scholarly journals Propensity Score Matching in Randomized Clinical Trials

Biometrics ◽  
2009 ◽  
Vol 66 (3) ◽  
pp. 813-823 ◽  
Author(s):  
Zhenzhen Xu ◽  
John D. Kalbfleisch
Keyword(s):  
Clinical Trials ◽  
Propensity Score ◽  
Propensity Score Matching ◽  
Randomized Clinical Trials

Propensity score matching versus coarsened exact matching in observational comparative effectiveness research

2021 ◽  
Author(s):  
David Guy ◽  
Igor Karp ◽  
Piotr Wilk ◽  
Joseph Chin ◽  
George Rodrigues
Keyword(s):  
Clinical Trials ◽  
Propensity Score ◽  
Propensity Score Matching ◽  
Observational Data ◽  
Randomized Clinical Trials ◽  
Original Data ◽  
Considerable Proportion ◽  
Exact Matching ◽  
Coarsened Exact Matching ◽  
Comparison Groups

Aim & methods: We compared propensity score matching (PSM) and coarsened exact matching (CEM) in balancing baseline characteristics between treatment groups using observational data obtained from a pan-Canadian prostate cancer radiotherapy database. Changes in effect estimates were evaluated as a function of improvements in balance, using results from randomized clinical trials to guide interpretation. Results: CEM and PSM improved balance between groups in both comparisons, while retaining the majority of original data. Improvements in balance were associated with effect estimates closer to those obtained in randomized clinical trials. Conclusion: CEM and PSM led to substantial improvements in balance between comparison groups, while retaining a considerable proportion of original data. This could lead to improved accuracy in effect estimates obtained using observational data in a variety of clinical situations.

Using Propensity Score Matching to Improve Validity in Public Administration Research

2022 ◽  
pp. 45-60
Author(s):  
Michael Howell-Moroney
Keyword(s):  
Clinical Trials ◽  
Propensity Score ◽  
Public Administration ◽  
Propensity Score Matching ◽  
Observational Data ◽  
Randomized Clinical Trials ◽  
Causal Effect ◽  
Social Science Research ◽  
Causal Effects ◽  
Government Employment

Randomized clinical trials have a longstanding status as the gold standard in detecting causal effects. In the social sciences, randomized clinical trials are rare because of their attendant logistical and cost burdens. Most social science research makes use of observational data. The empirical challenge posed by observational data is that treatment assignment is no longer random. This challenge continues to spur innovation across many disciplines toward more sophisticated techniques for estimating causal relationships. Scholars have developed a common theoretical framework for estimating causal effects, often called the potential outcomes or counterfactual framework. This chapter demonstrates the propensity score matching methodology as a way to estimate causal effects using observational data. Throughout, an example from public administration research, the effect of government employment on volunteerism, is used to illustrate the concepts. Empirical estimates of the treatment effects show that there may be a causal effect of government employment on volunteerism.

Comparative effectiveness of treatment options in elderly patients with colon cancer receiving adjuvant chemotherapy.

2012 ◽  
Vol 30 (4_suppl) ◽  
pp. 470-470
Author(s):  
Sacha Satram-Hoang ◽  
Devi Ramanan ◽  
Luen F. Lee ◽  
Shui Yu ◽  
Carolina M. Reyes ◽  
...  
Keyword(s):  
Colon Cancer ◽  
Clinical Trials ◽  
Propensity Score ◽  
Elderly Patients ◽  
Older Patients ◽  
Randomized Clinical Trials ◽  
Cohort Analysis ◽  
Risk Of Death ◽  
Morbidity Score ◽  
Co Morbidity

