Feasibility of reusing time-matched controls in an overlapping cohort

2016 ◽  
Vol 27 (6) ◽  
pp. 1818-1829 ◽  
Author(s):  
Bénédicte Delcoigne ◽  
Niels Hagenbuch ◽  
Maria EC Schelin ◽  
Agus Salim ◽  
Linda S Lindström ◽  
...  
Keyword(s):  
Cox Regression ◽  
Secondary Analysis ◽  
Sampling Bias ◽  
Case Control ◽  
Control Data ◽  
Kaplan Meier ◽  
Hazard Ratios ◽  
Multifocal Tumor ◽  
Nested Case Control ◽  
Study Base

The methods developed for secondary analysis of nested case-control data have been illustrated only in simplified settings in a common cohort and have not found their way into biostatistical practice. This paper demonstrates the feasibility of reusing prior nested case-control data in a realistic setting where a new outcome is available in an overlapping cohort where no new controls were gathered and where all data have been anonymised. Using basic information about the background cohort and sampling criteria, the new cases and prior data are “aligned” to identify the common underlying study base. With this study base, a Kaplan–Meier table of the prior outcome extracts the risk sets required to calculate the weights to assign to the controls to remove the sampling bias. A weighted Cox regression, implemented in standard statistical software, provides unbiased hazard ratios. Using the method to compare cases of contralateral breast cancer to available controls from a prior study of metastases, we identified a multifocal tumor as a risk factor that has not been reported previously. We examine the sensitivity of the method to an imperfect weighting scheme and discuss its merits and pitfalls to provide guidance for its use in medical research studies.

071 Natalizumab extended interval dosing (EID) is associated with a significant reduction in progressive multifocal leukoencephalopathy (PML) risk compared with standard interval dosing (SID) in the touch® prescribing program

2018 ◽  
Vol 89 (6) ◽  
pp. A29.2-A29 ◽  
Author(s):  
Lana Zhovtis Ryerson ◽  
John Foley ◽  
Ih Chang ◽  
Ilya Kister ◽  
Gary Cutter ◽  
...  
Keyword(s):  
Cox Regression ◽  
Jc Virus ◽  
Secondary Analysis ◽  
Statistical Analysis Plan ◽  
Rank Test ◽  
Primary Analysis ◽  
Standard Interval ◽  
Kaplan Meier ◽  
Hazard Ratios ◽  
Dosing Intervals

IntroductionNatalizumab, approved for 300 mg intravenous every-4-weeks dosing, is associated with PML risk. Prior studies have been inconclusive regarding EID’s impact on PML risk. The US REMS program (TOUCH) offers the largest data source that can inform on PML risk in patients on EID. This analysis aimed to determine whether natalizumab EID is associated with reduced PML risk compared with SID.MethodsInvestigators developed SID and EID definitions and finalised the statistical analysis plan while blinded to PML events. Average dosing intervals (ADIs) were ≥3 to<5 weeks for SID and >5 to≤12 weeks for EID. The primary analysis assessed ADI in the last 18 months of infusion history. The secondary analysis identified any prolonged period of EID at any time in the infusion history. The tertiary analysis assessed ADI over the full infusion history. Only anti-JC virus antibody positive (JCV Ab+) patients with dosing intervals≥3 to≤12 weeks were included. PML hazard ratios (HRs) were compared using adjusted Cox regression models and Kaplan-Meier estimates.ResultsAnalyses included 13,132 SID and 1988 EID patients (primary), 15,424 SID and 3331 EID patients (secondary), and 23,168 SID and 815 EID patients (tertiary). In primary analyses, ADI (days) was 30 for SID and 37 for EID; median exposure (months) was 44 for SID and 59 for EID. Most EID patients received >2 years SID prior to EID. The PML HR (95% CI) was 0.06 (0.01–0.22; p<0.001) for primary analysis and 0.12 (0.05–0.29; p<0.001) for secondary analysis (both in favour of EID); no EID PML cases were observed in tertiary analyses (Kaplan-Meier log-rank test p=0.02).ConclusionIn JCV Ab +patients, natalizumab EID is associated with a clinically and statistically significant reduction in PML risk as compared with SID. As TOUCH does not collect effectiveness data, further studies are needed.Study supportBiogen

