Beyond hypofrontality: a quantitative meta-analysis of functional neuroimaging studies of working memory in schizophrenia

Abstract

Although there is considerable evidence that patients with schizophrenia fail to activate the dorsolateral prefrontal cortex (DLPFC) to the degree seen in normal comparison subjects when performing working memory or executive tasks, hypofrontality may be coupled with relatively increased activity in other brain regions. However, most imaging studies of working memory in schizophrenia have focused on DLPFC activity. The goal of this work is to review functional neuroimaging studies that contrasted patients with schizophrenia and healthy comparison subjects during a prototypical working memory task, the n-back paradigm, to highlight areas of hyper- and hypoactivation in schizophrenia. We utilize a quantitative meta-analysis method to review 12 imaging studies where patients with schizophrenia were contrasted with healthy comparison subjects while performing the n-back paradigm. Although we find clear support for hypofrontality, we also document consistently increased activation in anterior cingulate and left frontal pole regions in patients with schizophrenia compared to that in controls. These data suggest that whereas reduced DLPFC activation is reported consistently in patients with schizophrenia relative to healthy subjects, abnormal activation patterns are not restricted to this region, raising questions as to whether the pathophysiological dysfunction in schizophrenia is specific to the DLPFC and about the relationship between impaired performance and aberrant activation patterns. The complex pattern of hyper- and hypoactivation consistently found across studies implies that rather than focusing on DLPFC dysregulation, researchers should consider the entire network of regions involved in a given task when making inferences about the biological mechanisms of schizophrenia.

Figure 1

Meta‐analytic activation maps, based on: all primary normative studies of the n‐back working memory paradigm (Functional Atlas; as reported in Owen et al. [2005]), activation foci reported for healthy subjects recruited as controls in psychiatric neuroimaging studies (Healthy Comparison), activation foci for patients with schizophrenia alone (Patients with Schizophrenia), activation foci for contrasts of healthy comparison subjects greater than patients (Healthy > Patients), and for regions where patients with schizophrenia activate more than comparison subjects (Patients > Healthy). Slices are spaced 6 mm apart, begin 4 mm above the anterior commissure–posterior commissure line and are presented according to neurological convention (right = right).

Figure 2

Volume rendering of between‐group contrasts where relative increased activity for healthy subjects is presented in red‐yellow (DLPFC; BA9) and relative increased activity for patients with schizophrenia is shown in purple‐pink (anterior cingulate; BA32). Although patients with schizophrenia engaged the DLPFC less than comparison subjects, they overactivated a portion of the anterior cingulate. Evidence of reduced DLPFC activation and increased activity in the anterior cingulate may be consistent with the notion that schizophrenia disrupts or reverses the normal functional connectivity of prefrontal and limbic structures.