470 Background: While colon cancer (CC) is predominantly a disease of the elderly, older patients are underrepresented in clinical trials. We sought to evaluate whether the treatment patterns and benefits realized by trial participants pertain to older patients in the real-world setting. Methods: Using the linked Surveillance, Epidemiology, and End Results (SEER)-Medicare database, we conducted a retrospective cohort analysis of 3390 stage II and III CC patients diagnosed between 1/1/ 2004 to 12/31/2007, who were >66 years, enrolled in Medicare Parts A and B, and received adjuvant treatment with 5FU/LV (n=1368), FOLFOX (n=1398), CAP (capecitabine; n=507), and CAPOX (CAP + oxaliplatin; n=117) within 3 months after surgery. Date of last follow-up was 12/31/2007. Chi-square test and ANOVA or t-test assessed differences in patient and disease characteristics by treatment. Propensity score weighted Cox regression assessed the relative risk of death by treatment. Results: Patients treated with CAP were older (mean age 77 years; p<.0001), more likely female (61%; p<.05), more likely non-white (19%; p<.05) and had higher co-morbidity score (p<.0001) compared to the other treatment groups. The mean time to chemo initiation after surgery were similar between the groups (mean 46-49 days) while mean duration of treatment were longer for 5FU/LV (149 days) and FOLFOX (144 days), compared to CAP (121 days) and CAPOX (111 days); p<.0001. The incidence of adverse events (AEs) within 180 days after initiation of treatment were higher in patients treated with FOLFOX (82%) and 5FU/LV (78%) compared to CAP (74%) and CAPOX (71%); p=0.0002. Propensity score adjusted multivariate analysis demonstrated comparable survival for CAP-based regimens vs. 5-FU/LV- based regimens ( table ). Conclusions: Treatment outcomes for elderly patients observed in routine clinical practice were comparable between CAP-based and 5FU/LV-based regimens and consistent with results reported in randomized clinical trials. AEs associated with medical resource utilization were less frequent with CAP-based regimens. [Table: see text]

scholarly journals Statins and clinical outcomes in hospitalized COVID-19 patients with and without Diabetes Mellitus: a retrospective cohort study with propensity score matching

2021 ◽  
Vol 20 (1) ◽  
Author(s):  
Prateek Lohia ◽  
Shweta Kapur ◽  
Sindhuri Benjaram ◽  
Zachary Cantor ◽  
Navid Mahabadi ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Cohort Study ◽  
Propensity Score ◽  
Propensity Score Matching ◽  
Retrospective Cohort Study ◽  
Retrospective Cohort ◽  
Randomized Clinical Trials ◽  
Multivariable Analysis ◽  
Statin Group ◽  
Statin Use

Abstract Background The pleiotropic effects of statins may reduce the severity of COVID-19 disease. This study aims to determine the association between inpatient statin use and severe disease outcomes among hospitalized COVID-19 patients, especially those with Diabetes Mellitus (DM). Research design and methods A retrospective cohort study on hospitalized patients with confirmed COVID-19 diagnosis. The primary outcome was mortality during hospitalization. Patients were classified into statin and non-statin groups based on the administration of statins during hospitalization. Analysis included multivariable regression analysis adjusting for confounders and propensity score matching to achieve a 1:1 balanced cohort. Subgroup analyses based on presence of DM were conducted. Results In the cohort of 922 patients, 413 had a history of DM. About 27.1% patients (n = 250) in the total cohort (TC) and 32.9% patients (n = 136) in DM cohort received inpatient statins. Atorvastatin (n = 205, 82%) was the most commonly prescribed statin medication in TC. On multivariable analysis in TC, inpatient statin group had reduced mortality compared to the non-statin group (OR, 0.61; 95% CI, 0.42–0.90; p = 0.01). DM modified this association between inpatient statins and mortality. Patients with DM who received inpatient statins had reduced mortality (OR, 0.35; 95% CI, 0.21–0.61; p < 0.001). However, no such association was noted among patients without DM (OR, 1.21; 95% CI, 0.67–2.17; p = 0.52). These results were further validated using propensity score matching. Conclusions Inpatient statin use was associated with significant reduction in mortality among COVID-19 patients especially those with DM. These findings support the pursuit of randomized clinical trials and inpatient statin use appears safe among COVID-19 patients.

scholarly journals Hydroxychloroquine for Pre-Exposure Prophylaxis for Sars-Cov-2

2020 ◽  
Vol 2 (1) ◽  
pp. 09-18
Author(s):  
Naiara Cubelos Fernández
Keyword(s):  
Clinical Trials ◽  
Propensity Score ◽  
Autoimmune Diseases ◽  
Propensity Score Matching ◽  
Specific Treatment ◽  
Risk Difference ◽  
Exposed Group ◽  
Control Group ◽  
Control Cohort ◽  
Exposure Prophylaxis

