Pharmacoepidemiological Evaluation in Prostate Cancer-Common Pitfalls and How to Avoid Them

Abstract

Pharmacoepidemiologic research provides opportunities to evaluate how commonly used drug groups, such as cholesterol-lowering or antidiabetic drugs, may affect the prostate cancer risk or mortality. This type of research is valuable in estimating real-life drug effects. Nonetheless, pharmacoepidemiological studies are prone to multiple sources of bias that mainly arise from systematic differences between medication users and non-users. If these are not appreciated and properly controlled for, there is a risk of obtaining biased results and reaching erroneous conclusions. Therefore, in order to improve the quality of future research, we describe common biases in pharmacoepidemiological studies, particularly in the context of prostate cancer research. We also list common ways to mitigate these biases and to estimate causality between medication use and cancer outcomes.

Keywords: common biases; confounding; metabolism; pharmacoepidemiology; prostate cancer; retrospective studies.

Figure 1

Illustration of time immortal bias in an observational cohort study (treated (misclassified)) and one solution to avoid it (treated). Immortal time bias can generate an illusion of treatment effectiveness when it does not actually occur. This bias can be avoided by using time-dependent variables where exposure status is updated during the follow-up, or alternatively by excluding all of the non-exposed follow-up times from the beginning of exposure.

Figure 2

Illustration of time-window bias in an observational pharmacoepidemiological case–control study. This bias occurs when the limitation for drug exposure differs between the cases and controls; exposure is limited to occur before cancer diagnosis among the cases, but no such limitation is applied among the controls. The time-window bias can be avoided by assessing equal time windows for exposure both in cases and their matched controls.

Figure 3

Illustration of bias caused by selective discontinuation of drugs in the terminal phase of cancer and the use of time-dependent variables. This bias may create an illusion that non-users, who might well have been users for most of the follow-up time but discontinue usage in the terminal phase of cancer (user with outcome), are more prone to die. This bias can be avoided by keeping subjects as non-users until the first exposure of drugs, and after that, they remain as ever-users throughout the whole follow-up period.

Figure 4

Illustration of lag-time analysis to avoiding protopathic bias. The exposure of drug is lagged in the follow-up time, e.g., with a one-year time lag, the cancer risk is not evaluated by medication use that occurred at time of diagnosis, but by usage that occurred up to one year before that time point.