A Hybrid Risk Assessment Model for Cardiovascular Disease Using Cox Regression Analysis and a 2-means clustering algorithm

2019 ◽  
Vol 113 ◽  
pp. 103400 ◽  
Author(s):  
T. Vivekanandan ◽  
Swathi Jamjala Narayanan
Keyword(s):  
Cardiovascular Disease ◽  
Risk Assessment ◽  
Regression Analysis ◽  
Clustering Algorithm ◽  
Cox Regression ◽  
Assessment Model ◽  
Risk Assessment Model ◽  
Cox Regression Analysis

scholarly journals Immune-Related lncRNAs to Construct Novel Signatures and Predict the Prognosis of Rectal Cancer

2021 ◽  
Vol 11 ◽  
Author(s):  
Xiao-Liang Xing ◽  
Chaoqun Xing ◽  
Zhi Huang ◽  
Zhi-Yong Yao ◽  
Yuan-Wu Liu
Keyword(s):  
Risk Assessment ◽  
Rectal Cancer ◽  
Differential Expression ◽  
Immune Cells ◽  
Cox Regression ◽  
Differential Expression Analysis ◽  
Rectal Adenocarcinoma ◽  
Assessment Model ◽  
Risk Assessment Model ◽  
Cox Regression Analysis

Colorectal cancer (CRC) is one of the most common cancers. Almost 1/3 of CRC are rectal cancer, and 95% of rectal cancers are rectal adenocarcinoma (READ). Increasing evidences indicated that long noncoding RNAs (lncRNAs) have important role in the genesis and development of cancers. The purpose of our present study was to identify the differential expression lncRNAs which potentially related with immune cells infiltration and establish a risk assessment model to predict the clinical outcome for READ patients. We obtained three immune-related differential expression lncRNAs (IR-DELs) (C17orf77, GATA2-AS1, and TPT1-AS1) by differential expression analysis following correlation analysis and Cox regression analysis. A risk assessment model were constructed by integrating these analysis results. We then plotted the 1-, 3-, and 5-year ROC curves depending on our risk assessment model, which suggested that all AUC values were over 0.7. In addition, we found that the risk assessment model was correlated with several immune cells and factors. This study suggested that those three signatures (C17orf77, GATA2-AS1, and TPT1-AS1) screened by pairing IR-DELs could be prognosis markers for READ patients and might benefit them from antitumor immunotherapy.

A Validated Risk Model for Prediction of Early Readmission in Patients with Hepatic Encephalopathy

2018 ◽  
Vol 17 (5) ◽  
pp. 0-10
Author(s):  
Andrew J. Kruger ◽  
Fasika Aberra ◽  
Sylvester M. Black ◽  
Alice Hinton ◽  
James Hanje ◽  
...  
Keyword(s):  
Risk Assessment ◽  
Hepatic Encephalopathy ◽  
High Risk ◽  
Risk Model ◽  
Cox Regression ◽  
Low Risk ◽  
Assessment Model ◽  
Risk Assessment Model ◽  
Early Readmission ◽  
The Impact

Introduction and aim. Hepatic encephalopathy (HE) is a common complication in cirrhotics and is associated with an increased healthcare burden. Our aim was to study independent predictors of 30-day readmission and develop a readmission risk model in patients with HE. Secondary aims included studying readmission rates, cost, and the impact of readmission on mortality. Material and methods. We utilized the 2013 Nationwide Readmission Database (NRD) for hospitalized patients with HE. A risk assessment model based on index hospitalization variables for predicting 30-day readmission was developed using multivariate logistic regression and validated with the 2014 NRD. Patients were stratified into Low Risk and High Risk groups. Cox regression models were fit to identify predictors of calendar-year mortality. Results. Of 24,473 cirrhosis patients hospitalized with HE, 32.4% were readmitted within 30-days. Predictors of readmission included presence of ascites (OR: 1.19; 95% CI: 1.06-1.33), receiving paracentesis (OR: 1.43; 95% CI: 1.26-1.62) and acute kidney injury (OR: 1.11; 95% CI: 1.00-1.22). Our validated model stratified patients into Low Risk and High Risk of 30-day readmissions (29% and 40%, respectively). The cost of the first readmission was higher than index admission in the 30-day readmission cohort ($14,198 vs. $10,386; p-value < 0.001). Thirty-day readmission was the strongest predictor of calendar-year mortality (HR: 4.03; 95% CI: 3.49-4.65). Conclusions. Nearly one-third of patients with HE were readmitted within 30-days, and early readmission adversely impacted healthcare utilization and calendar-year mortality. With our proposed simple risk assessment model, patients at high risk for early readmissions can be identified to potentially avert poor outcomes.

