Addressing the issue of channeling bias in observational studies with propensity scores analysis

Lobo, Francis; Wagner, Samuel; Gross, Cynthia R.; Schommer, Jon C.

doi:10.1016/j.sapharm.2005.12.001

Cited by 69 publications

(54 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…3,4 Neither study evaluated lipid levels; however, the current study had equal use of statin therapies across groups. After the publication of the Gerritus study, Winkelmayer et al 16 found a 13% greater risk of AHF (incident rate ratio, 1.13; 95% CI, 1.01 to 1.26) and 15% greater risk (incident rate ratio, 1.15; 95% CI, 1.05 to 1.26) of mortality associated with rosiglitazone compared with pioglitazone for patients who initiated therapy between January 1, 2000, and December 31,2005, in a large study of Medicare patients Ͼ65 years of age. No significant differences were found in rates of MI.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Risk of Cardiovascular Events and All-Cause Mortality in Patients Treated With Thiazolidinediones in a Managed-Care Population

Wertz

Chang

Sarawate

et al. 2010

Circ: Cardiovascular Quality and Outcomes

View full text Add to dashboard Cite

Background-This study directly compares risk of acute myocardial infarction (AMI), acute heart failure (AHF), or all-cause death among pioglitazone-and rosiglitazone-treated patients in a managed-care population. Methods and Results-Patients Ն18 years of age, newly initiated on rosiglitazone or pioglitazone between January 1, 2001, and December 12, 2005, were included. The date of the first pharmacy claim for rosiglitazone or pioglitazone was defined as index date. Patients were excluded if they had Ͻ1 year continuous eligibility preindex or a preindex insulin claim. Primary outcome measure was time to composite event of AMI, AHF or death among pioglitazone-and rosiglitazone-treated patients. The National Death Index database was accessed to obtain date of death for patients who died during the study period. Propensity score matching was used to control for potential confounders. The Cox proportional hazards model was used to evaluate effects of exposure to rosiglitazone and pioglitazone on time to event. A total of 36 628 patients (58% male; mean age, 54 years) were identified. Of the rosiglitazone-treated patients, 602 (4.16%) had an AMI, AHF, or death compared with 599 (4.14%) propensity score-matched pioglitazone-treated patients. No significant difference was observed between matched groups for risk of composite event (hazard ratio, 1.03; 95% confidence interval, 0.91 to 1.15; Pϭ0.666) when patients were followed from index date until end of study period, termination of enrollment status, or diagnosis of AMI/AHF/death. Conclusions-In this retrospective cohort study directly comparing rosiglitazone and pioglitazone with a propensity score-matched population that includes mortality data, no significant differences were found in the risk of AMI, AHF or death. (Circ Cardiovasc Qual Outcomes. 2010;3:538-545.)

show abstract

Section: Discussionmentioning

confidence: 99%

“…30 To address this potential bias, propensity score matching was used to help control channeling bias. 31 Comparison of the data shows there were few differences between groups before matching. After matching, no statistically significant differences were observed in the variables of interest between patients in the preindex period.…”

Section: Study Limitationsmentioning

confidence: 99%

Risk of Cardiovascular Events and All-Cause Mortality in Patients Treated With Thiazolidinediones in a Managed-Care Population

Wertz

Chang

Sarawate

et al. 2010

Circ: Cardiovascular Quality and Outcomes

View full text Add to dashboard Cite

show abstract

“…However, restrictive entry criteria and stringent protocols can be barriers to generalizing RCT findings to clinical practice. Although observational studies lack the robustness of RCTs and may include uncontrolled confounding variables [26], they can nevertheless yield important data to complement the results from RCTs (e.g. in the study of rare outcomes, risk factors and side effects) and provide valuable information on long-term outcomes in routine clinical practice [27].…”

Section: Discussionmentioning

confidence: 99%

European Adrenal Insufficiency Registry (EU-AIR): a comparative observational study of glucocorticoid replacement therapy

