ApoE4 effects on automated diagnostic classifiers for mild cognitive impairment and Alzheimer's disease
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 ma...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2014-01-01
|
| Series: | NeuroImage: Clinical |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S221315821300171X |
| _version_ | 1818051041711620096 |
|---|---|
| author | Liana G. Apostolova Kristy S. Hwang Omid Kohannim David Avila David Elashoff Clifford R. Jack, Jr. Leslie Shaw John Q. Trojanowski Michael W. Weiner Paul M. Thompson |
| author_facet | Liana G. Apostolova Kristy S. Hwang Omid Kohannim David Avila David Elashoff Clifford R. Jack, Jr. Leslie Shaw John Q. Trojanowski Michael W. Weiner Paul M. Thompson |
| author_sort | Liana G. Apostolova |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-10T11:03:04Z |
| format | Article |
| id | doaj.art-de8308d678e340a88b432ada4cd2563a |
| institution | Directory Open Access Journal |
| issn | 2213-1582 |
| language | English |
| last_indexed | 2024-12-10T11:03:04Z |
| publishDate | 2014-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage: Clinical |
| spelling | doaj.art-de8308d678e340a88b432ada4cd2563a2022-12-22T01:51:38ZengElsevierNeuroImage: Clinical2213-15822014-01-014C46147210.1016/j.nicl.2013.12.012ApoE4 effects on automated diagnostic classifiers for mild cognitive impairment and Alzheimer's diseaseLiana G. Apostolova0Kristy S. Hwang1Omid Kohannim2David Avila3David Elashoff4Clifford R. Jack, Jr.5Leslie Shaw6John Q. Trojanowski7Michael W. Weiner8Paul M. Thompson9Department of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USADepartment of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USAImaging genetics Center, Institute for Neuroimaging and Informatics, University of Southern California, Los Angeles, CA, USADepartment of Neurology, David Geffen School of Medicine, UCLA, Los Angeles, CA, USADepartment of Medicine Statistics Core, UCLA, Los Angeles, CA, USADepartment of Diagnostic Radiology, Mayo Clinic, Rochester, MN, USADepartment of Pathology and Laboratory Medicine, University of Pennsylvania School of Medicine, Philadelphia, PA, USADepartment of Pathology and Laboratory Medicine, University of Pennsylvania School of Medicine, Philadelphia, PA, USADepartment of Radiology, University of Pittsburgh, Pittsburgh, PA, USAImaging genetics Center, Institute for Neuroimaging and Informatics, University of Southern California, Los Angeles, CA, USABiomarkers 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.http://www.sciencedirect.com/science/article/pii/S221315821300171XAlzheimer's diseaseAbetaTauHippocampus atrophyADNIDiagnosis |
| spellingShingle | Liana G. Apostolova Kristy S. Hwang Omid Kohannim David Avila David Elashoff Clifford R. Jack, Jr. Leslie Shaw John Q. Trojanowski Michael W. Weiner Paul M. Thompson ApoE4 effects on automated diagnostic classifiers for mild cognitive impairment and Alzheimer's disease NeuroImage: Clinical Alzheimer's disease Abeta Tau Hippocampus atrophy ADNI Diagnosis |
| title | ApoE4 effects on automated diagnostic classifiers for mild cognitive impairment and Alzheimer's disease |
| title_full | ApoE4 effects on automated diagnostic classifiers for mild cognitive impairment and Alzheimer's disease |
| title_fullStr | ApoE4 effects on automated diagnostic classifiers for mild cognitive impairment and Alzheimer's disease |
| title_full_unstemmed | ApoE4 effects on automated diagnostic classifiers for mild cognitive impairment and Alzheimer's disease |
| title_short | ApoE4 effects on automated diagnostic classifiers for mild cognitive impairment and Alzheimer's disease |
| title_sort | apoe4 effects on automated diagnostic classifiers for mild cognitive impairment and alzheimer s disease |
| topic | Alzheimer's disease Abeta Tau Hippocampus atrophy ADNI Diagnosis |
| url | http://www.sciencedirect.com/science/article/pii/S221315821300171X |
| work_keys_str_mv | AT lianagapostolova apoe4effectsonautomateddiagnosticclassifiersformildcognitiveimpairmentandalzheimersdisease AT kristyshwang apoe4effectsonautomateddiagnosticclassifiersformildcognitiveimpairmentandalzheimersdisease AT omidkohannim apoe4effectsonautomateddiagnosticclassifiersformildcognitiveimpairmentandalzheimersdisease AT davidavila apoe4effectsonautomateddiagnosticclassifiersformildcognitiveimpairmentandalzheimersdisease AT davidelashoff apoe4effectsonautomateddiagnosticclassifiersformildcognitiveimpairmentandalzheimersdisease AT cliffordrjackjr apoe4effectsonautomateddiagnosticclassifiersformildcognitiveimpairmentandalzheimersdisease AT leslieshaw apoe4effectsonautomateddiagnosticclassifiersformildcognitiveimpairmentandalzheimersdisease AT johnqtrojanowski apoe4effectsonautomateddiagnosticclassifiersformildcognitiveimpairmentandalzheimersdisease AT michaelwweiner apoe4effectsonautomateddiagnosticclassifiersformildcognitiveimpairmentandalzheimersdisease AT paulmthompson apoe4effectsonautomateddiagnosticclassifiersformildcognitiveimpairmentandalzheimersdisease |