Violations of proportional hazard assumption in Cox regression model of transcriptomic data in TCGA pan-cancer cohorts

Abstract Background: Utilizing genomic data to predict cancer prognosis was insufficient. Proteomics can improve our understanding of the etiology and progression of cancer and improve the assessment of cancer prognosis. Based on CPTAC (Clinical Proteomic Tumor Analysis Consortium) which has generated extensive proteomics data of the vast majority of tumors, we can perform a proteomic pan-carcinoma analysis.Methods: The proteomics data and clinical features of cancer patients were collected from CPTAC. We screened 69 differentially expressed proteins with R software. GO and KEGG analysis were performed to clarify the function of these proteins. The DEPs-based prognostic model was identified by least absolute shrinkage and selection operator (LASSO)-Cox regression model. The time-dependent receiver operating characteristics analysis was used to evaluate the ability of the prognostic model to predict overall survival.Results: A total of 69 differentially expressed proteins were screened in five different types of cancers: hepatocellular carcinoma (HCC), lung adenocarcinoma (LUAD), children's brain tumor tissue consortium (CBTTC), clear cell renal cell carcinoma (CCRC) and uterine corpus endometrial carcinoma (UCEC). Furthermore, the differentially expressed proteins were related to cell metabolism, cell proliferation and extracellular matrix. Then 24 DEPs-based classifiers for predicting OS was developed by LASSO-Cox regression model in training cohort, which was validated in validation cohort. Conclusions: In the present study, we identified DEPs-based survival-predictor model to predict most cancers. We are the first group to utilize proteomics to construct a pan-cancer prognosis model, which could accurately and effectively predict the survival rate of most cancers.

Download Full-text

813. The Reduction of the acquisition rate of carbapenem resistant Acinetobacter baumannii after room privatization in the intensive care unit

Open Forum Infectious Diseases ◽

10.1093/ofid/ofaa439.1002 ◽

2020 ◽

Vol 7 (Supplement_1) ◽

pp. S448-S449

Author(s):

Jongtak Jung ◽

Pyoeng Gyun Choe ◽

Chang Kyung Kang ◽

Kyung Ho Song ◽

Wan Beom Park ◽

...

Keyword(s):

Regression Model ◽

Acinetobacter Baumannii ◽

Cox Regression ◽

Univariate Analysis ◽

Intervention Group ◽

Feeding Tube ◽

Control Group ◽

Cox Regression Model ◽

Carbapenem Resistant ◽

Hospital Acquired

Abstract Background Acinetobacter baumannii is one of the major pathogens of hospital-acquired infection recently and hospital outbreaks have been reported worldwide. On September 2017, New intensive care unit(ICU) with only single rooms, remodeling from old ICU with multibed bay rooms, was opened in an acute-care tertiary hospital in Seoul, Korea. We investigated the effect of room privatization in the ICU on the acquisition of carbapenem-resistant Acinetobacter baumannii(CRAB). Methods We retrospectively reviewed medical records of patients who admitted to the medical ICU in a tertiary care university-affiliated 1,800-bed hospital from 1 January 2015 to 1 January 2019. Patients admitted to the medical ICU before the remodeling of the ICU were designated as the control group, and those who admitted to the medical ICU after the remodeling were designated as the intervention group. Then we compared the acquisition rate of CRAB between the control and intervention groups. Patients colonized with CRAB or patients with CRAB identified in screening tests were excluded from the study population. The multivariable Cox regression model was performed using variables with p-values of less than 0.1 in the univariate analysis. Results A total of 1,105 cases admitted to the ICU during the study period were analyzed. CRAB was isolated from 110 cases in the control group(n=687), and 16 cases in the intervention group(n=418). In univariate analysis, room privatization, prior exposure to antibiotics (carbapenem, vancomycin, fluoroquinolone), mechanical ventilation, central venous catheter, tracheostomy, the presence of feeding tube(Levin tube or percutaneous gastrostomy) and the length of ICU stay were significant risk factors for the acquisition of CRAB (p< 0.05). In the multivariable Cox regression model, the presence of feeding tube(Hazard ratio(HR) 4.815, 95% Confidence interval(CI) 1.94-11.96, p=0.001) and room privatization(HR 0.024, 95% CI 0.127-0.396, p=0.000) were independent risk factors. Table 1. Univariate analysis of Carbapenem-resistant Acinetobacter baumannii Table 2. Multivariable Cox regression model of the acquisition of Carbapenem-resistant Acinetobacter baumannii Conclusion In the present study, room privatization of the ICU was correlated with the reduction of CRAB acquisition independently. Remodeling of the ICU to the single room would be an efficient strategy for preventing the spreading of multidrug-resistant organisms and hospital-acquired infection. Disclosures All Authors: No reported disclosures