scholarly journals Vertebral Osteomyelitis: A Mortality Analysis Comparing Surgical and Conservative Management

2019 ◽  
Vol 10 (4) ◽  
pp. 456-463
Author(s):  
Spogmai Zadran ◽  
Peter Heide Pedersen ◽  
Søren Eiskjær
Keyword(s):  
Cardiovascular Disease ◽  
Regression Analysis ◽  
Predictive Model ◽  
Conservative Management ◽  
Cox Regression ◽  
Vertebral Osteomyelitis ◽  
Area Under The Curve ◽  
Karnofsky Score ◽  
Cox Regression Analysis ◽  
Choice Of Treatment

Study Design: Retrospective cohort study. Objectives: To compare the mortality between patients treated for vertebral osteomyelitis (VO) with either surgical or conservative management and to construct a predictive model for mortality after VO. Methods: All patients with a diagnosis of VO in Region North Denmark from 2004 to 2014 were followed for at least 2 years or until death. They were all treated according to a standardized guideline for the choice of treatment modality. Nineteen dichotomized variables with possible influence on the mortality were registered for all patients in the study. LASSO (least absolute shrinkage and selection operator) penalized Cox regression analysis was used to build a predictive model for 2-year survival after VO. Results: A total of 125 patients were eligible for inclusion, mean age 67 years, 36 women. 75 were treated surgically. Twenty-one patients were dead 2 years after the diagnosis. Kaplan-Meier estimate of 2-year survival was 0.82 [0.75, 0.88]. Any difference in mortality between surgically and conservatively treated patients was nonsignificant at 1 and 2 years (univariate Cox regression analysis). Significant factors included in the predictive model after LASSO penalized Cox regression analysis was Charlson Comorbidity Index (CCI), cardiovascular disease, C-reactive protein (CRP) normalization, thoracic infection, and Karnofsky score. The area under the curve (AUC) for the predictive model ranged from 0.74 to 0.77. Conclusion: Patients undergoing surgical management for vertebral osteomyelitis according to standardized and agreed-upon guidelines had no higher mortality than those allocated to conservative treatment. The predictive model included 5 variables associated with an increased mortality: CCI, CRP normalization, cardiovascular disease, thoracic infection, and Karnofsky score.

scholarly journals The Value of Blood Urea Nitrogen in the Prediction of Risks of Cardiovascular Disease in an Older Population

2021 ◽  
Vol 8 ◽  
Author(s):  
Qin Lan ◽  
Liang Zheng ◽  
Xiaohui Zhou ◽  
Hong Wu ◽  
Nicholas Buys ◽  
...  
Keyword(s):  
Cardiovascular Disease ◽  
Regression Analysis ◽  
Kidney Disease ◽  
Blood Urea Nitrogen ◽  
Cox Regression ◽  
Older Population ◽  
Urea Nitrogen ◽  
Cox Regression Analysis ◽  
Increased Risk

Background: High blood urea nitrogen (BUN) is associated with adverse outcomes in patients with cardiac disease risks. However, no study has explored whether BUN can predict the risk of cardiovascular disease (CVD) in the healthy older population. This study aims to explore the incidence and risk factors of CVD among a healthy older population community in China.Design and Methods: This study was designed as a cohort study with a 4-year follow-up. We recruited 5,000 older people among 137,625 residents of the Gaohang community. In the baseline, subjects were asked to participate in medical screening and biological tests, and answered survey questions. During the follow-up period (2014–2017), the researchers regularly tested the subjects' indicators and assessment scales. We monitored the occurrence of CVD and explored the relationship between BUN and CVD via a Cox regression analysis.Results: During the follow-up, subjects were newly diagnosed with CVD including heart failure (HF), heart disease events, atrial fibrillation, diabetes, hypertension, metabolic syndrome, and kidney disease. The Cox regression analysis found an association between baseline BUN and incident CVD in female subjects, with higher BUN associated with increased risk of AF in females and kidney disease in both male and females. No association was found between BUN and CVD in male subjects.Conclusions: Current results indicate that BUN is a valuable predictive biomarker of CVD. A higher BUN level (&gt;13.51 mg/dL) is associated with an increased occurrence of HF but a decreased occurrence of diabetes and metabolic symptoms in normal older females.