A maximum likelihood method for secondary analysis of nested case-control data

2014 ◽  
Vol 33 (11) ◽  
pp. 1842-1852 ◽  
Author(s):  
Agus Salim ◽  
Ma Xiangmei ◽  
Li Jialiang ◽  
Marie Reilly
Keyword(s):  
Maximum Likelihood ◽  
Maximum Likelihood Method ◽  
Secondary Analysis ◽  
Case Control ◽  
Likelihood Method ◽  
Control Data ◽  
Nested Case Control

scholarly journals Long-term risk of a major cardiovascular event by apoB, apoA-1, and the apoB/apoA-1 ratio—Experience from the Swedish AMORIS cohort: A cohort study

PLoS Medicine ◽  
2021 ◽  
Vol 18 (12) ◽  
pp. e1003853
Author(s):  
Göran Walldius ◽  
Ulf de Faire ◽  
Lars Alfredsson ◽  
Karin Leander ◽  
Peter Westerholm ◽  
...  
Keyword(s):  
Cohort Study ◽  
Cox Regression ◽  
Early Recognition ◽  
Age Groups ◽  
Major Adverse Cardiovascular Events ◽  
Men And Women ◽  
Kaplan Meier ◽  
Hazard Ratios ◽  
Nested Case Control ◽  
The Impact

Background Elevated apolipoprotein B (apoB) and elevated apoB/apoA-1 ratio increase the risk of myocardial infarction (MI) and stroke, whereas high apoA-1 is protective. We study how these apolipoproteins are associated with major adverse cardiovascular events (MACEs), whether apoA-1 contributes to this association, and whether abnormal values occur decades before such events develop. Methods and findings In the Swedish AMORIS (Apolipoprotein-related MOrtality RISk) cohort study, 137,100 men and women aged 25–84 years were followed an average 17.8 years. ApoB, apoA-1, and the apoB/apoA-1 ratio were analysed in relation to MACEs (non-fatal MI, stroke, and cardiovascular [CV] mortality), yielding 22,473 events. Hazard ratios (HRs) were estimated using Cox regression. Kaplan–Meier estimates were used to investigate the relationship of MACEs with increasing quintiles of the apoB/apoA-1 ratio in all age groups for both sexes. In nested case–control analyses, cases were randomly matched to age- and sex-matched controls, yielding population trajectories for apolipoproteins. Increased level of apoB and increased apoB/apoA-1 ratio were associated with risk of MACE and all clinical sub-components in both men and women across all ages (10th versus first decile in both sexes combined: HR 1.7 for MACE and 2.7 for non-fatal MI). Decreased values of apoA-1 potentiated the impact of apoB at all levels of apoB (on average across apoB range: 40% increase in HR for MACE and 72% increase in HR for non-fatal MI), indicating that the apoB/apoA-1 ratio covers a broader range of persons with dyslipidaemia at risk than apoB alone. In both men and women, MACEs occurred earlier on average for each increasing quintile of the apoB/apoA-1 ratio. Individuals with the highest levels of apoB/apoA-1 ratio experienced CV events on average several years earlier than those with lower ratios. Higher apoB/apoA-1 ratio in cases of MACE versus controls was seen already about 20 years before the event. A limitation of this study was that adjustment for tobacco smoking and hypertension was only possible in a small validation study. Conclusions An imbalance between apoB and apoA-1 resulting in an increased apoB/apoA-1 ratio is strongly associated with the outcome MACE and its sub-components, in both men and women of all ages. An increased apoB/apoA-1 ratio already 2 decades before events calls for early recognition and primary prevention. Simple evidence-based cut values should be considered in future cardiovascular guidelines.