Download Full-text

Testing the proportional hazards assumption in cox regression and dealing with possible non-proportionality in total joint arthroplasty research: methodological perspectives and review

BMC Musculoskeletal Disorders ◽

10.1186/s12891-021-04379-2 ◽

2021 ◽

Vol 22 (1) ◽

Author(s):

Ilari Kuitunen ◽

Ville T. Ponkilainen ◽

Mikko M. Uimonen ◽

Antti Eskelinen ◽

Aleksi Reito

Keyword(s):

Survival Analysis ◽

Regression Model ◽

Total Joint Arthroplasty ◽

Full Text ◽

Proportional Hazards ◽

Cox Regression ◽

Joint Arthroplasty ◽

Central Research ◽

Cox Regression Model ◽

Pubmed Database

Abstract Background Survival analysis and effect of covariates on survival time is a central research interest. Cox proportional hazards regression remains as a gold standard in the survival analysis. The Cox model relies on the assumption of proportional hazards (PH) across different covariates. PH assumptions should be assessed and handled if violated. Our aim was to investigate the reporting of the Cox regression model details and testing of the PH assumption in survival analysis in total joint arthroplasty (TJA) studies. Methods We conducted a review in the PubMed database on 28th August 2019. A total of 1154 studies were identified. The abstracts of these studies were screened for words “cox and “hazard*” and if either was found the abstract was read. The abstract had to fulfill the following criteria to be included in the full-text phase: topic was knee or hip TJA surgery; survival analysis was used, and hazard ratio reported. If all the presented criteria were met, the full-text version of the article was then read. The full-text was included if Cox method was used to analyze TJA survival. After accessing the full-texts 318 articles were included in final analysis. Results The PH assumption was mentioned in 114 of the included studies (36%). KM analysis was used in 281 (88%) studies and the KM curves were presented graphically in 243 of these (87%). In 110 (45%) studies, the KM survival curves crossed in at least one of the presented figures. The most common way to test the PH assumption was to inspect the log-minus-log plots (n = 59). The time-axis division method was the most used corrected model (n = 30) in cox analysis. Of the 318 included studies only 63 (20%) met the following criteria: PH assumption mentioned, PH assumption tested, testing method of the PH assumption named, the result of the testing mentioned, and the Cox regression model corrected, if required. Conclusions Reporting and testing of the PH assumption and dealing with non-proportionality in hip and knee TJA studies was limited. More awareness and education regarding the assumptions behind the used statistical models among researchers, reviewers and editors are needed to improve the quality of TJA research. This could be achieved by better collaboration with methodologists and statisticians and introducing more specific reporting guidelines for TJA studies. Neglecting obvious non-proportionality undermines the overall research efforts since causes of non-proportionality, such as possible underlying pathomechanisms, are not considered and discussed.

Download Full-text

FRI0181 ORGAN DAMAGE FREE SURVIVAL IN SOUTHERN CHINESE PATIENTS WITH ACTIVE LUPUS NEPHRITIS

Annals of the Rheumatic Diseases ◽

10.1136/annrheumdis-2020-eular.2552 ◽

2020 ◽

Vol 79 (Suppl 1) ◽

pp. 674.1-674

Author(s):

C. C. Mok ◽

C. S. Sin ◽

K. C. Hau ◽

T. H. Kwan

Keyword(s):

