Logistic Regression Model ◽  
Multivariate Logistic Regression ◽  
Clinicopathologic Characteristics

Background: Postoperative delirium (POD) is a very common complication in elderly patients with gastric cancer (GC) and associated with poor prognosis. MicroRNAs (miRNAs) serve as key post-transcriptional regulators of gene expression via targeting mRNAs and play important roles in the nervous system. This study aimed to investigate the potential predictive role of miRNAs for POD. Methods: Elderly GC patients who were scheduled to undergo elective curative resection were consequently enrolled in this study. POD was assessed at 1 day before surgery and 1-7 days after surgery following the guidance of the 5th edition of Diagnostic and Statistical Manual of Mental Disorders (DSM V, 2013). The demographics, clinicopathologic characteristics and preoperative circulating miRNAs by quantitative reverse transcription-polymerase chain reaction (qRT-PCR) were compared between patients with or without POD. Risk factors for POD were assessed via univariate and multivariate logistic regression analyses. Results: A total of 370 participants were enrolled, of which 63 had suffered from POD within postoperative 7 days with an incidence of 17.0%. Preoperative miR-210 was a predictor for POD with an area under the curve (AUC) of 0.921, a cut-off value of 1.67, a sensitivity of 95.11%, and a specificity of 92.06%, (P<0.001). In the multivariate logistic regression model, the relative expression of serum miR-210 was an independent risk factor for POD (OR: 3.37, 95%CI: 1.98–5.87, P=0.003). Conclusions: In conclusion, the present study highlighted that preoperative miR-210 could serve as a potential predictor for POD in elderly GC patients undergoing curative resection.

CDH1 germline mutations in healthy individuals from families with the hereditary diffuse gastric cancer syndrome

2021 ◽  
pp. jmedgenet-2021-108226
Author(s):  
Giovanni Corso ◽  
Francesca Magnoni ◽  
Giulia Massari ◽  
Cristina Maria Trovato ◽  
Alessandra Margherita De Scalzi ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Healthy Subjects ◽  
Relevant Literature ◽  
Germline Mutations ◽  
Hereditary Diffuse Gastric Cancer ◽  
Diffuse Gastric Cancer ◽  
Missense Mutations ◽  
Healthy Individuals ◽  
Cancer Syndrome ◽  
The Difference

The objective of this study was to determining the frequency of different sub-types of pathogenic CDH1 germline mutations in healthy and asymptomatic individuals from families with the hereditary diffuse gastric cancer (HDGC) syndrome. Relevant literature dating from 1998 to 2019 was systematically searched for data on CDH1 germline mutations. The collected variants were classified according to their subtype into the following classes: missense, non-sense, splicing, insertions and deletions. The χ2 test was used to estimate if the difference observed between patients with gastric cancer (GC) and unaffected individuals was statistically significant. CDH1 genetic screening data were retrieved for 224 patients with GC and 289 healthy individuals. Among the subjects that had tested CDH1 positive, splicing mutations were found in 30.4% of the healthy individuals and in 15.2% of the patients with GC (p=0.0076). Missense mutations were also found to occur in healthy subjects with higher frequency (22.2%) than in GC-affected individuals (18.3%), but the difference was not significant in this case. In families meeting the clinical criteria for the HDGC syndrome, CDH1 splicing and missense germline mutations have been reported to occur with higher frequency in healthy subjects than in patients with cancer. This preliminary observation suggests that not all pathogenic CDH1 germline mutations confer the same risk of developing GC.

Predicting Mobile Portability Across Telecommunication Networks Using the Integrated-KLR

2021 ◽  
Vol 17 (3) ◽  
pp. 50-62
Author(s):  
Ayodeji Samuel Makinde ◽  
Abayomi O. Agbeyangi ◽  
Wilson Nwankwo
Keyword(s):  
Logistic Regression ◽  
Telecommunication Networks ◽  
Mobile Service ◽  
Personal Choice ◽  
Kernel Logistic Regression ◽  
Service Efficiency ◽  
Number Portability ◽  
Prediction Techniques ◽  
The Cost ◽  
Potential Customers

Mobile number portability (MNP) across telecommunication networks entails the movement of a customer from one mobile service provider to another. This, often, is as a result of seeking better service delivery or personal choice. Churning prediction techniques seek to predict customers tending to churn and allow for improved customer sustenance campaigns and the cost therein through an improved service efficiency to customer. In this paper, MNP predicting model using integrated kernel logistic regression (integrated-KLR) is proposed. The Integrated-KLR is a combination of kernel logistic regression and expectation-maximization clustering which helps in proactively detecting potential customers before defection. The proposed approach was evaluated with five others, mostly used algorithms: SOM, MLP, Naïve Bayes, RF, J48. The proposed iKLR outperforms the other algorithms with ROC and PRC of 0.856 and 0.650, respectively.

scholarly journals Expression of LOX Suggests Poor Prognosis in Gastric Cancer

2021 ◽  
Vol 8 ◽  
Author(s):  
Jinfeng Zhu ◽  
Chen Luo ◽  
Jiefeng Zhao ◽  
Xiaojian Zhu ◽  
Kang Lin ◽  
...  
Keyword(s):  
Gene Expression ◽  
Gastric Cancer ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Poor Prognosis ◽  
Cox Regression ◽  
Gene Set Enrichment Analysis ◽  
High Expression ◽  
Expression Level ◽  
Cox Regression Analysis