Infections seem to be more frequent before onset of pediatric multiple sclerosis: A Danish nationwide nested case–control study

2018 ◽  
Vol 25 (6) ◽  
pp. 783-791 ◽  
Author(s):  
Magnus Spangsberg Boesen ◽  
Nils Koch-Henriksen ◽  
Lau Caspar Thygesen ◽  
Frank Eriksson ◽  
Gorm Greisen ◽  
...  
Keyword(s):  
Multiple Sclerosis ◽  
Case Control Study ◽  
Cox Regression ◽  
Case Control ◽  
Cumulative Number ◽  
Childhood Infections ◽  
Clinical Onset ◽  
Hazard Ratios ◽  
Nested Case Control ◽  
Control Study

Background: Infections are suspected environmental triggers for multiple sclerosis (MS). The relationship between the timing and cumulative number of childhood infections regarding pediatric MS risk is uninvestigated. Objectives: To investigate whether childhood infections contribute to pediatric MS. Methods: A nationwide nested case–control study with detailed MS case ascertainment including chart review was undertaken. For each MS case, we selected five control children using density sampling from the entire Danish population, matching controls to children with MS by sex and birthdate. We analyzed data with the cumulative number of childhood infections as exposure and MS as outcome. Hazard ratios (HRs) including 95% confidence intervals (CIs) were estimated using Cox regression. Results: We identified 212 children with MS and 1,060 controls. Median age at MS onset was 15.3 years (range: 7.6–17.8 years); 72% were girls. Each infection during the preceding 3 years increased the hazard for MS by 11% (95% CI = 1.01–1.22, p = 0.04); having 5+ infections compared with 0–4 infections in the preceding 3 years doubled the hazard for MS (HR: 2.18; 95% CI = 1.12–4.30, p = 0.02). Conclusion: Children with MS appeared to have more infections in the 3 years preceding MS clinical onset; accordingly, immune response to infections may influence MS pathogenesis.

scholarly journals Infarct Topography and Detection of Atrial Fibrillation in Cryptogenic Stroke: Results from CRYSTAL AF

2015 ◽  
Vol 40 (1-2) ◽  
pp. 91-96 ◽  
Author(s):  
Richard A. Bernstein ◽  
Vincenzo Di Lazzaro ◽  
Marilyn M. Rymer ◽  
Rod S. Passman ◽  
Johannes Brachmann ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Cox Regression ◽  
Brain Infarction ◽  
Cryptogenic Stroke ◽  
Monitoring Methods ◽  
Brain Images ◽  
Kaplan Meier ◽  
Imaging Characteristics ◽  
Hazard Ratios ◽  
Routine Monitoring

Background: Insertable cardiac monitors (ICM) have been shown to detect atrial fibrillation (AF) at a higher rate than routine monitoring methods in patients with cryptogenic stroke (CS). However, it is unknown whether there are topographic patterns of brain infarction in patients with CS that are particularly associated with underlying AF. If such patterns exist, these could be used to help decide whether or not CS patients would benefit from long-term monitoring with an ICM. Methods: In this retrospective analysis, a neuro-radiologist blinded to clinical details reviewed brain images from 212 patients with CS who were enrolled in the ICM arm of the CRYptogenic STroke And underLying AF (CRYSTAL AF) trial. Kaplan-Meier estimates were used to describe rates of AF detection at 12 months in patients with and without pre-specified imaging characteristics. Hazard ratios (HRs), 95% confidence intervals (CIs), and p values were calculated using Cox regression. Results: We did not find any pattern of acute brain infarction that was significantly associated with AF detection after CS. However, the presence of chronic brain infarctions (15.8 vs. 7.0%, HR 2.84, 95% CI 1.13-7.15, p = 0.02) or leukoaraiosis (18.2 vs. 7.9%, HR 2.94, 95% CI 1.28-6.71, p < 0.01) was associated with AF detection. There was a borderline significant association of AF detection with the presence of chronic territorial (defined as within the territory of a first or second degree branch of the circle of Willis) infarcts (20.9 vs. 10.0%, HR 2.37, 95% CI 0.98-5.72, p = 0.05). Conclusions: We found no evidence for an association between brain infarction pattern and AF detection using an ICM in patients with CS, although patients with coexisting chronic, as well as acute, brain infarcts had a higher rate of AF detection. Acute brain infarction topography does not reliably predict or exclude detection of underlying AF in patients with CS and should not be used to select patients for ICM after cryptogenic stroke.