Lupus Nephritis ◽

Regression Model ◽

Cox Regression ◽

Organ Damage ◽

Renal Survival ◽

Cox Regression Model ◽

Free Survival ◽

Renal Response

Background:The goals of treatment of lupus nephritis (LN) are to induce remission, retard the progression of chronic kidney disease, prevent organ complications and ultimately reduce mortality. Previous cohort studies of LN have mainly focused on the risk of mortality and development of end stage renal failure (ESRF) (renal survival). The cumulative frequency of LN patients who survive without organ damage, which correlates better with the balance between treatment efficacy and toxicity, as well as quality of life, has not been well studied.Objectives:To study the organ damage free survival and its predictive factors in patients with active LN.Methods:Consecutive patients who fulfilled ≥4 ACR/SLICC criteria for SLE and with biopsy proven active LN between 2003 and 2018 were retrospectivey analyzed. Those with organ damage before LN onset were excluded. Data on renal parameters and treatment regimens were collected. Complete renal response (CR) was defined as normalization of serum creatinine (SCr), urine P/Cr (uPCR) <0.5 and inactive urinary sediments. Partial renal response (PR) was defined as ≥50% reduction in uPCR and <25% increase in SCr. Organ damage of SLE was assessed by the ACR/SLICC damage index (SDI). The cumulative risk of having any organ damage or mortality since LN was studied by Kaplan-Meier’s analysis. Factors associated with a poor outcome were studied by a forward stepwise Cox regression model, with entry of covariates with p<0.05 and removal with p>0.10.Results:273 LN patients were identified but 64 were excluded (organ damage before LN onset). 211 LN patients were studied (92% women; age at SLE 30.4±13.5 years; SLE duration at LN 1.9±3.1years). 47 (22%) patients had nephrotic syndrome and 60 (29%) were hypertensive. Histological LN classes was: III/IV±V (75.1%), I/II (7.8%) and pure V (17.1%) (histologic activity and chronicity score 7.0±4.2 and 1.8±1.5, respectively). Induction regimens were: prednisolone (33.1±17.5mg/day) in combination with intravenous cyclophosphamide (CYC) (21.4%; 1.0±0.2g per pulse), oral CYC (8.6%; 96.4±37.8mg/day), azathioprine (AZA) (14.3%; 78.6±25.2mg/day), mycophenolate mofetil (MMF) (22.8%; 1.9±0.43g/day) and tacrolimus (TAC) (17.1%; 4.3±1.1mg/day). After a follow-up of 8.6±5.4 years, 94(45%) patient developed organ damage (SDI≥1) and 21(10%) patients died. The commonest organ damage was renal (36.3%) and musculoskeletal (17.9%), and the causes of death were: infection (38.1%), malignancy (19.0%), cardiovascular events (9.5%) and ESRF complications (9.5%). At last visit, 114 (55%) patients survived without any organ damage. The cumulative organ damage free survival at 5, 10 and 15 years after renal biopsy was 73.5%, 59.6% and 48.3%, respectively. The 5, 10 and 15-year renal survival rate were 95.2%, 92.0% and 84.1% respectively. In a Cox regression model, nephritic relapse (HR 3.72[1.78-7.77]), proteinuric relapse (HR 2.30[1.07-4.95]) and older age (HR 1.89[1.05-3.37]) were associated with either organ damage or mortality, whereas CR (HR 0.25[0.12-0.50]) at month 12 were associated with organ damage free survival. Baseline SCr, uPCR and histological LN classes were not significantly associated with a poor outcome. Among patients with class III/IV LN, the long-term organ damage free survival were not significantly different in users of MMF (reference) from CYC (IV/oral) (HR 1.45[0.76- 2.75]) or TAC (HR 1.03[0.26-1.62]) as induction therapy.Conclusion:Organ damage free survival is achieved in 55% of patients with active LN upon 9 years of follow-up. CYC/MMF/TAC based induction regimens did not differ for the long-term outcome of LN. Targeting complete renal response and preventing renal relapses remain important goals of LN treatment.Acknowledgments:NILDisclosure of Interests:None declared

Download Full-text

The effect of censoring on a multivariate cox regression model comparing surgical and medical treatment for aortic disease patients

Controlled Clinical Trials ◽

10.1016/s0197-2456(98)80190-6 ◽

1998 ◽

Vol 19 (3) ◽

pp. S78-S79

Author(s):

Charles Oprian ◽

Kwan Hur ◽

William Henderson ◽

Bharat Thakkar ◽

Frederick Masoudi ◽

...

Keyword(s):

Medical Treatment ◽

Regression Model ◽

Cox Regression ◽

Aortic Disease ◽

Cox Regression Model

Download Full-text

Cox regression survival analysis with compositional covariates: Application to modelling mortality risk from 24-h physical activity patterns

Statistical Methods in Medical Research ◽

10.1177/0962280219864125 ◽

2019 ◽

Vol 29 (5) ◽

pp. 1447-1465 ◽

Cited By ~ 11

Author(s):

DE McGregor ◽

J Palarea-Albaladejo ◽

PM Dall ◽

K Hron ◽

SFM Chastin

Keyword(s):

