TY - JOUR T1 - ApoE4 effects on automated diagnostic classifiers for mild cognitive impairment and Alzheimer's disease. AU - Apostolova,Liana G, AU - Hwang,Kristy S, AU - Kohannim,Omid, AU - Avila,David, AU - Elashoff,David, AU - Jack,Clifford R,Jr AU - Shaw,Leslie, AU - Trojanowski,John Q, AU - Weiner,Michael W, AU - Thompson,Paul M, AU - ,, Y1 - 2014/01/04/ PY - 2013/03/26/received PY - 2013/12/24/revised PY - 2013/12/24/accepted PY - 2014/3/18/entrez PY - 2014/3/19/pubmed PY - 2014/3/19/medline KW - AD, Alzheimer's disease KW - ADNI KW - ADNI, Alzheimer's Disease Neuroimaging Initiative KW - AUC, area under the curve KW - Abeta KW - Alzheimer's disease KW - ApoE, apolipoprotein E KW - Aβ, Amyloid beta KW - Aβ42, Amyloid beta with 42 amino acid residues KW - CSF, cerebrospinal fluid KW - Diagnosis KW - Hippocampus atrophy KW - ICBM, International Consortium for Brain Mapping KW - MCI, mild cognitive impairment KW - MCIc, MCI converters KW - MCInc, MCI nonconverters KW - MMSE, Mini-Mental State Examination KW - NC, normal control KW - ROC, receiver operating curve KW - SVM, support vector machine KW - Tau KW - p-tau, phosphorylated tau protein KW - t-tau, total tau protein SP - 461 EP - 72 JF - NeuroImage. Clinical JO - Neuroimage Clin VL - 4 N2 - Biomarkers are the only feasible way to detect and monitor presymptomatic Alzheimer's disease (AD). No single biomarker can predict future cognitive decline with an acceptable level of accuracy. In addition to designing powerful multimodal diagnostic platforms, a careful investigation of the major sources of disease heterogeneity and their influence on biomarker changes is needed. Here we investigated the accuracy of a novel multimodal biomarker classifier for differentiating cognitively normal (NC), mild cognitive impairment (MCI) and AD subjects with and without stratification by ApoE4 genotype. 111 NC, 182 MCI and 95 AD ADNI participants provided both structural MRI and CSF data at baseline. We used an automated machine-learning classifier to test the ability of hippocampal volume and CSF Aβ, t-tau and p-tau levels, both separately and in combination, to differentiate NC, MCI and AD subjects, and predict conversion. We hypothesized that the combined hippocampal/CSF biomarker classifier model would achieve the highest accuracy in differentiating between the three diagnostic groups and that ApoE4 genotype will affect both diagnostic accuracy and biomarker selection. The combined hippocampal/CSF classifier performed better than hippocampus-only classifier in differentiating NC from MCI and NC from AD. It also outperformed the CSF-only classifier in differentiating NC vs. AD. Our amyloid marker played a role in discriminating NC from MCI or AD but not for MCI vs. AD. Neurodegenerative markers contributed to accurate discrimination of AD from NC and MCI but not NC from MCI. Classifiers predicting MCI conversion performed well only after ApoE4 stratification. Hippocampal volume and sex achieved AUC = 0.68 for predicting conversion in the ApoE4-positive MCI, while CSF p-tau, education and sex achieved AUC = 0.89 for predicting conversion in ApoE4-negative MCI. These observations support the proposed biomarker trajectory in AD, which postulates that amyloid markers become abnormal early in the disease course while markers of neurodegeneration become abnormal later in the disease course and suggests that ApoE4 could be at least partially responsible for some of the observed disease heterogeneity. SN - 2213-1582 UR - https://www.unboundmedicine.com/medline/citation/24634832/ApoE4_effects_on_automated_diagnostic_classifiers_for_mild_cognitive_impairment_and_Alzheimer's_disease_ DB - PRIME DP - Unbound Medicine ER -