Format

Send to

Choose Destination
J Clin Epidemiol. 2015 Nov;68(11):1366-74. doi: 10.1016/j.jclinepi.2015.02.012. Epub 2015 Feb 27.

Estimates of absolute treatment benefit for individual patients required careful modeling of statistical interactions.

Author information

1
Department of Public Health, Erasmus MC: University Medical Center Rotterdam, Wytemaweg 80, 3015 CN, Rotterdam, The Netherlands. Electronic address: d.vanklaveren.1@erasmusmc.nl.
2
Department of Public Health, Erasmus MC: University Medical Center Rotterdam, Wytemaweg 80, 3015 CN, Rotterdam, The Netherlands.
3
Department of Interventional Cardiology, Thoraxcenter, Erasmus MC: University Medical Center Rotterdam, 's-Gravendijkwal 230, 3015 CE, Rotterdam, The Netherlands; Manchester Heart Centre, Manchester Royal Infirmary, Central Manchester University Hospitals NHS Trust, Oxford Road, Manchester M13 9WL, United Kingdom.
4
Department of Interventional Cardiology, Thoraxcenter, Erasmus MC: University Medical Center Rotterdam, 's-Gravendijkwal 230, 3015 CE, Rotterdam, The Netherlands.

Abstract

OBJECTIVES:

We aimed to compare modeling approaches to estimate the individual survival benefit of treatment with either coronary artery bypass graft surgery (CABG) or percutaneous coronary intervention (PCI) for patients with complex coronary artery disease.

STUDY DESIGN AND SETTING:

We estimated survival with Cox regression models that included the treatment variable (CABG/PCI) interacting with either an internally developed overall prognostic index (PI) or with individual prognostic factors. We analyzed data of patients who were randomized in the Synergy between Percutaneous Coronary Intervention with Taxus and Cardiac Surgery trial (1,800 patients, 178 deaths).

RESULTS:

A negligible interaction with the PI (P = 0.51) led to 4-year survival estimates in favor of CABG for all patients. In contrast, individual interactions indicated substantial relative treatment effect heterogeneity (overall interaction P = 0.004), and estimates of 4-year survival were numerically in favor of CABG for 1,275 of 1,800 patients (71%; 519 with 95% confidence). To test the more complex model with individual interactions, we first used penalized regression, resulting in smaller but largely consistent individual estimates of the survival difference between CABG and PCI. Second, strong treatment interactions were confirmed at external validation in 2,891 patients from a multinational registry.

CONCLUSION:

Modeling strategies that omit interactions may result in misleading estimates of absolute treatment benefit for individual patients with the potential hazard of suboptimal decision making.

KEYWORDS:

Coronary artery bypass graft surgery; Coronary artery disease; Individualized treatment decisions; Percutaneous coronary intervention; SYNTAX trial; Statistical interactions; Treatment effect heterogeneity

PMID:
25814403
PMCID:
PMC5569577
DOI:
10.1016/j.jclinepi.2015.02.012
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Elsevier Science Icon for PubMed Central
Loading ...
Support Center