How childhood maltreatment alters perception and cognition - the predictive processing account of borderline personality disorder

Abstract

Borderline personality disorder (BPD) is a severe mental disorder, comprised of heterogeneous psychological and neurobiological pathologies. Here, we propose a predictive processing (PP) account of BPD to integrate these seemingly unrelated pathologies. In particular, we argue that the experience of childhood maltreatment, which is highly prevalent in BPD, leaves a developmental legacy with two facets: first, a coarse-grained, alexithymic model of self and others - leading to a rigidity and inflexibility concerning beliefs about self and others. Second, this developmental legacy leads to a loss of confidence or precision afforded beliefs about the consequences of social behavior. This results in an over reliance on sensory evidence and social feedback, with concomitant lability, impulsivity and hypersensitivity. In terms of PP, people with BPD show a distorted belief updating in response to new information with two opposing manifestations: rapid changes in beliefs and a lack of belief updating despite disconfirmatory evidence. This account of distorted information processing has the potential to explain both the instability (of affect, self-image, and interpersonal relationships) and the rigidity (of beliefs about self and others) which is typical of BPD. At the neurobiological level, we propose that enhanced levels of dopamine are associated with the increased integration of negative social feedback, and we also discuss the hypothesis of an impaired inhibitory control of the prefrontal cortex in the processing of negative social information. Our account may provide a new understanding not only of the clinical aspects of BPD, but also a unifying theory of the corresponding neurobiological pathologies. We conclude by outlining some directions for future research on the behavioral, neurobiological, and computational underpinnings of this model, and point to some clinical implications of it.

Keywords: Active inference; Bayesian brain; belief updating; borderline personality disorder; childhood maltreatment; expectation; predictive processing.

Fig. 1.

Schematic illustration of the belief updating process. (a): Precision can refer to both the reliability of new information and the confidence afforded to priors. Their balance critically determines the extent to which a prior is updated given new information. Put simply, if the prior is afforded low precision (referred to as ‘weak priors’), new information has much influence on the formation of the posterior (b), while the opposite is true for ‘strong priors’ (c). In other words, if we are unsure about how much we can trust our beliefs, we prefer to rely on new information, provided that new information appears sufficiently valid. On the other hand, if priors are afforded overly much precision, they dominate perception such that information that is consistent with prior predictions is prioritized and discrepant information is largely neglected (Powers et al., 2017).

Fig. 2.

Portrayal of the basic assumptions of the predictive processing account of BPD.

Fig. 3.

Neural specification of the predictive processing account of BPD.