H3K27M-mutant Diffuse Midline Gliomas should be Further Molecularly Stratified: An Integrated Analysis of 669 Patients

2021 ◽  
Author(s):  
Huy Gia Vuong ◽  
Hieu Trong Le ◽  
Tam N.M. Ngo ◽  
Kar-Ming Fung ◽  
James D. Battiste ◽  
...  
Keyword(s):  
Cox Regression ◽  
Fatal Outcome ◽  
Extent Of Resection ◽  
Tumor Location ◽  
Genetic Alterations ◽  
Integrated Analysis ◽  
Prognostic Impact ◽  
Kaplan Meier ◽  
Hazard Ratios ◽  
The Impact

Abstract Introduction: H3K27M-mutated diffuse midline gliomas (H3-DMGs) are aggressive tumors with a fatal outcome. This study integrating individual patient data (IPD) from published studies aimed to investigate the prognostic impact of different genetic alterations on survival of these patients.Methods: We accessed PubMed and Web of Science to search for relevant articles. Studies were included if they have available data of follow-up and additional molecular investigation of H3-DMGs. For survival analysis, Kaplan-Meier analysis and Cox regression models were utilized, and corresponding hazard ratios (HR) and 95% confidence intervals (CI) were computed to analyze the impact of genetic events on overall survival (OS).Result: We included 30 studies with 669 H3-DMGs. TP53 mutations were the most common second alteration among these neoplasms. In univariate Cox regression model, TP53 mutation was an indicator of shortened survival (HR = 1.446; 95% CI = 1.143-1.829) whereas ACVR1 (HR = 0.712; 95% CI = 0.518-0.976) and FGFR1 mutations (HR = 0.408; 95% CI = 0.208-0.799) conferred prolonged survival. In addition, ATRX loss was also associated with a better OS (HR = 0.620; 95% CI = 0.386-0.996). Adjusted for age, gender, tumor location, and the extent of resection, the presence of TP53 mutations, the absence of ACVR1 or FGFR1 mutations remained significantly poor prognostic factors.Conclusions: We outlined the prognostic importance of additional genetic alterations in H3-DMGs and recommended that these neoplasms should be further molecularly segregated. It could help neuro-oncologists better evaluate the risk stratification of patients and consider pertinent treatments.

scholarly journals Prognostic Potential of Liver Enzymes in Patients With COVID-19 at the Leishenshan Hospital in Wuhan

2021 ◽  
Vol 11 ◽  
Author(s):  
Zeming Liu ◽  
Di Hu ◽  
Jinpeng Li ◽  
Qing Xia ◽  
Yan Gong ◽  
...  
Keyword(s):  
Liver Function ◽  
Liver Enzymes ◽  
Cox Regression ◽  
Liver Function Tests ◽  
Regression Analyses ◽  
Survival Curves ◽  
Severity Of Disease ◽  
Kaplan Meier ◽  
Hazard Ratios ◽  
Disease Mortality

BackgroundCoronavirus disease 2019 (COVID-19) has evolved into a pandemic. We hypothesized that biochemical indicators of liver function may help determine the prognosis of COVID-19 patients.MethodsPatient information was collected from the Wuhan-Leishenshan hospital. Logistic and Cox regression analyses, Kaplan-Meier curves, and Curve fitting were used to determine the correlation between elevated levels of aspartate transaminase (AST), alanine transaminase (ALT), and AST/ALT and severity of disease/mortality.ResultsLogistic and Cox regression analyses and Kaplan-Meier survival curves showed that COVID-19 progression correlated with elevated levels of AST and AST/ALT. The odds ratios for elevated levels of AST and AST/ALT in patients were 0.818 (95% confidence interval [CI]: 0.274-2.441, P = 0.035) and 2.055 (95% CI: 1.269-3.327, P = 0.003), respectively; the hazard ratios were 4.195 (95% CI: 1.219-14.422, P = 0.023) and 3.348 (95% CI: 1.57-7.139, P = 0.002), respectively. The Kaplan-Meier survival curves demonstrated that patients with elevated AST and AST/ALT levels had a higher risk of developing severe COVID-19.ConclusionElevated AST and AST/ALT levels correlated with severity of COVID-19 and mortality. Liver function tests may help clinicians in determining the prognosis of patients undergoing treatment for COVID-19.

