A mechanistic model for individualised treatment of anxiety disorders based on predictive neural biomarkers

Abstract

Increased amygdala responsiveness is the hallmark of fear and a characteristic across patients with anxiety disorders. The amygdala is embedded in a complex regulatory circuit. Multiple different mechanisms may elevate amygdala responsiveness and lead to the occurrence of an anxiety disorder. While top-down control by the prefrontal cortex (PFC) downregulates amygdala responses, the locus coeruleus (LC) drives up amygdala activation via noradrenergic projections. This indicates that the same fearful phenotype may result from different neural mechanisms. We propose a mechanistic model that defines three different neural biomarkers causing amygdala hyper-responsiveness in patients with anxiety disorders: (a) inherent amygdala hypersensitivity, (b) low prefrontal control and (c) high LC drive. First-line treatment for anxiety disorders is exposure-based cognitive behavioural therapy, which strengthens PFC recruitment during emotion regulation and thus targets low-prefrontal control. A treatment response rate around 50% (Loerinc et al., 2015, Clinical Psychological Reviews, 42, 72-82) might indicate heterogeneity of underlying neurobiological mechanisms among patients, presumably leading to high variation in treatment benefit. Transforming insights from cognitive neuroscience into applicable clinical heuristics to categorise patients based on their underlying biomarker may support individualised treatment selection in psychiatry. We review literature on the three anxiety-related mechanisms and present a mechanistic model that may serve as a rational for pathology-based diagnostic and biomarker-guided treatment selection in psychiatry.

Keywords: Anxiety; PFC; PTSD; amygdala; exposure therapy; generalized anxiety disorder; locus coeruleus; noradrenaline; panic disorder; social phobia.

Fig. 1.

(a) Despite high PFC control, increased amygdala (AMG) response occurs due to inherent amygdala hypersensitivity. (b) A lack of emotion regulation is based on low PFC control, which results in increased amygdala responsiveness. (c) Elevated noradrenaline release due to high LC drive leads to increased amygdala responsiveness and distraction in cortical processes involved in emotion processing.

Fig. 2.

Biomarker characterisation in patients with anxiety disorders based on the three potential mechanisms of anxiety: amygdala hypersensitivity, low PFC control and high LC drive may provide a heuristic for pathology-guided treatment selection. Inherent amygdala hypersensitivity indicates treatment with GABA-based medications like benzodiazepines, low PFC control can be treated by exposure interventions, and high LC drive might be targeted by noradrenergic agents.

Fig. 3.

Based on the model, all three biomarkers reveal increased amygdala (AMG) activation. For patients with amygdala hypersensitivity (AMG biomarker) increased AMG activation is the key feature, while PFC and LC activation are not deviating in this biomarker. The PFC biomarker is characterised by low PFC activation. Patients with an LC biomarker would express increased LC activation as a key feature, while PFC activation might increase due to regulatory attempts of the PFC. Yet, high noradrenaline release from the LC to the PFC might upregulate PFC activation, causing to exceed the optimal activation level of the PFC.