Structural and functional biomarkers of prodromal Alzheimer's disease: A high-dimensional pattern classification study. Fan, Y., Resnick, S. M., Wu, X., & Davatzikos, C. Neuroimage, 41(2):277--285, June, 2008. abstract bibtex This work builds upon previous studies that reported high sensitivity and specificity in classifying individuals with mild cognitive impairment (MCI), which is often a prodromal phase of Alzheimer's disease (AD), via pattern classification of MRI scans. The current study integrates MRI and PET 15O water scans from 30 participants in the Baltimore Longitudinal Study of Aging, and tests the hypothesis that joint evaluation of structure and function can yield higher classification accuracy than either alone. Classification rates of up to 100% accuracy were achieved via leave-one-out cross-validation, whereas conservative estimates of generalization performance in new scans, evaluated via bagging cross-validation, yielded an area under the receiver operating characteristic (ROC) curve equal to 0.978 (97.8%), indicating excellent diagnostic accuracy. Spatial maps of regions determined to contribute the most to the classification implicated many temporal, prefrontal, orbitofrontal, and parietal regions. Detecting complex patterns of brain abnormality in early stages of cognitive impairment has pivotal importance for the detection and management of AD.
@Article{Fan2008,
author = {Fan, Yong and Resnick, Susan M. and Wu, Xiaoying and Davatzikos, Christos},
title = {{Structural and functional biomarkers of prodromal Alzheimer's disease: A high-dimensional pattern classification study}},
journal = {Neuroimage},
year = {2008},
volume = {41},
number = {2},
pages = {277--285},
month = jun,
abstract = {This work builds upon previous studies that reported high sensitivity and specificity in classifying individuals with mild cognitive impairment (MCI), which is often a prodromal phase of Alzheimer's disease (AD), via pattern classification of MRI scans. The current study integrates MRI and PET 15O water scans from 30 participants in the Baltimore Longitudinal Study of Aging, and tests the hypothesis that joint evaluation of structure and function can yield higher classification accuracy than either alone. Classification rates of up to 100\% accuracy were achieved via leave-one-out cross-validation, whereas conservative estimates of generalization performance in new scans, evaluated via bagging cross-validation, yielded an area under the receiver operating characteristic (ROC) curve equal to 0.978 (97.8\%), indicating excellent diagnostic accuracy. Spatial maps of regions determined to contribute the most to the classification implicated many temporal, prefrontal, orbitofrontal, and parietal regions. Detecting complex patterns of brain abnormality in early stages of cognitive impairment has pivotal importance for the detection and management of AD.},
issn = {1053-8119},
keywords = {Alzheimer's disease; MCI; High-dimensional pattern classification; MRI; PET; Voxel-based analysis; Diagnosis of AD},
owner = {imagenes2},
timestamp = {2009.02.12}
}
Downloads: 0
{"_id":"4MhNadZstBNLP985X","bibbaseid":"fan-resnick-wu-davatzikos-structuralandfunctionalbiomarkersofprodromalalzheimersdiseaseahighdimensionalpatternclassificationstudy-2008","downloads":0,"creationDate":"2018-02-26T10:56:23.713Z","title":"Structural and functional biomarkers of prodromal Alzheimer's disease: A high-dimensional pattern classification study","author_short":["Fan, Y.","Resnick, S. M.","Wu, X.","Davatzikos, C."],"year":2008,"bibtype":"article","biburl":"http://wpd.ugr.es/~fjesusmartinez/wp-content/uploads/2016/09/pachus-mod.bib","bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Fan"],"firstnames":["Yong"],"suffixes":[]},{"propositions":[],"lastnames":["Resnick"],"firstnames":["Susan","M."],"suffixes":[]},{"propositions":[],"lastnames":["Wu"],"firstnames":["Xiaoying"],"suffixes":[]},{"propositions":[],"lastnames":["Davatzikos"],"firstnames":["Christos"],"suffixes":[]}],"title":"Structural and functional biomarkers of prodromal