Complement system biomarkers in first episode psychosis

Abstract

Several lines of evidence implicate immunological/inflammatory factors in development of schizophrenia. Complement is a key driver of inflammation, and complement dysregulation causes pathology in many diseases. Here we explored whether complement dysregulation occurred in first episode psychosis (FEP) and whether this provides a source of biomarkers. Eleven complement analytes (C1q, C3, C4, C5, factor B [FB], terminal complement complex [TCC], factor H [FH], FH-related proteins [FHR125], Properdin, C1 inhibitor [C1inh], soluble complement receptor 1 [CR1]) plus C-reactive protein (CRP) were measured in serum from 136 first episode psychosis (FEP) cases and 42 mentally healthy controls using established in-house or commercial ELISA. The relationship between caseness and variables (analytes measured, sex, age, ethnicity, tobacco/cannabis smoking) was tested by multivariate logistic regression. When measured individually, only TCC was significantly different between FEP and controls (p=0.01). Stepwise selection demonstrated interdependence between some variables and revealed other variables that significantly and independently contributed to distinguishing cases and controls. The final model included demographics (sex, ethnicity, age, tobacco smoking) and a subset of analytes (C3, C4, C5, TCC, C1inh, FHR125, CR1). A receiver operating curve analysis combining these variables yielded an area under the curve of 0.79 for differentiating FEP from controls. This model was confirmed by multiple replications using randomly selected sample subsets. The data suggest that complement dysregulation occurs in FEP, supporting an underlying immune/inflammatory component to the disorder. Classification of FEP cases according to biological variables rather than symptoms would help stratify cases to identify those that might most benefit from therapeutic modification of the inflammatory response.

Keywords: Biomarkers; Complement; Inflammation; Predictors.

Fig. 1

Receiver operated characteristic (ROC) curves to predict the probability of FEP compared to control subjects. The first model (A) comprised demographics (sex, age, ethnicity) and contributing analytes TCC and CRP; this gave an AUC statistic of 0.72. The values of sensitivity and specificity were respectively 0.79 and 0.64, with a minimised difference probability threshold (MDT) of 0.72.The second model (B) included tobacco smoking status as an additional demographic factor and contributing analytes comprised C3, C4, C5, TCC, C1inh, FHR125, CR1; this gave an AUC statistic of 0.79. This model has respective sensitivity and specificity of 0.85 and 0.69, with MDT = 0.78.