scholarly journals Objective Sleep Efficiency Predicts Cardiovascular Disease in a Community Population: The Sleep Heart Health Study

2021 ◽  
Author(s):  
Bin Yan ◽  
Jian Yang ◽  
Binbin Zhao ◽  
Yajuan Fan ◽  
Wei Wang ◽  
...  
Keyword(s):  
Cardiovascular Disease ◽  
Regression Analysis ◽  
Cox Regression ◽  
Sleep Onset ◽  
Sleep Efficiency ◽  
Cardiovascular Outcome ◽  
Health Study ◽  
Heart Health ◽  
Cox Regression Analysis ◽  
Cvd Mortality

Background There was little evidence about the role of objective sleep efficiency (SE) in the incidence of major cardiovascular disease (CVD) events. The purpose of this study was to investigate the correlation between objective SE and CVD based on polysomnography. Methods and Results A total of 3810 participants from the SHHS (Sleep Heart Health Study) were selected in the current study. CVD was assessed during an almost 11‐year follow‐up period. The primary composite cardiovascular outcome was major adverse cardiovascular events, defined as CVD mortality, congestive heart failure, myocardial infarction, and stroke. The secondary composite cardiovascular outcome was major adverse cardiovascular event plus revascularization. Objective measured SE, including SE and wake after sleep onset, was based on in‐home polysomnography records. Cox regression analysis was used to explore the association between SE and CVD. After multivariate Cox regression analysis, poor SE (<80%) was significantly associated with primary (hazard ratio [HR], 1.338; 95% CI, 1.025–1.745; P =0.032) and secondary composite cardiovascular outcomes (HR, 1.250; 95% CI, 1.027–1.521; P =0.026); it was also found to be a predictor of CVD mortality (HR, 1.887; 95% CI, 1.224–2.909; P =0.004). Moreover, wake after sleep onset of fourth quartile (>78.0 minutes) was closely correlated with primary (HR, 1.436; 95% CI, 1.066–1.934; P =0.017), secondary composite cardiovascular outcomes (HR, 1.374; 95% CI, 1.103–1.712; P =0.005), and CVD mortality (HR, 2.240; 95% CI, 1.377–3.642; P =0.001). Conclusions Poor SE and long wake after sleep onset, objectively measured by polysomnography, were associated with the increased risk of incident CVD.

scholarly journals Recognition of Immune Microenvironment Landscape and Immune-Related Prognostic Genes in Breast Cancer

2020 ◽  
Vol 2020 ◽  
pp. 1-16
Author(s):  
Huiling Wang ◽  
Shuo You ◽  
Meng Fang ◽  
Qian Fang
Keyword(s):  
Breast Cancer ◽  
T Cells ◽  
Regression Analysis ◽  
Clustering Algorithm ◽  
Immune Cell ◽  
Cox Regression ◽  
Therapeutic Potential ◽  
Enrichment Analysis ◽  
Cox Regression Analysis ◽  
Immune Infiltration

Background. Breast cancer (BC) is the most common malignant tumor in women. The immunophenotype of tumor microenvironment (TME) has shown great therapeutic potential in tumor. Method. The transcriptome was obtained from TCGA and GEO data. Immune infiltration was analyzed by single-sample gene set enrichment (ssGSEA). The immune feature was constructed by Cox regression analysis. In addition, the coexpression of differential expression genes (DEGs) was identified. Through enrichment analysis, the function and pathway of module genes were identified. The somatic mutations related to immune characteristics were analyzed by Maftools. By using the consistency clustering algorithm, the molecular subtypes were constructed, and the overall survival time (OS) was predicted. Results. Immune landscape can be divided into low immune infiltration and high immune infiltration. Cox regression analysis identified seven immune cells as protective factors of BC. In the coexpression modules for DEGs of high and low immune infiltration, module 1 was related to T cells and high immune infiltration. In particular, the area under the curve (AUC) value of hub gene SASH3 was the highest, and the correlation with T cells was stronger in the high immune infiltration. Enrichment analysis found that oxidative stress, T cell aggregation, and apoptosis were observed in high immune infiltration. In addition, TP53 was identified as the most important somatic gene mutation related to immune characteristics. Importantly, we also constructed seven immune cell-based breast cancer subtypes to predict OS. Conclusion. We evaluated the immune landscape of BC and constructed the gene characteristics related to the immune landscape. The potential of T cells and SASH3 in immunotherapy of BC was revealed, which may guide the development of new clinical treatment strategies.