scholarly journals Application of the matched nested case-control design to the secondary analysis of trial data

2020 ◽  
Author(s):  
Christopher Partlett ◽  
Nigel J Hall ◽  
Alison Leaf ◽  
Edmund Juszczak ◽  
Louise Linsell
Keyword(s):  
Clinical Trial ◽  
Case Control Study ◽  
Secondary Analysis ◽  
Control Design ◽  
Case Control ◽  
Necrotising Enterocolitis ◽  
Trial Data ◽  
Standard Case ◽  
Nested Case Control ◽  
Control Study

Abstract Background A nested case-control study is an efficient design that can be embedded within an existing cohort study or randomised trial. It has a number of advantages compared to the conventional case-control design, and has the potential to answer important research questions using untapped prospectively collected data. Methods We demonstrate the utility of the matched nested case-control design by applying it to a secondary analysis of the Abnormal Doppler Enteral Prescription Trial. We investigated the role of milk feed type and changes in milk feed type in the development of necrotising enterocolitis in a group of 398 high risk growth-restricted preterm infants. Results Using matching, we were able to generate a comparable sample of controls selected from the same population as the cases. In contrast to the standard case-control design, exposure status was ascertained prior to the outcome event occurring and the comparison between the cases and matched controls could be made at the point at which the event occurred. This enabled us to reliably investigate the temporal relationship between feed type and necrotising enterocolitis. Conclusions A matched nested case-control study can be used to identify credible associations in a secondary analysis of clinical trial data where the exposure of interest was not randomised, and has several advantages over a standard case-control design. This method offers the potential to make reliable inferences in scenarios where it would be unethical or impractical to perform a randomised clinical trial.

scholarly journals Estimation of Relative and Absolute Risks in a Competing-Risks Setting Using a Nested Case-Control Study Design: Example From the ProMort Study

2019 ◽  
Vol 188 (6) ◽  
pp. 1165-1173 ◽  
Author(s):  
Renata Zelic ◽  
Daniela Zugna ◽  
Matteo Bottai ◽  
Ove Andrén ◽  
Jonna Fridfeldt ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Competing Risks ◽  
Case Control Study ◽  
Case Control ◽  
Likelihood Method ◽  
Cancer Death ◽  
Hazard Ratios ◽  
Prostate Cancer Death ◽  
Nested Case Control ◽  
Control Study

Abstract In this paper, we describe the Prognostic Factors for Mortality in Prostate Cancer (ProMort) study and use it to demonstrate how the weighted likelihood method can be used in nested case-control studies to estimate both relative and absolute risks in the competing-risks setting. ProMort is a case-control study nested within the National Prostate Cancer Register (NPCR) of Sweden, comprising 1,710 men diagnosed with low- or intermediate-risk prostate cancer between 1998 and 2011 who died from prostate cancer (cases) and 1,710 matched controls. Cause-specific hazard ratios and cumulative incidence functions (CIFs) for prostate cancer death were estimated in ProMort using weighted flexible parametric models and compared with the corresponding estimates from the NPCR cohort. We further drew 1,500 random nested case-control subsamples of the NPCR cohort and quantified the bias in the hazard ratio and CIF estimates. Finally, we compared the ProMort estimates with those obtained by augmenting competing-risks cases and by augmenting both competing-risks cases and controls. The hazard ratios for prostate cancer death estimated in ProMort were comparable to those in the NPCR. The hazard ratios for dying from other causes were biased, which introduced bias in the CIFs estimated in the competing-risks setting. When augmenting both competing-risks cases and controls, the bias was reduced.

Sign in / Sign up

Export Citation Format

Share Document