Public Health ◽

Physical Activity ◽

Survival Analysis ◽

Regression Model ◽

Cox Regression ◽

Public Health Problem ◽

Sitting Time ◽

Cox Regression Model ◽

Log Ratio ◽

Activity Behaviour

Survival analysis is commonly conducted in medical and public health research to assess the association of an exposure or intervention with a hard end outcome such as mortality. The Cox (proportional hazards) regression model is probably the most popular statistical tool used in this context. However, when the exposure includes compositional covariables (that is, variables representing a relative makeup such as a nutritional or physical activity behaviour composition), some basic assumptions of the Cox regression model and associated significance tests are violated. Compositional variables involve an intrinsic interplay between one another which precludes results and conclusions based on considering them in isolation as is ordinarily done. In this work, we introduce a formulation of the Cox regression model in terms of log-ratio coordinates which suitably deals with the constraints of compositional covariates, facilitates the use of common statistical inference methods, and allows for scientifically meaningful interpretations. We illustrate its practical application to a public health problem: the estimation of the mortality hazard associated with the composition of daily activity behaviour (physical activity, sitting time and sleep) using data from the U.S. National Health and Nutrition Examination Survey (NHANES).

Download Full-text

Adjusted score functions for monotone likelihood in the Cox regression model

Statistics in Medicine ◽

10.1002/sim.8496 ◽

2020 ◽

Vol 39 (10) ◽

pp. 1558-1572

Author(s):

Euloge C. Kenne Pagui ◽

Enrico A. Colosimo

Keyword(s):

Regression Model ◽

Cox Regression ◽

Cox Regression Model ◽

Score Functions ◽

Adjusted Score

Download Full-text

Yaşam çözümlemesinde zamana bağlı açıklayıcı değişkenli Cox regresyon modeli Cox regression model with time dependent covariate in survival anaysis

Ankara Üniversitesi Tıp Fakültesi Mecmuası ◽

10.1501/tipfak_0000000176 ◽

2005 ◽

Vol 58 (4) ◽

pp. 1

Author(s):

SERTKAYA Durdu

Keyword(s):

Regression Model ◽

Cox Regression ◽

Time Dependent ◽

Cox Regression Model

Download Full-text

Prosthetic complications of fixed dental prostheses supported by locking-taper implants: A retrospective study with a mean follow-up of 5 years.

10.21203/rs.3.rs-228445/v1 ◽

2021 ◽

Author(s):

Wen Mo Gao ◽

Wei Geng ◽

Chen Chen Luo

Keyword(s):

Retrospective Study ◽

Bone Loss ◽

Regression Model ◽

Protective Factor ◽

Cox Regression ◽

Marginal Bone Loss ◽

Cox Regression Model ◽

Prosthetic Complications ◽

Free Rate

Abstract Background: Restoration with locking-taper implants is a widely used methodology. However, relatively few have examined conical connection systems like locking-taper implant systems. This study provides a retrospective study of locking-taper fixed restorations, mainly focused on prosthetic complications.Methods: All patients who underwent conical connected implants from 2008–2010 were examined. Preparation of the implant sites was performed according to the standard procedures for the Bicon system. The bone healing took over 6 months, and the prosthetic procedure was initiated thereafter. Integrated abutment crowns or gold porcelain crowns were used, and the prosthesis type was a single crown or a fixed dental prosthesis. Once the crown was in place, its occlusion was thoroughly checked and adjusted, and then the crown was glazed or finely polished. The Kaplan-Meier method was used to calculate the cumulative complication-free rates for 5 and 10 years. Additionally, a Cox regression model was used to identify the factors that independently influenced the results. Implant survival and marginal bone loss were also investigated.Results: A total of 392 patients who underwent 541 implants and 434 locking taper implant-based restorations from 2008–2010 were examined. The overall 5-year cumulative complication-free rate was 83.34%. The most common prosthetic complication was veneer chipping, with a frequency of 67.53%. According to the Cox regression model, the complication-free rate of integrated abutment crowns was significantly higher than gold porcelain crowns, molar regions was significantly higher than premolar regions, and females was significantly higher than males. Only three implant failures happened, and a mean marginal bone loss at 1- year, 5-year and 10- year was 0.25mm（95%CI：±0.12）, 0.40mm （95%CI：±0.03）and 0.51mm（95%CI：±0.05）, respectively.Conclusion: Veneer chipping was the most common complication with locking-taper implants supported fixed restorations. According to the result of Cox regression model, gold porcelain crowns are a protective factor relative to integrated abutment crowns, male sex is a protective factor relative to female sex, and premolar prosthetics are a protective factor relative to molar prosthetics. The long-term clinical effect of locking-taper implant is stable, and the implant success rate can meet the clinical needs. The bone tissue level around the implant can maintain long-term stability.

Download Full-text