Background: Lysyl oxidase (LOX) is a key enzyme for the cross-linking of collagen and elastin in the extracellular matrix. This study evaluated the prognostic role of LOX in gastric cancer (GC) by analyzing the data of The Cancer Genome Atlas (TCGA) and the Gene Expression Omnibus (GEO) dataset.Methods: The Wilcoxon rank-sum test was used to calculate the expression difference of LOX gene in gastric cancer and normal tissues. Western blot and immunohistochemical staining were used to evaluate the expression level of LOX protein in gastric cancer. Kaplan-Meier analysis was used to calculate the survival difference between the high expression group and the low expression group in gastric cancer. The relationship between statistical clinicopathological characteristics and LOX gene expression was analyzed by Wilcoxon or Kruskal-Wallis test and logistic regression. Univariate and multivariate Cox regression analysis was used to find independent risk factors affecting the prognosis of GC patients. Gene set enrichment analysis (GSEA) was used to screen the possible mechanisms of LOX and GC. The CIBERSORT calculation method was used to evaluate the distribution of tumor-infiltrating immune cell (TIC) abundance.Results: LOX is highly expressed in gastric cancer tissues and is significantly related to poor overall survival. Wilcoxon or Kruskal-Wallis test and Logistic regression analysis showed, LOX overexpression is significantly correlated with T-stage progression in gastric cancer. Multivariate Cox regression analysis on TCGA and GEO data found that LOX (all p &lt; 0.05) is an independent factor for poor GC prognosis. GSEA showed that high LOX expression is related to ECM receptor interaction, cancer, Hedgehog, TGF-beta, JAK-STAT, MAPK, Wnt, and mTOR signaling pathways. The expression level of LOX affects the immune activity of the tumor microenvironment in gastric cancer.Conclusion: High expression of LOX is a potential molecular indicator for poor prognosis of gastric cancer.

scholarly journals Effect of Positive Hepatitis B Surface Antigen on The Risk of Synchronous Liver Metastasis: A Retrospective Study of 868 Consecutive Patients of Newly Diagnosed Gastric Cancer

2020 ◽  
Author(s):  
Tingya Wang ◽  
Haijun Zhang
Keyword(s):  
Risk Factors ◽  
Gastric Cancer ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Retrospective Study ◽  
Liver Metastasis ◽  
Hepatitis B ◽  
Surface Antigen ◽  
Hepatitis B Surface Antigen ◽  
Newly Diagnosed

Abstract Background. The study aimed to explore the influence of hepatitis B virus (HBV) infection on the risk of synchronous gastric cancer liver metastasis (synGCLM).Methods. This was a retrospective study which enrolled 868 patients with newly diagnosed gastric cancer (GC). The study compared the prevalence of synGCLM between hepatitis B surface antigen (HBsAg)-positive (HBsAg+) and -negative (HBsAg-) patients. Logistic regression analysis was utilized to analyze the risk factors for synGCLM. Among patients with and without synGCLM, aspartate aminotransferase to platelet ratio index (APRI), liver fibrosis-4 index (FIB-4) and hepatitis B e antigen (HBeAg) status were further analyzed. Results. The prevalence of synGCLM in the HBsAg+ patients was higher than that in the HBsAg- patients, which was statistically significant (P = 0.025). Multivariate logistic regression analysis demonstrated that HBsAg, the elevated level of carcinoembryonic antigen (CEA), alpha-fetoprotein (AFP), γ-glutamyltransferase (GGT) and alkaline phosphatase (ALP) were risk factors for synGCLM. Among the HBsAg+ patients, both ARPI and FIB-4 were significantly higher in the patients with synGCLM (synGCLM+) than those without synGCLM (synGCLM-) (ARPI: P = 0.045; FIB-4: P = 0.047); HBeAg positivity was detected in 20.0% of synGCLM+ patients compared to 6.0% of synGCLM- patients, but the difference was of no significance (P = 0.190). Conclusions. HBV infection significantly increases the risk of synGCLM, and elevated ARPI and FIB-4 may be pro-metastatic especially among the HBsAg+ GC patients.

scholarly journals CLASSIFICATION OF BIPOLAR DISORDER, MAJOR DEPRESSIVE DISORDER, AND HEALTHY STATE USING VOICE

2018 ◽  
Vol 11 (15) ◽  
pp. 89 ◽  
Author(s):  
Masakazu Higuchi ◽  
Shinichi Tokuno ◽  
Mitsuteru Nakamura ◽  
Shuji Shinohara ◽  
Shunji Mitsuyoshi ◽  
...  
Keyword(s):  
Bipolar Disorder ◽  
Logistic Regression ◽  
Major Depressive Disorder ◽  
Depressive Disorder ◽  
Mental Disease ◽  
Healthy Individuals ◽  
Major Depressive ◽  
Healthy State ◽  
Polytomous Logistic Regression

Objective: In this study, we propose a voice index to identify healthy individuals, patients with bipolar disorder, and patients with major depressive disorder using polytomous logistic regression analysis.Methods: Voice features were extracted from voices of healthy individuals and patients with mental disease. Polytomous logistic regression analysis was performed for some voice features.Results: With the prediction model obtained using the analysis, we identified subject groups and were able to classify subjects into three groups with 90.79% accuracy.Conclusion: These results show that the proposed index may be used as a new evaluation index to identify depression.

Sign in / Sign up

Export Citation Format

Share Document