Ekman

Marelli²,

Murray

et al. 2014

BMC Endocr Disord

View full text Add to dashboard Cite

BackgroundIncreased morbidity and mortality associated with conventional glucocorticoid replacement therapy for primary adrenal insufficiency (primary AI; estimated prevalence 93–140/million), secondary AI (estimated prevalence, 150–280/million, respectively) or congenital adrenal hyperplasia (estimated prevalence, approximately 65/million) may be due to the inability of typical glucocorticoid treatment regimens to reproduce the normal circadian profile of plasma cortisol. A once-daily modified-release formulation of hydrocortisone has been developed to provide a plasma cortisol profile that better mimics the daytime endogenous profile of cortisol. Here, we describe the protocol for the European Adrenal Insufficiency Registry (EU-AIR), an observational study to assess the long-term safety of modified-release hydrocortisone compared with conventional glucocorticoid replacement therapies in routine clinical practice (ClinicalTrials.gov identifier: NCT01661387).MethodsPatients enrolled in EU-AIR have primary or secondary AI and are receiving either modified-release or conventional glucocorticoid replacement therapy. The primary endpoints of EU-AIR are the incidence of intercurrent illness, adrenal crisis and serious adverse events (SAEs), as well as the duration of SAEs and dose changes related to SAEs. Data relating to morbidity, mortality, adverse drug reactions, dosing and concomitant therapies will be collected. Patient diaries will record illness-related dose changes between visits. All decisions concerning medical care are made by the registry physician and patient. Enrolment is targeted at achieving 3600 patient-years of treatment (1800 patient-years per group) for the primary analysis, which is focused on determining the non-inferiority of once-daily modified-release replacement therapy compared with conventional glucocorticoid therapy.ResultsRecruitment began in August 2012 and, as of March 2014, 801 patients have been enrolled. Fifteen centres are participating in Germany, the UK and Sweden, with recruitment soon to be initiated in the Netherlands.ConclusionsEU-AIR will provide a unique opportunity not only to collect long-term safety data on a modified-release preparation of glucocorticoid but also to evaluate baseline data on conventional glucocorticoid replacement. Such data should help to improve the treatment of AI.

show abstract

“…Therefore, a well-designed observational study must define, a priori , clinically meaningful subgroups to permit data collection for known and proposed new confounders. Incorporating such data into statistical models that account for confounding secondary to nonrandom treatment assignment is a cornerstone of observational CER [35]. There is a track record of successful observational cohort studies using patient-reported outcomes in prostate cancer.…”

mentioning

confidence: 99%

Using a population-based observational cohort study to address difficult comparative effectiveness research questions: the CEASAR study

Barocas

Chen

Cooperberg

et al. 2013

J. Compar. Effect. Res.

View full text Add to dashboard Cite

Background While randomized controlled trials represent the highest level of evidence we can generate in comparative effectiveness research, there are clinical scenarios where this type of study design is not feasible. The Comparative Effectiveness Analyses of Surgery and Radiation in localized prostate cancer (CEASAR) study is an observational study designed to compare the effectiveness and harms of different treatments for localized prostate cancer, a clinical scenario in which randomized controlled trials have been difficult to execute and, when completed, have been difficult to generalize to the population at large. Methods CEASAR employs a population-based, prospective cohort study design, using tumor registries as cohort inception tools. The primary outcome is quality of life after treatment, measured by validated instruments. Risk adjustment is facilitated by capture of traditional and nontraditional confounders before treatment and by propensity score analysis. Results We have accrued a diverse, representative cohort of 3691 men in the USA with clinically localized prostate cancer. Half of the men invited to participate enrolled, and 86% of patients who enrolled have completed the 6-month survey. Conclusion Challenging comparative effectiveness research questions can be addressed using well-designed observational studies. The CEASAR study provides an opportunity to determine what treatments work best, for which patients, and in whose hands.

show abstract

Addressing the issue of channeling bias in observational studies with propensity scores analysis

Cited by 69 publications

References 16 publications

Risk of Cardiovascular Events and All-Cause Mortality in Patients Treated With Thiazolidinediones in a Managed-Care Population

Risk of Cardiovascular Events and All-Cause Mortality in Patients Treated With Thiazolidinediones in a Managed-Care Population

European Adrenal Insufficiency Registry (EU-AIR): a comparative observational study of glucocorticoid replacement therapy

Using a population-based observational cohort study to address difficult comparative effectiveness research questions: the CEASAR study

Contact Info

Product

Resources

About