SARS-CoV-2 infection has a high transmission level. At the present time there is not a specific treatment approved but it is known that, in vitro, chloroquine and hydroxychloroquine can inhibit the coronavirus. Objective: verifying if patients with autoimmune diseases that are on treatment with HCQ have less incidence and severity on COVID-19. Material and methods: this is a retrospective cohort study. The exposed cohort was formed by individuals with autoimmune diseases with HCQ treatment. The control cohort was randomly selected using the Health Card database. To deal with confounding variables and evaluate the effect of HCQ on the incidence and severity of SARS-CoV-2 infection, propensity score matching was used. Risk difference and paired percentage difference between exposed and non-exposed groups was estimated. Results: 919 individuals formed the exposed cohort and 1351 the control cohort. After matching, there were 690 patients on each group. During the time of the study, in the exposed group there were 42 (6.1%) individuals with suspected COVID-19, 12(1.7%) with confirmed COVID-19 and 3(0.4%) were hospitalized. In the control group there were 30(4.3%) individuals with suspected COVID-19, 13(1.9%) with confirmed COVID-19 and 2(0.3%) were hospitalized. The risk difference between each cohort was: 0.017(-0.05-0.04) for suspected COVID-19; -0.014(-0.015-0.012) for confirmed COVID-19 and 0.001(-0.007-0.007) for hospitalized patients. There were not significant differences. Conclusion: there is no difference neither on the incidence nor on the severity of COVID-19 between patients with autoimmune diseases with HCQ treatment and patients that do not take HCQ. Strengths and limitations of this study Strenghts: Ii provides evidence on pre-exposure prophylaxis of HCQ against COVID-19 for which there is still no evidence in clinical trials. The study on the pre-exposure prophylaxis of HCQ was carried out during the period of maximum circulation of SARS-COV-2 in Spain. Therefore, both cohorts had a high probability of exposure to the virus, which increases the power of the study. The dose of HCQ taken by most of the study subjects (400 mg per day) is similar to that used in several clinical trials that are underway as pre- and post-exposure prophylaxis of COVID-19. Limitations: The population of the exposed group suffers entirely from rheumatic diseases. This condition could act as a confounding factor, making it difficult to generalize the results to the entire population. Propensity score matching resulted in a reduction in sample size. Of the 900 initial couples, only 690 survive. Given the shortage of diagnostic tests during the study period, many of the possible COVID-19s were left unconfirmed, limiting the power of the study.

scholarly journals Evidence-based approaches to comparing the effectiveness of modern cardiology interventions: trends, bias and prospects

2020 ◽  
Vol 25 (8) ◽  
pp. 4037
Author(s):  
S. R. Gilyarevsky ◽  
Yu. N. Belenkov
Keyword(s):  
Clinical Trials ◽  
Clinical Practice ◽  
Drug Use ◽  
Propensity Score ◽  
Observational Studies ◽  
Large Scale ◽  
Randomized Clinical Trials ◽  
Evidence Based ◽  
Improved Methods

The article discusses the limitations of the evidence from observational studies. Modern approaches to reducing bias in observational studies are discussed in detail, in particular, propensity score matching, which has become popular in recent years. The main differences between randomized and observational studies are discussed. Arguments against the observational studies and improved methods of analysis to compare the treatments’ effectiveness in clinical practice are presented. The role of observational studies as a source of evidence is discussed. The article points out the validity of performing large-scale prospective observational studies to assess the effects of postmarketing drug use in clinical practice, as well as to obtain data on drug use in patients that differ from those in randomized clinical trials.

scholarly journals Covariate adjustment in subgroup analyses of randomized clinical trials: A propensity score approach

2021 ◽  
pp. 174077452110285
Author(s):  
Siyun Yang ◽  
Fan Li ◽  
Laine E Thomas ◽  
Fan Li
Keyword(s):  
Clinical Trials ◽  
Propensity Score ◽  
Exercise Training ◽  
Randomized Clinical Trials ◽  
Analysis Of Covariance ◽  
Covariate Adjustment ◽  
Operating Characteristics ◽  
Propensity Score Model ◽  
Propensity Score Weighting ◽  
Subgroup Analyses

