Compulsivity Reveals a Novel Dissociation between Action and Confidence

Abstract

Confidence and actions are normally tightly interwoven-if I am sure that it is going to rain, I will take an umbrella-therefore, it is difficult to understand their interplay. Stimulated by the ego-dystonic nature of obsessive-compulsive disorder (OCD), where compulsive actions are recognized as disproportionate, we hypothesized that action and confidence might be independently updated during learning. Participants completed a predictive-inference task designed to identify how action and confidence evolve in response to surprising changes in the environment. While OCD patients (like controls) correctly updated their confidence according to changes in the environment, their actions (unlike those of controls) mostly disregarded this knowledge. Therefore, OCD patients develop an accurate, internal model of the environment but fail to use it to guide behavior. Results demonstrated a novel dissociation between confidence and action, suggesting a cognitive architecture whereby confidence estimates can accurately track the statistic of the environment independently from performance.

Keywords: action; beliefs; compulsivity; computational psychiatry; confidence; learning; metacognition; obsessive-compulsive disorder; uncertainty.

Figure 1

Diagram of the Predictive-Inference Task and Model Parameters (A) On each trial, participants chose a position for the bucket (orange segment) and scored their confidence for their prediction on a bar appearing thereafter. One particle was then fired from the center of the big circle. Throughout each experimental block, particles were drawn from a Gaussian distribution. Mean of the distribution could change on any trial with a probability of 0.125 (H, hazard rate) determining a change in action-outcome contingencies in the environment (change-point). (B) Top: example of a sequence of trials. Points mark the position at which particles landed on the big circle (0°–360°). The dotted line identifies the predictions of the quasi-optimal Bayesian model. Bottom: two theoretical factors, change-point probability (CPP) and model confidence (MC), jointly influence learning rate. When unexpected observations occur, CPP is high and MC attenuated.

Figure 2

Learning Rates in OCD and Controls (A) Learning rate (LR) for participants $\left(\hat{\alpha }\right)$ (Equation 1). Patients showed significantly higher LRs $\left(\hat{\alpha }\right)$ compared with controls. Dots represent individual subjects. Mean ± SEM are displayed in blue. (B) LR for participants $\left(\hat{\alpha }\right)$ (Equation 1) plotted as a function of the error magnitude (Equation 2). The distribution of the values of the spatial prediction error was divided in 20 quantiles (Table S2 for mean and SEM for each quantile). For visualization purposes, data from 18 quantiles are shown. Mean ± SEM are shown. Subjects tended to use variable LRs $\left(\hat{\alpha }\right)$ spanning the entire allowed range, with higher LRs for higher spatial prediction error. However, LR $\left(\hat{\alpha }\right)$ was higher in OCD patients, regardless of error magnitude. ^∗∗∗p < 0.001.

Figure 3

Regression-Based Analysis for Learning Rates and Confidence (A and B) (A) Model learning rate (LR) (α) and (B) human LR $\left(\hat{\alpha }\right)$ aligned to change-points (vertical dashed line). LRs were highest after change-point trials and decayed thereafter. OCD patients showed increased LRs $\left(\hat{\alpha }\right)$ on trials before and after change-points. (C) Regression analysis of behavioral data for human action, constructed similar to the update formula of the quasi-optimal Bayesian model, multiplying the LR $\left(\hat{\alpha }\right)$ by the absolute spatial prediction error $\left(\left|\widehat{{\text{δ}}_{\text{t}}}\right|\right)$. (D and E) (D) Model confidence (υ) and (E) human confidence (Z-scored) aligned to change-points. The effects of confidence on LRs are greatest on the trials immediately after a change-point when confidence drops. Confidence recovers over several trials thereafter, with no between-group differences. (F) Regression analysis of behavioral data for human confidence (Z-scored). Error bars represent SEM. Plotted predictors for action and confidence regressions correspond to absolute prediction error (|δ|), change-point probability $\left(\text{Ω}\right)$, model confidence (υ), and hit/miss categorical predictor. (A) (model learning rate) and (D) (model confidence) represent value of the first change-point. For (B) (human learning rate) and (E) (human confidence), all epochs were identified per subject where a change-point was preceded by five data points and followed by four. Group-level mean and SEM were calculated separately for controls and OCD patients. See also Table S3. ^∗p < 0.05.

Figure 4

Uncoupling between Confidence and Action in OCD and Relationship with Symptom Severity (A) Regression model whereby action updating (i.e., the absolute difference between where participants positioned bucket on trial t and t-1) is predicted by confidence updating (i.e., the absolute difference between Z-scored confidence reports on trial t and t-1). Dots represent individual subjects. Mean ± SEM are displayed in blue. (B) Association between self-reported symptom severity and coupling confidence-action updating in patients. OCI-R, obsessive-compulsive inventory revised. Shaded gray area represents 95% confidence interval. ^∗∗p < 0.01.