Moving towards best practice when using inverse probability of treatment weighting (IPTW) using the propensity score to estimate causal treatment effects in observational studies

Austin, Peter C.; Stuart, Elizabeth A.

doi:10.1002/sim.6607

Cited by 3,187 publications

(2,824 citation statements)

References 60 publications

Supporting

Mentioning

2,805

Contrasting

Unclassified

Order By: Relevance

“…We used the methods described by Austin and Stuart27 to calculate standardized differences post‐IPTW adjustment to ensure all baseline covariates were equally distributed in the adjusted cohorts. We then built IPTW‐adjusted Cox proportional hazards regression models to calculate adjusted HRs for the risk of each outcome and estimated IPTW‐adjusted survival curves using the approach of Cole and Hernán 28.…”

Section: Methodsmentioning

confidence: 99%

Association Between Statin Use and Cardiovascular Events After Carotid Artery Revascularization

Hussain

Saposnik

Raju

et al. 2018

JAHA

View full text Add to dashboard Cite

BackgroundStatins are commonly used for the prevention of cardiovascular events; however, statins are underutilized in patients with noncoronary atherosclerosis. We sought to establish the rates of statin use in patients with carotid artery disease and to examine the association between statin therapy and outcomes after carotid revascularization.Methods and ResultsIn this population‐level retrospective cohort study, we identified all individuals aged ≥66 years who underwent carotid endarterectomy or stenting in Ontario, Canada (2002–2014). The primary outcome was a composite of 1‐year stroke, myocardial infarction, or death (major adverse cardiac and cerebrovascular events). Five‐year risks were also examined. Adjusted hazard ratios were computed using inverse probability of treatment weighting based on propensity scores. A total of 7893 of 10 723 patients (73.6%) who underwent carotid revascularization were on preprocedural statin therapy; moderate‐ or high‐dose therapy was utilized by 7384 patients (68.9%). The composite rate of 1‐year major adverse cardiac and cerebrovascular events was lower among statin users (adjusted hazard ratio: 0.76; 95% confidence interval, 0.70–0.83). Patients who were on persistent long‐term statin therapy after the carotid procedure continued to experience significantly lower risk of major adverse cardiac and cerebrovascular events at 5 years (adjusted hazard ratio: 0.75, 95% confidence interval, 0.71–0.80). The beneficial associations with statin use were observed regardless of type of carotid revascularization procedure, carotid artery symptom status, or statin dose.ConclusionsContinuous statin therapy was associated with a 25% lower risk of long‐term adverse cardiovascular events in patients with significant carotid disease. Along with other supportive evidence, statins should be considered in patients undergoing carotid revascularization, and efforts are required to increase statin use in this undertreated population.

show abstract

Section: Methodsmentioning

confidence: 99%

Association Between Statin Use and Cardiovascular Events After Carotid Artery Revascularization

Hussain

Saposnik

Raju

et al. 2018

JAHA

View full text Add to dashboard Cite

show abstract

“…We also included the type of major surgery (eg, orthopedic, vascular, thoracic, abdominal, or urologic/pelvic) and hospital teaching status as covariates in the model. Weighted standardized differences were used to compare baseline covariates between exposure groups in the weighted samples 16. All statistical analyses were conducted separately in patients undergoing elective surgery and in those undergoing urgent surgery.…”

Section: Methodsmentioning

confidence: 99%

Association of Atrial Fibrillation and Oral Anticoagulant Use With Perioperative Outcomes After Major Noncardiac Surgery

