Comparison of Propensity Score Methods and Covariate Adjustment

Elze, Markus C.; Gregson, John; Baber, Usman; Williamson, Elizabeth; Sartori, Samantha; Mehran, Roxana; Nichols, Melissa; Stone, Gregg W.; Pocock, Stuart J.

doi:10.1016/j.jacc.2016.10.060

Cited by 541 publications

(426 citation statements)

References 32 publications

Supporting

Mentioning

416

Contrasting

Unclassified

Order By: Relevance

“…Fourth, after 2015, most of the cases were treated with the Turbo‐Power device which may have further improved the outcomes compared to the initial laser devices. Fifth, the two groups had differences in their baseline characteristics, but propensity score matching analysis was not used because of the small sample . Sixth, two different DCB devices were used, Lutonix and In.PACT.…”

Section: Discussionmentioning

confidence: 99%

Laser atherectomy and drug‐coated balloons for the treatment of femoropopliteal in‐stent restenosis: 2‐Year outcomes

Kokkinidis

Behan

Jawaid

et al. 2019

Cathet Cardio Intervent

View full text Add to dashboard Cite

Background Femoropopliteal (FP) artery is one of the most anatomically challenging areas for sustained stent patency. The incidence of FP in‐stent restenosis (ISR) is estimated at 50% at 24 months. Prior studies have shown that lesion debulking with laser atherectomy (LA) combined with drug coated balloon (DCB) have superior outcomes compared to LA + balloon angioplasty (BA) ISR, but there have not been studies evaluating 2‐year outcomes. Methods This was a dual‐center retrospective cohort study that compared patients with FP‐ISR treated with LA + DCB versus LA + BA. Cox regression analysis was used to examine 2‐year outcomes of target lesion revascularization (TLR) and the composite outcome of TLR or restenosis. Multivariable analysis was performed for clinical and statistically significant (in the univariate analysis) variables. Results One hundred and seventeen consecutive patients with Tosaka II (n = 32) and III (n = 85) ISR were analyzed. Sixty‐six patients were treated with LA + DCB and 51 with LA + BA. The LA + DCB group had more lesions with moderate to severe calcification (58% vs. 13%; p < .0001). The LA + DCB group was more likely to be treated with the use of embolic protection devices (64% vs. 23%, p < .001) and cutting balloons (61% vs. 6%, p < .001). Bail‐out stenting rates were lower in the LA + DCB group (32% vs. 57%, p = .008). LA + DCB was superior (HR: 0.57; 95% CI: 0.34–0.9, p = .027) for the composite outcome of 2‐year TLR or restenosis. The 12‐month KM estimates for freedom from TLR or restenosis were 66% in the LA + DCB group versus 46% in the LA + BA group. The 24‐month KM estimates were 45% in the LA + DCB group versus 24% in the LA + BA group. Conclusions The combination of DCB + LA was associated with decreased rates of bail‐out stenting and improved 2‐year TLR or restenosis rates. Randomized clinical trials examining the DCB + LA combination for FP‐ISR are needed.

show abstract

Section: Discussionmentioning

confidence: 99%

Laser atherectomy and drug‐coated balloons for the treatment of femoropopliteal in‐stent restenosis: 2‐Year outcomes

Kokkinidis

Behan

Jawaid

et al. 2019

Cathet Cardio Intervent

View full text Add to dashboard Cite

show abstract

“…A propensity score is defined as the probability of a patient being assigned to an intervention, given a set of covariates and all patient characteristics being summarized into a single covariate, thus reducing (although not eliminating) the potential for overfitting and correcting for selection biases and potential confounding. While this technique provides an excellent balance of covariates in most circumstances, it is less precise, and some patients may remain unmatched and hence excluded from the analysis 33. Moreover, it balances the distribution of characteristics between the compared exposure groups on average, thus there may be pairs that are discordant on special characteristics; finally, there is no clear understanding of the relative performance of matching strategies in subgroup analyses 34…”

Section: A Critical Appraisal Of Methodological Issuesmentioning

confidence: 99%

Observational research on sodium glucose co‐transporter‐2 inhibitors: A real breakthrough?

Raschi

Poluzzi

Fadini

et al. 2018

Diabetes Obesity Metabolism

View full text Add to dashboard Cite

Sodium glucose co‐transporter‐2 inhibitors have attracted the interest of the scientific community following the results from dedicated cardiovascular outcome trials, which demonstrated remarkable reduction in all‐cause mortality and other cardiovascular (CV) endpoints with empagliflozin and canagliflozin. These impressive results raised further expectations on real world data from large observational cohort studies. They were designed to address the possible existence of a class effect, and the uncertainty on whether this benefit can be extended from secondary to primary CV prevention of patients with type 2 diabetes. In this review, we collated data from existing observational studies (including the celebrated CVD‐REAL cohorts) and critically appraised results and methodological issues with the aim of providing clinical insight, including unsettled aspects, and proposing a research agenda for future investigations.

show abstract

“…A propensity score approach was also considered with ICP (Yes vs. No) as the outcome. However, there was still an imbalance of covariates after stratification adjustment, indicating that this approach was not optimal [20, 21]. A two-sided p value < 0.05 was considered statistically significant.…”

Section: Methodsmentioning

confidence: 99%

Impact of the Timing of Placement of an Intracranial Pressure Monitor on Outcomes in Children with Severe Traumatic Brain Injury

et al. 2018

View full text Add to dashboard Cite

Background: Severe traumatic brain injury (sTBI) is the leading cause of morbidity and mortality from trauma. Brain Trauma Foundation guidelines recommend intracranial pressure (ICP) monitoring in sTBI. We hypothesized that early ICP monitor placement was associated with better outcomes in children. Methods: This was a retrospective study of children with sTBI admitted to the participating pediatric intensive care units (PICUs) and entered into the Virtual Pediatric Systems (VPS), LLC, database between 1 January 2010 and 31 December 2015. We compared outcomes of patients who had an ICP monitor placed early (≤6 h from PICU admission) to those with later placement (> 6 to < 72 h). We collected demographics, diagnoses, procedure data, illness severity scores, outcomes, and site data. Multivariable regression analysis was used to identify variables independently associated with outcomes. Results: Twenty-seven percent of 3,608 patients with sTBI underwent ICP monitoring, 355 in the early and 156 in the later ICP monitoring groups, respectively. A higher proportion of patients in the early ICP monitoring group had worse markers of illness/injury severity; unadjusted analysis showed higher mortality in this group (31.3 vs. 21.8%, p = 0.029). Multivariable regression analysis showed that ICP monitoring was not independently associated with any of the outcomes. Conclusion: Time to ICP monitoring was not associated with outcomes after pediatric sTBI.

show abstract

Comparison of Propensity Score Methods and Covariate Adjustment

Cited by 541 publications

References 32 publications

Laser atherectomy and drug‐coated balloons for the treatment of femoropopliteal in‐stent restenosis: 2‐Year outcomes

Laser atherectomy and drug‐coated balloons for the treatment of femoropopliteal in‐stent restenosis: 2‐Year outcomes

Observational research on sodium glucose co‐transporter‐2 inhibitors: A real breakthrough?

Impact of the Timing of Placement of an Intracranial Pressure Monitor on Outcomes in Children with Severe Traumatic Brain Injury

Contact Info

Product

Resources

About