Identifying cognitively healthy elderly individuals with subsequent memory decline by using automated MR temporoparietal volumes.
| Publication Type | Academic Article |
| Authors | Chiang G, Insel P, Tosun D, Schuff N, Truran-Sacrey D, Raptentsetsang S, Jack C, Weiner M |
| Journal | Radiology |
| Volume | 259 |
| Issue | 3 |
| Pagination | 844-51 |
| Date Published | 04/05/2011 |
| ISSN | 1527-1315 |
| Keywords | Alzheimer Disease, Magnetic Resonance Imaging, Memory Disorders, Parietal Lobe, Temporal Lobe |
| Abstract | PURPOSE: To determine whether automated temporoparietal brain volumes can be used to accurately predict future memory decline among a multicenter cohort of cognitively healthy elderly individuals. MATERIALS AND METHODS: The study was approved by the institutional review board at each site and was HIPAA compliant, with written consent obtained from all participants. One hundred forty-nine cognitively healthy study participants were recruited through the Alzheimer's Disease Neuroimaging Initiative and underwent a standardized baseline 1.5-T magnetic resonance (MR) imaging examination, as well as neuropsychological assessment at baseline and after 2 years of follow-up. A composite memory score for the 2-year change in the results of two delayed-recall tests was calculated, and memory decline was defined as a composite score that was at least 1 standard deviation below the group mean score. The predictive accuracy of the brain volumes was estimated by using areas under receiver operating characteristic curves and was further assessed by using leave-one-out cross validation. RESULTS: Use of the most accurate region model, which included the hippocampus; parahippocampal gyrus; amygdala; superior, middle, and inferior temporal gyri; superior parietal lobe; and posterior cingulate gyrus, resulted in a fitted accuracy of 94% and a cross-validated accuracy of 81%. CONCLUSION: Study results indicate that automated temporal and parietal volumes can be used to identify with high accuracy cognitively healthy individuals who are at risk for future memory decline. Further validation of this predictive model in a new cohort is required. |
| DOI | 10.1148/radiol.11101637 |
| PubMed ID | 21467255 |
| PubMed Central ID | PMC3099048 |