Prediction of placebo responses: a systematic review of the literature

Abstract

Objective: Predicting who responds to placebo treatment-and under which circumstances-has been a question of interest and investigation for generations. However, the literature is disparate and inconclusive. This review aims to identify publications that provide high quality data on the topic of placebo response (PR) prediction.

Methods: To identify studies concerned with PR prediction, independent searches were performed in an expert database (for all symptom modalities) and in PubMed (for pain only). Articles were selected when (a) they assessed putative predictors prior to placebo treatment and (b) an adequate control group was included when the associations of predictors and PRs were analyzed.

Results: Twenty studies were identified, most with pain as dependent variable. Most predictors of PRs were psychological constructs related to actions, expected outcomes and the emotional valence attached to these events (goal-seeking, self-efficacy/-esteem, locus of control, optimism). Other predictors involved behavioral control (desire for control, eating restraint), personality variables (fun seeking, sensation seeking, neuroticism), or biological markers (sex, a single nucleotide polymorphism related to dopamine metabolism). Finally, suggestibility and beliefs in expectation biases, body consciousness, and baseline symptom severity were found to be predictive.

Conclusions: While results are heterogeneous, some congruence of predictors can be identified. PRs mainly appear to be moderated by expectations of how the symptom might change after treatment, or expectations of how symptom repetition can be coped with. It is suggested to include the listed constructs in future research. Furthermore, a closer look at variables moderating symptom change in control groups seems warranted.

Keywords: optimism; pain; personality; placebo; placebo response prediction; self-efficacy.

Figure 1

Conceptual illustration of some possible interactions between predictor(s) and symptom change in placebo group (PG) and control group (CG). Each regression slope represents a correlation between a predictor (x-axis) and symptom change (y-axis) in either PG or CG. The single regression slopes can be either significant (as denoted by the asterisk) or not significant (n.s.). For valid placebo response prediction, the two slopes must be significantly different, as denoted by the asterisk next to the curly brackets. (A) Differential association of predictors and symptom change in PG and CG (both correlations significant but opposite, e.g., positive in PG, negative in CG). (B) Subthreshold association (no correlation significant, only slope difference). (C) Placebo-association (correlation significant in PG but not CG). (D) Placebo-disassociation (correlation significant in CG but not PG).

Figure 2

Flow diagram of study selection. A total of 15 publications were included containing 20 (sub-)studies. (A) Placebo database search. (B) Pubmed search.