Key result
Disease risk scores developed under an intention-to-treat approach showed less overfitting and better confounding control than those developed under an as-treated approach when comparing dabigatran to warfarin.
Why the study?
Little was known about how disease risk score development should proceed under different pharmacoepidemiologic follow-up strategies.
Does the method of disease risk score development (intention-to-treat vs. as-treated) affect confounding control in an observational study of dabigatran versus warfarin for major bleeding?
Observational (n=79,265)
Does the method of disease risk score development (intention-to-treat vs. as-treated) affect confounding control in an observational study of dabigatran versus warfarin for major bleeding?
In pharmacoepidemiologic studies of anticoagulant safety, developing disease risk scores under an intention-to-treat principle may provide better confounding control and less overfitting than an as-treated approach.
Answers are grounded in this paper and cite their sources.
Supports intention-to-treat over as-treated disease risk scores for confounding control in observational anticoagulant studies; leaves open effects on major bleeding estimates.
PURPOSE: Little is known about how disease risk score (DRS) development should proceed under different pharmacoepidemiologic follow-up strategies. In an analysis of dabigatran vs. warfarin and risk of major bleeding, we compared the results of DRS adjustment when models were developed under "intention-to-treat" (ITT) and "as-treated" (AT) approaches. METHODS: We assessed DRS model discrimination, calibration, and ability to induce prognostic balance via the "dry run analysis". AT treatment effects stratified on each DRS were compared with each other and with a propensity score (PS) stratified reference estimate. Bootstrap resampling of the historical cohort at 10 percent-90 percent sample size was performed to assess the impact of sample size on DRS estimation. RESULTS: Historically-derived DRS models fit under AT showed greater decrements in discrimination and calibration than those fit under ITT when applied to the concurrent study population. Prognostic balance was approximately equal across DRS models (-6 percent to -7 percent "pseudo-bias" on the hazard ratio scale). Hazard ratios were between 0.76 and 0.78 with all methods of DRS adjustment, while the PS stratified hazard ratio was 0.83. In resampling, AT DRS models showed more overfitting and worse prognostic balance, and led to hazard ratios further from the reference estimate than did ITT DRSs, across sample sizes. CONCLUSIONS: In a study of anticoagulant safety, DRSs developed under an AT principle showed signs of overfitting and reduced confounding control. More research is needed to determine if development of DRSs under ITT is a viable solution to overfitting in other settings.
No takes yet. Share an insight, caveat, or question.
Bohn et al. (2019) conducted an observational in Atrial fibrillation (n=79,265). Dabigatran vs. Warfarin was evaluated on Major bleeding event (HR 0.76, 95% CI 0.68, 0.85). Disease risk scores developed under an intention-to-treat approach showed less overfitting and better confounding control than those developed under an as-treated approach when comparing dabigatran to warfarin.
Synapse has enriched 10 related papers. Consider them for comparative context: