Premium
IC‐P‐204: PROGNOSTIC UTILITY OF MRI ATROPHY MEASURES IN AMCI PATIENTS WITH MINIMAL COGNITIVE DECLINE
Author(s) -
Bodryzlova Yuliya,
Potvin Olivier,
Duchesne Simon
Publication year - 2014
Publication title -
alzheimer's and dementia
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 6.713
H-Index - 118
eISSN - 1552-5279
pISSN - 1552-5260
DOI - 10.1016/j.jalz.2014.05.212
Subject(s) - medicine , atrophy , cognitive impairment , receiver operating characteristic , neurology , magnetic resonance imaging , area under the curve , cardiology , nuclear medicine , radiology , disease , psychiatry
Background: The utility of MRI atrophy measures for predicting progression of amnestic MCI (aMCI) to Alzheimer’s disease (AD) is limited, as evidenced by proven prognostic likelihood ratios (LR; positive LR 1⁄4 2,9; negative LR 1⁄4 0,49-0,56)(Frisoni et al., Neurology 2013) that are outside the ranges usually required for clinical implementation (LR+ 5,0 and LR0,2). We tested the hypothesis that stratification of patients by global cognitive function could improve the prognostic value of MRI. Methods: 4502We selected 147 aMCI subjects from the ADNI-1 database with MMSE 1⁄4 [28-30] at baseline and 195 with MMSE 1⁄4 [24-27] for which we had complete MRI volumetric results (FreeSurfer) and general primary-level information. We created a prognostic model for progression to AD within 36 months based on these measures. Results: The model that included left hippocampal volume and left mid-temporal cortical thickness, when adjusted for intracranial volume, age and sex, had a 87,4% area under ROC curve (AUC), 80.3% classification accuracy, 53,8% sensitivity, 88,2% specificity, LR+ 1⁄4 4,81 and LR1⁄4 0.49 (with classification cut-point of disease probability 1⁄4 0.4). After excluding statistical outliers (three subjects; impact chi-square (dl 6)1⁄412.59), the same model had AUC of 91,1%, 81.9% classification accuracy, 71.4% sensitivity, 85.3% specificity, LR+1⁄44.9 and LR-1⁄40.3 (with classification cut-point of 0.3). Applying the same model to the ADNI aMCI subjects with baseline MMSE in the [24-27]range gave a AUC of 64.5 %. In fact, simply adding a dichotomous variable in the MRI model for cognitive status (i.e. baseline MMSE in range [24-27] or [28-30]) gives a AUC of 73.3% for all aMCI in the ADNI-1 population. Conclusions: A clinically relevant prognostic significance for left hippocampal volume and left mid-temporal cortical thickness, when adjusted for intracranial volume, age and sex, has been observed in ADNI-1 aMCI subjects with baseline MMSE in the [28-30] range. The prognostic LR+ and LRobserved in these strata is higher than previously described for a more general population and reaches clinical applicability.