Atzema

et al. 2017

JAHA

Self Cite

View full text Add to dashboard Cite

BackgroundWe examined the association of atrial fibrillation (AF) and oral anticoagulant use with perioperative death and bleeding among patients undergoing major noncardiac surgery.Methods and ResultsA population‐based study of patients aged 66 years and older who underwent elective (n=87 257) or urgent (n=35 930) noncardiac surgery in Ontario, Canada (April 2012 to March 2015) was performed. Outcomes were compared between AF groups using inverse probability of treatment weighting using the propensity score. Of 4612 urgent surgical patients with AF, treatments before surgery included warfarin (n=1619), a direct oral anticoagulant (DOAC) (n=729), and no anticoagulation (n=2264). After urgent surgery, the death rate within 30 days was significantly higher in patients with AF compared with patients with no AF (hazard ratio [HR], 1.28; 95% confidence interval [CI], 1.12–1.45). In contrast, among 4769 elective surgical patients with AF treated with warfarin (n=1453), a DOAC (n=1165), or no anticoagulation (n=2151), prior AF was not associated with higher mortality. Comparing patients with AF who were or were not anticoagulated, there was no difference in 30‐day mortality after urgent (HR, 0.95; 95% CI, 0.79–1.14) or elective (HR, 0.65; 95% CI, 0.38–1.09) surgery. There was no difference in 30‐day mortality between patients with AF treated with a DOAC or warfarin after urgent (HR, 0.91; 95% CI, 0.70–1.18) or elective (HR, 1.64; 95% CI, 0.77–3.53) surgery. Bleeding and thromboembolic rates did not differ significantly among patients with AF prescribed a DOAC or warfarin.ConclusionsPrior AF was associated with 30‐day mortality among patients undergoing urgent surgery. In patients with AF, neither the preoperative use of oral anticoagulants, nor the type of agent (either a DOAC or warfarin) were associated with the rate of 30‐day mortality.

show abstract

“…Balance in the baseline covariates between the 2 procedure groups was assessed by calculating standardized differences separately for each of the covariates included in the PS model (18). The standardized difference for a continuous covariate is defined as the absolute difference in procedure group means divided by an estimate of the pooled SD.…”

Section: Statistical Analysesmentioning

confidence: 99%

Perioperative Complications and Cost of Vaginal, Open Abdominal, and Robotic Surgery for Apical Vaginal Vault Prolapse

Anand

Weaver

Fruth

et al. 2015

Journal of Minimally Invasive Gynecology

View full text Add to dashboard Cite

SummaryAccounting for selection bias, MMC is associated with decreased operative time, non-UTI morbidity, and hospital costs to patients compared with sacrocolpopexy in treating posthysterectomy prolapse. AbstractObjectives-To determine the rate of perioperative complications and cost associated with Methods-We retrospectively searched for the records of patients undergoing posthysterectomy apical vaginal prolapse surgery (MMC, ASC, or RSC) between January 1, 2000, and June 30, 2012, at our institution. For all patients identified, perioperative complications, length of hospital stay, and inpatient costs to patients were abstracted from the medical records and compared by procedure. Inverse-probability-of-procedure weighting using propensity scores was used to obtain less-biased comparisons of outcomes between procedures.Results-A total of 512 patients met the inclusion criteria (174 MMC, 237 ASC, and 101 RSC). Using inverse-probability weighting, the MMC group had a significantly lower intraoperative complication rate (3.3% vs 11.6% for ASC; 3.4% vs 24.1% for RSC), median operative time (94 min vs 217 min for ASC; 100 min vs 228 min for RSC), and median cost ($8,776 vs $12,695 for ASC and $8,773 vs $13,107 for RSC) than the ASC and RSC groups (all P<.01). In addition, the MMC group had significantly fewer postoperative grade III+ complications than the RSC group (1.1% vs 9.4%; P<.01).Conclusions-In the treatment of posthysterectomy vaginal vault prolapse, MMC is associated with decreased non-urinary tract infection, less perioperative morbidity, and lower cost to patients compared with sacrocolpopexy.

show abstract

Moving towards best practice when using inverse probability of treatment weighting (IPTW) using the propensity score to estimate causal treatment effects in observational studies

Cited by 3,187 publications

References 60 publications

Association Between Statin Use and Cardiovascular Events After Carotid Artery Revascularization

Association Between Statin Use and Cardiovascular Events After Carotid Artery Revascularization

Association of Atrial Fibrillation and Oral Anticoagulant Use With Perioperative Outcomes After Major Noncardiac Surgery

Perioperative Complications and Cost of Vaginal, Open Abdominal, and Robotic Surgery for Apical Vaginal Vault Prolapse

Contact Info

Product

Resources

About