Comparison of brief cognitive tests and CSF biomarkers in predicting Alzheimer's disease in mild cognitive impairment: six-year follow-up study

Abstract

Introduction: Early identification of Alzheimer's disease (AD) is needed both for clinical trials and in clinical practice. In this study, we compared brief cognitive tests and cerebrospinal fluid (CSF) biomarkers in predicting conversion from mild cognitive impairment (MCI) to AD.

Methods: At a memory clinic, 133 patients with MCI were followed until development of dementia or until they had been stable over a mean period of 5.9 years (range 3.2-8.8 years). The Mini-Mental State Examination (MMSE), the clock drawing test, total tau, tau phosphorylated at Thr(181) (P-tau) and amyloid-β(1-42) (Aβ(42)) were assessed at baseline.

Results: During clinical follow-up, 47% remained cognitively stable and 53% developed dementia, with an incidence of 13.8%/year. In the group that developed dementia the prevalence of AD was 73.2%, vascular dementia 14.1%, dementia with Lewy bodies (DLB) 5.6%, progressive supranuclear palsy (PSP) 4.2%, semantic dementia 1.4% and dementia due to brain tumour 1.4%. When predicting subsequent development of AD among patients with MCI, the cognitive tests classified 81% of the cases correctly (AUC, 0.85; 95% CI, 0.77-0.90) and CSF biomarkers 83% (AUC, 0.89; 95% CI, 0.82-0.94). The combination of cognitive tests and CSF (AUC, 0.93; 95% CI 0.87 to 0.96) was significantly better than the cognitive tests (p = 0.01) and the CSF biomarkers (p = 0.04) alone when predicting AD.

Conclusions: The MMSE and the clock drawing test were as accurate as CSF biomarkers in predicting future development of AD in patients with MCI. Combining both instruments provided significantly greater accuracy than cognitive tests or CSF biomarkers alone in predicting AD.

Figure 1. AUCs for MCI-AD compared with stable MCI and MCI-other dementias.

The AUCs were derived from the logistic regression models (Table 3). The AUC from the combined model with both cognitive tests and CSF biomarkers was significantly better than that of the CSF model (p = 0.04) and the cognitive test model (p = 0.01). MMSE (O & R)  =  the orientation and delayed word recall parts of the MMSE.