Alzheimer's disease: A high-dimensional pattern classification study","journal":"Neuroimage","year":"2008","volume":"41","number":"2","pages":"277--285","month":"June","abstract":"This work builds upon previous studies that reported high sensitivity and specificity in classifying individuals with mild cognitive impairment (MCI), which is often a prodromal phase of Alzheimer's disease (AD), via pattern classification of MRI scans. The current study integrates MRI and PET 15O water scans from 30 participants in the Baltimore Longitudinal Study of Aging, and tests the hypothesis that joint evaluation of structure and function can yield higher classification accuracy than either alone. Classification rates of up to 100% accuracy were achieved via leave-one-out cross-validation, whereas conservative estimates of generalization performance in new scans, evaluated via bagging cross-validation, yielded an area under the receiver operating characteristic (ROC) curve equal to 0.978 (97.8%), indicating excellent diagnostic accuracy. Spatial maps of regions determined to contribute the most to the classification implicated many temporal, prefrontal, orbitofrontal, and parietal regions. Detecting complex patterns of brain abnormality in early stages of cognitive impairment has pivotal importance for the detection and management of AD.","issn":"1053-8119","keywords":"Alzheimer's disease; MCI; High-dimensional pattern classification; MRI; PET; Voxel-based analysis; Diagnosis of AD","owner":"imagenes2","timestamp":"2009.02.12","bibtex":"@Article{Fan2008,\n author = {Fan, Yong and Resnick, Susan M. and Wu, Xiaoying and Davatzikos, Christos},\n title = {{Structural and functional biomarkers of prodromal Alzheimer's disease: A high-dimensional pattern classification study}},\n journal = {Neuroimage},\n year = {2008},\n volume = {41},\n number = {2},\n pages = {277--285},\n month = jun,\n abstract = {This work builds upon previous studies that reported high sensitivity and specificity in classifying individuals with mild cognitive impairment (MCI), which is often a prodromal phase of Alzheimer's disease (AD), via pattern classification of MRI scans. The current study integrates MRI and PET 15O water scans from 30 participants in the Baltimore Longitudinal Study of Aging, and tests the hypothesis that joint evaluation of structure and function can yield higher classification accuracy than either alone. Classification rates of up to 100\\% accuracy were achieved via leave-one-out cross-validation, whereas conservative estimates of generalization performance in new scans, evaluated via bagging cross-validation, yielded an area under the receiver operating characteristic (ROC) curve equal to 0.978 (97.8\\%), indicating excellent diagnostic accuracy. Spatial maps of regions determined to contribute the most to the classification implicated many temporal, prefrontal, orbitofrontal, and parietal regions. Detecting complex patterns of brain abnormality in early stages of cognitive impairment has pivotal importance for the detection and management of AD.},\n issn = {1053-8119},\n keywords = {Alzheimer's disease; MCI; High-dimensional pattern classification; MRI; PET; Voxel-based analysis; Diagnosis of AD},\n owner = {imagenes2},\n timestamp = {2009.02.12}\n}\n\n","author_short":["Fan, Y.","Resnick, S. M.","Wu, X.","Davatzikos, C."],"key":"Fan2008","id":"Fan2008","bibbaseid":"fan-resnick-wu-davatzikos-structuralandfunctionalbiomarkersofprodromalalzheimersdiseaseahighdimensionalpatternclassificationstudy-2008","role":"author","urls":{},"keyword":["Alzheimer's disease; MCI; High-dimensional pattern classification; MRI; PET; Voxel-based analysis; Diagnosis of AD"],"downloads":0},"search_terms":["structural","functional","biomarkers","prodromal","alzheimer","disease","high","dimensional","pattern","classification","study","fan","resnick","wu","davatzikos"],"keywords":["alzheimer's disease; mci; high-dimensional pattern classification; mri; pet; voxel-based analysis; diagnosis of ad"],"authorIDs":[],"dataSources":["dWW3j9XN4xTKk2o3d"]}