Improving subgroup analysis using methods to extend inferences to specific target populations

Subgroup analyses are common in epidemiologic and clinical research. Unfortunately, restriction to subgroup members to test for heterogeneity can yield imprecise effect estimates. If the true effect differs between members and non-members due to different distributions of other measured effect measure modifiers (EMMs), leveraging data from non-members can improve the precision of subgroup effect estimates. We obtained data from the PRIME RCT of panitumumab in patients with metastatic colon and rectal cancer from Project Datasphere(TM) to demonstrate this method. We weighted non-Hispanic White patients to resemble Hispanic patients in measured potential EMMs (e.g., age, KRAS distribution, sex), combined Hispanic and weighted non-Hispanic White patients in one data set, and estimated 1-year differences in progression-free survival (PFS). We obtained percentile-based 95% confidence limits for this 1-year difference in PFS from 2,000 bootstraps. To show when the method is less helpful, we also reweighted male patients to resemble female patients and mutant-type KRAS (no treatment benefit) patients to resemble wild-type KRAS (treatment benefit) patients. The PRIME RCT included 795 non-Hispanic White and 42 Hispanic patients with complete data on EMMs. While the Hispanic-only analysis estimated a one-year PFS change of -17% (95% C.I. -45%, 8.8%) with panitumumab, the combined weighted estimate was more precise (-8.7%, 95% CI -22%, 5.3%) while differing from the full population estimate (1.0%, 95% CI: -5.9%, 7.5%). When targeting wild-type KRAS patients the combined weighted estimate incorrectly suggested no benefit (one-year PFS change: 0.9%, 95% CI: -6.0%, 7.2%). Methods to extend inferences from study populations to specific targets can improve the precision of estimates of subgroup effect estimates when their assumptions are met. Violations of those assumptions can lead to bias, however.