A two-study comparison of clinical and MRI markers of transition from mild cognitive impairment to Alzheimer's disease

Abstract

A published predictor model in a single-site cohort study (questionable dementia, QD) that contained episodic verbal memory (SRT total recall), informant report of function (FAQ), and MRI measures was tested using logistic regression and ROC analyses with comparable measures in a second multisite cohort study (Alzheimer's Disease Neuroimaging Initiative, ADNI). There were 126 patients in QD and 282 patients in ADNI with MCI followed for 3 years. Within each sample, the differences in AUCs between the statistical models were very similar. Adding hippocampal and entorhinal cortex volumes to the model containing AVLT/SRT, FAQ, age and MMSE increased the area under the curve (AUC) in ADNI but not QD, with sensitivity increasing by 2% in ADNI and 2% in QD for a fixed specificity of 80%. Conversely, adding episodic verbal memory (SRT/AVLT) and FAQ to the model containing age, Mini Mental State Exam (MMSE), hippocampal and entorhinal cortex volumes increased the AUC in ADNI and QD, with sensitivity increasing by 17% in ADNI and 10% in QD for 80% specificity. The predictor models showed similar differences from each other in both studies, supporting independent validation. MRI hippocampal and entorhinal cortex volumes showed limited added predictive utility to memory and function measures.

Figure 1

Comparison of receiver operating characteristic (ROC curves) for three statistical models in the ADNI and QD studies. Model 1 (red line) contained age, MMSE, AVLT/SRT and FAQ, Model 2 (blue line) contained age, MMSE, hippocampal and entorhinal cortex volumes, and Model 3 (green line) contained age, MMSE, AVLT/SRT, FAQ, hippocampal and entorhinal cortex volumes. The vertical lines at 80% specificity (0.2 on x-axis) indicate 20% false positives.