Background: Subgroup analyses are frequently conducted in randomized clinical trials to assess evidence of heterogeneous treatment effect across patient subpopulations. Although randomization balances covariates within subgroups in expectation, chance imbalance may be amplified in small subgroups and adversely impact the precision of subgroup analyses. Covariate adjustment in overall analysis of randomized clinical trial is often conducted, via either analysis of covariance or propensity score weighting, but covariate adjustment for subgroup analysis has been rarely discussed. In this article, we develop propensity score weighting methodology for covariate adjustment to improve the precision and power of subgroup analyses in randomized clinical trials. Methods: We extend the propensity score weighting methodology to subgroup analyses by fitting a logistic regression propensity model with pre-specified covariate–subgroup interactions. We show that, by construction, overlap weighting exactly balances the covariates with interaction terms in each subgroup. Extensive simulations were performed to compare the operating characteristics of unadjusted estimator, different propensity score weighting estimators and the analysis of covariance estimator. We apply these methods to the Heart Failure: A Controlled Trial Investigating Outcomes of Exercise Training trial to evaluate the effect of exercise training on 6-min walk test in several pre-specified subgroups. Results: Standard errors of the adjusted estimators are smaller than those of the unadjusted estimator. The propensity score weighting estimator is as efficient as analysis of covariance, and is often more efficient when subgroup sample size is small (e.g. <125), and/or when outcome model is misspecified. The weighting estimators with full-interaction propensity model consistently outperform the standard main-effect propensity model. Conclusion: Propensity score weighting is a transparent and objective method to adjust chance imbalance of important covariates in subgroup analyses of randomized clinical trials. It is crucial to include the full covariate–subgroup interactions in the propensity score model.

scholarly journals Digoxin treatment and long-term mortality depending on left ventricular ejection fraction and atrial fibrillation: a propensity score matched analysis

2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
M.R Grubler ◽  
N.D Verheyen ◽  
A Meinitzer ◽  
L Fiedler ◽  
M Tscharre ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Clinical Trials ◽  
Coronary Angiography ◽  
Propensity Score ◽  
Ejection Fraction ◽  
Propensity Score Matching ◽  
Increased Risk ◽  
All Cause Mortality

Abstract Background/Introduction Atrial fibrillation (AF) is a common heart rhythm disturbance, associated with an increased risk of stroke, hospital admissions and mortality, especially in patients with reduced ejection fraction. Among the oldest medications used for heart-rate control is digitalis, but largely due to observational studies showing an increased risk of death it has fallen out of favour. Recently newer clinical trials reported that the treatment with digitalis in permanent AF might be superior to beta blocker therapy in regard to functional status and symptom burden. Given this diverging results we attempt to analysis a large cohort of patients facilitating a propensity score matching algorithm. Purpose To assess the associations of digitalis treatment with mortality in patients with increased cardiovascular risk. Methods Patients were derived from a large cohort study including participants from a tertiary care centre who were referred to coronary angiography. The propensity score matching is based on a predefined list of variables, with digitalis as treatment. Matching strategy is nearest neighbour matching and to prove consistency, radius matching (radius = 0.1). For survival analysis we used a Cox proportional hazard regression comparing patients with and without digitalis for all-cause mortality. The analysis is conducted using STATA 13 MP. All patients provided written informed consent and the study was approved by the ethics committee. Results A total of 2457 patients (median age: 63.5 [IQR = 56.3–70.6] years, 30.1% women) referred to coronary angiography, with a median follow up of 9.9 (IQR = 8.5–10.7) years were included. The matching process and the resulting propensity score fulfilled all statistical assumptions and resulted in a balanced cohort. The risk for all-cause mortality was higher among propensity score matched participants not treated with digitalis compared to patients on treatment (n=514) HR 3.03 (95% CI 2.5 to 3.7). Total mortality in patients with AF on digitalis after a median follow-up of 9.9 years was 27.6%. At baseline, only 42.4% of patients with AF were on oral anticoagulation. Conclusions In the present cohort treatment with digitalis was associated with a lower risk of all-cause mortality after long-term follow-up. The patient population has a clinically significant 10-year mortality risk. The results may not apply to other cohorts but may help inform future clinical trials. FUNDunding Acknowledgement Type of funding sources: None.

Sign in / Sign up

Export Citation Format

Share Document