scholarly journals Coexpressed Genes That Promote the Infiltration of M2 Macrophages in Melanoma Can Evaluate the Prognosis and Immunotherapy Outcome

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Kexin Yan ◽  
Yutao Wang ◽  
Yuxiu Lu ◽  
Zhangyong Yan
Keyword(s):  
Regression Analysis ◽  
Cox Regression ◽  
Essential Genes ◽  
Assessment Model ◽  
Functional Enrichment ◽  
Coexpression Network ◽  
M2 Macrophages ◽  
Cox Regression Analysis ◽  
Coexpression Module ◽  
Coexpressed Genes

Purpose. To improve immunotherapy efficacy for melanoma, a coexpression network and key genes of M2 macrophages in melanoma were explored. A prognostic risk assessment model was established for M2-related coexpressed genes, and the role of M2 macrophages in the immune microenvironment of melanoma was elucidated. Method. We obtained mRNA data from melanoma and peritumor tissue samples from The Cancer Genome Atlas-skin cutaneous melanoma (TCGA-SKCM). Then, we used CIBERSORT to calculate the proportion of M2 macrophage cells. A coexpression module most related to M2 macrophages in TCGA-SKCM was determined by analyzing the weighted gene coexpression network, and a coexpression network was established. After survival analysis, factors with significant results were incorporated into a Cox regression analysis to establish a model. The model’s essential genes were analyzed using functional enrichment, GSEA, and subgroup and total carcinoma. Finally, external datasets GSE65904 and GSE78220 were used to verify the prognostic risk model. Results. The yellow-green module was the coexpression module most related to M2 macrophages in TCGA-SKCM; NOTCH3, DBN1, KDELC2, and STAB1 were identified as the essential genes that promoted the infiltration of M2 macrophages in melanoma. These genes are concentrated in antigen treatment and presentation, chemokine, cytokine, the T cell receptor pathway, and the IFN-γ pathway. These factors were analyzed for survival, and factors with significant results were included in a Cox regression analysis. According to the methods, a model related to M2-TAM coexpressed gene was established, and the formula was risk   score = 0.25 ∗ NOTCH 3 + 0.008 ∗   DBN 1 − 0.031 ∗ KDELC 2 − 0.032 ∗ STAB 1 . The new model was used to perform subgroup evaluation and external queue validation. The results showed good prognostic ability. Conclusion. We proposed a Cox proportional hazards regression model associated with coexpression genes of melanoma M2 macrophages that may provide a measurement method for generating prognosis scores in patients with melanoma. Four genes coexpressed with M2 macrophages were associated with high levels of infiltration of M2 macrophages. Our findings may provide significant candidate biomarkers for the treatment and monitoring of melanoma.

scholarly journals Derivation and Validation of a Risk Assessment Model for Immunomodulatory Drug–Associated Thrombosis Among Patients With Multiple Myeloma

2019 ◽  
Vol 17 (7) ◽  
pp. 840-847 ◽  
Author(s):  
Ang Li ◽  
Qian Wu ◽  
Suhong Luo ◽  
Greg S. Warnick ◽  
Neil A. Zakai ◽  
...  
Keyword(s):  
Risk Assessment ◽  
Multiple Myeloma ◽  
Cox Regression ◽  
Risk Groups ◽  
Assessment Model ◽  
Risk Assessment Model ◽  
Veterans Health ◽  
Health Administration ◽  
Clinical Model ◽  
Nccn Guidelines

