Review and meta-analysis of biomarkers and diagnostic imaging in Alzheimer's disease

Abstract

Mild Alzheimer's disease (AD) is often difficult to differentiate from mild cognitive impairment (MCI) or non-AD dementias. A multitude of diagnostic biomarkers and advanced imaging strategies have been developed to aid in the diagnosis and management of AD. We sought to review and analyze the published evidence on key test characteristics of major diagnostic strategies to formulate best estimates of sensitivity (SN) and specificity (SP). A systematic review was undertaken to locate and abstract all studies of biomarkers or diagnostic imaging for AD published in English from January 1990 to March 2010 that provided estimates of SN and SP. Meta-analysis was performed using a bivariate mixed-effects binary regression model. We calculated -SN, SP, and area under the receiver operating curves (AUROC), with confidence and prediction contours. Of 1,840 unique studies identified, 119 presented primary data sufficient for analysis. SN and SP were calculated against non-demented controls, non-AD dementias with and without MCI, if available. Compared to non-demented controls, FDG-PET demonstrated the highest AUROC (0.96), with 90% SN (95%CI 84% to 94%), and 89% SP (95% CI 81% to 94%). FDG-PET also was most accurate in discriminating AD from demented controls (including MCI) with AUROC 0.91, and 92% SN (95%CI 84% to 96%) and 78% SP (95% CI 69% to 85%). For discrimination of AD from non-AD dementias (excluding MCI), CSF Ptau, and SPECT produced identical AUROC (0.86). Diagnostic strategies for AD show wide variation in test characteristics and some show promise for use in clinical practice.