AbstractBackground: Although venous thromboembolism (VTE) is a significant complication for patients with multiple myeloma (MM) receiving immunomodulatory drugs (IMiDs), no validated clinical model predicts VTE in this population. This study aimed to derive and validate a new risk assessment model (RAM) for IMiD-associated VTE. Methods: Patients with newly diagnosed MM receiving IMiDs were selected from the SEER-Medicare database (n=2,397) to derive a RAM and then data from the Veterans Health Administration database (n=1,251) were used to externally validate the model. A multivariable cause-specific Cox regression model was used for model development. Results: The final RAM, named the “SAVED” score, included 5 clinical variables: prior surgery, Asian race, VTE history, age ≥80 years, and dexamethasone dose. The model stratified approximately 30% of patients in both the derivation and the validation cohorts as high-risk. Hazard ratios (HRs) were 1.85 (P<.01) and 1.98 (P<.01) for high- versus low-risk groups in the derivation and validation cohorts, respectively. In contrast, the method of stratification recommended in the current NCCN Guidelines for Cancer-Associated Venous Thromboembolic Disease had HRs of 1.21 (P=.17) and 1.41 (P=.07) for the corresponding risk groups in the 2 datasets. Conclusions: The SAVED score outperformed the current NCCN Guidelines in risk-stratification of patients with MM receiving IMiD therapy. This clinical model can help inform providers and patients of VTE risk before IMiD initiation and provides a simplified clinical backbone for further prognostic biomarker development in this population.

scholarly journals Identification of Two Immune Related Genes Correlated With Aberrant Methylations as Prognosis Signatures for Renal Clear Cell Carcinoma

2021 ◽  
Vol 12 ◽  
Author(s):  
Zhi-Yong Yao ◽  
Chaoqung Xing ◽  
Yuan-Wu Liu ◽  
Xiao-Liang Xing
Keyword(s):  
Risk Assessment ◽  
Cox Regression ◽  
Clear Cell ◽  
Renal Clear Cell Carcinoma ◽  
Assessment Model ◽  
Risk Scores ◽  
Aberrant Methylation ◽  
Cox Regression Analysis ◽  
Risk Assessment Models ◽  
Immune Related Genes

Almost 75% of renal cancers are renal clear cell carcinomas (KIRC). Accumulative evidence indicates that epigenetic dysregulations are closely related to the development of KIRC. Cancer immunotherapy is an effective treatment for cancers. The aim of this study was to identify immune-related differentially expressed genes (IR-DEGs) associated with aberrant methylations and construct a risk assessment model using these IR-DEGs to predict the prognosis of KIRC. Two IR-DEGs (SLC11A1 and TNFSF14) were identified by differential expression, correlation analysis, and Cox regression analysis, and risk assessment models were established. The area under the receiver operating characteristic (ROC) curve (AUC) was 0.6907. In addition, we found that risk scores were significantly associated with 31 immune cells and factors. Our present study not only shows that two IR-DEGs can be used as prognosis signatures for KIRC, but also provides a strategy for the screening of suitable prognosis signatures associated with aberrant methylation in other cancers.

scholarly journals Immune-Related Gene Expression Analysis Revealed Three lncRNAs as Prognostic Factors for Colon Cancer

2021 ◽  
Vol 12 ◽  
Author(s):  
Xiao-Liang Xing ◽  
Ti Zhang ◽  
Zhi-Yong Yao ◽  
Chaoqun Xing ◽  
Chunxiao Wang ◽  
...  
Keyword(s):  
Risk Assessment ◽  
Gene Expression Analysis ◽  
Operating Characteristic ◽  
Cox Regression ◽  
Area Under The Curve ◽  
Assessment Model ◽  
Risk Assessment Model ◽  
Immune Related Gene ◽  
Non Coding Rnas

Colorectal cancer (CRC) is one of the most common cancers. Almost 80% of CRC cases are colon adenocarcinomas (COADs). Several studies have indicated the role of immunotherapy in the treatment of various cancers. Our study aimed to identify immune-related long non-coding RNAs (lncRNAs) and to use them to construct a risk assessment model for evaluating COAD prognosis. Using differential expression, correlation, and Cox regression analyses, we identified three immune-related differentially expressed lncRNAs (IR-DELs) and used them to construct a risk assessment model. The area under the curve (AUC) for each receiver operating characteristic (ROC) curve at 3-, 5-, and 10-years were greater than 0.6. In addition, the risk assessment model was correlated with several immune cells and factors. The three IR-DELs (AC124067.4, LINC02604, and MIR4435-2HG) identified in this study can be used to predict outcomes for patients with COAD and might help in identifying those who can benefit from anti-tumor immunotherapy.

Sign in / Sign up

Export Citation Format

Share Document