Boosting power for clinical trials using classifiers based on multiple biomarkers

Omid Kohannim, Xue Hua, Derrek P. Hibar, Suh Lee, Yi Y. Chou, Arthur W. Toga, Clifford R Jr. Jack, Michael W. Weiner, Paul M. Thompson

Research output: Contribution to journalArticle

114 Citations (Scopus)

Abstract

Machine learning methods pool diverse information to perform computer-assisted diagnosis and predict future clinical decline. We introduce a machine learning method to boost power in clinical trials. We created a Support Vector Machine algorithm that combines brain imaging and other biomarkers to classify 737 Alzheimer's disease Neuroimaging initiative (ADNI) subjects as having Alzheimer's disease (AD), mild cognitive impairment (MCI), or normal controls. We trained our classifiers based on example data including: MRI measures of hippocampal, ventricular, and temporal lobe volumes, a PET-FDG numerical summary, CSF biomarkers (t-tau, p-tau, and Aβ42), ApoE genotype, age, sex, and body mass index. MRI measures contributed most to Alzheimer's disease (AD) classification; PET-FDG and CSF biomarkers, particularly Aβ42, contributed more to MCI classification. Using all biomarkers jointly, we used our classifier to select the one-third of the subjects most likely to decline. In this subsample, fewer than 40 AD and MCI subjects would be needed to detect a 25% slowing in temporal lobe atrophy rates with 80% power-a substantial boosting of power relative to standard imaging measures.

Original languageEnglish (US)
Pages (from-to)1429-1442
Number of pages14
JournalNeurobiology of Aging
Volume31
Issue number8
DOIs
StatePublished - Aug 2010

Fingerprint

Alzheimer Disease
Biomarkers
Clinical Trials
Temporal Lobe
Neuroimaging
Computer-Assisted Diagnosis
Apolipoproteins E
Atrophy
Body Mass Index
Genotype
Power (Psychology)
Cognitive Dysfunction
Machine Learning

Keywords

  • Alzheimer's disease
  • Biomarkers
  • Classification
  • Clinical trial enrichment
  • Magnetic resonance imaging
  • Mild cognitive impairment
  • Neuroimaging
  • Support vector machines

ASJC Scopus subject areas

  • Aging
  • Developmental Biology
  • Geriatrics and Gerontology
  • Clinical Neurology
  • Neuroscience(all)

Cite this

Kohannim, O., Hua, X., Hibar, D. P., Lee, S., Chou, Y. Y., Toga, A. W., ... Thompson, P. M. (2010). Boosting power for clinical trials using classifiers based on multiple biomarkers. Neurobiology of Aging, 31(8), 1429-1442. https://doi.org/10.1016/j.neurobiolaging.2010.04.022

Boosting power for clinical trials using classifiers based on multiple biomarkers. / Kohannim, Omid; Hua, Xue; Hibar, Derrek P.; Lee, Suh; Chou, Yi Y.; Toga, Arthur W.; Jack, Clifford R Jr.; Weiner, Michael W.; Thompson, Paul M.

In: Neurobiology of Aging, Vol. 31, No. 8, 08.2010, p. 1429-1442.

Research output: Contribution to journalArticle

Kohannim, O, Hua, X, Hibar, DP, Lee, S, Chou, YY, Toga, AW, Jack, CRJ, Weiner, MW & Thompson, PM 2010, 'Boosting power for clinical trials using classifiers based on multiple biomarkers', Neurobiology of Aging, vol. 31, no. 8, pp. 1429-1442. https://doi.org/10.1016/j.neurobiolaging.2010.04.022
Kohannim, Omid ; Hua, Xue ; Hibar, Derrek P. ; Lee, Suh ; Chou, Yi Y. ; Toga, Arthur W. ; Jack, Clifford R Jr. ; Weiner, Michael W. ; Thompson, Paul M. / Boosting power for clinical trials using classifiers based on multiple biomarkers. In: Neurobiology of Aging. 2010 ; Vol. 31, No. 8. pp. 1429-1442.
@article{26719222a4a4406aafa4eef3dea31b84,
title = "Boosting power for clinical trials using classifiers based on multiple biomarkers",
abstract = "Machine learning methods pool diverse information to perform computer-assisted diagnosis and predict future clinical decline. We introduce a machine learning method to boost power in clinical trials. We created a Support Vector Machine algorithm that combines brain imaging and other biomarkers to classify 737 Alzheimer's disease Neuroimaging initiative (ADNI) subjects as having Alzheimer's disease (AD), mild cognitive impairment (MCI), or normal controls. We trained our classifiers based on example data including: MRI measures of hippocampal, ventricular, and temporal lobe volumes, a PET-FDG numerical summary, CSF biomarkers (t-tau, p-tau, and Aβ42), ApoE genotype, age, sex, and body mass index. MRI measures contributed most to Alzheimer's disease (AD) classification; PET-FDG and CSF biomarkers, particularly Aβ42, contributed more to MCI classification. Using all biomarkers jointly, we used our classifier to select the one-third of the subjects most likely to decline. In this subsample, fewer than 40 AD and MCI subjects would be needed to detect a 25{\%} slowing in temporal lobe atrophy rates with 80{\%} power-a substantial boosting of power relative to standard imaging measures.",
keywords = "Alzheimer's disease, Biomarkers, Classification, Clinical trial enrichment, Magnetic resonance imaging, Mild cognitive impairment, Neuroimaging, Support vector machines",
author = "Omid Kohannim and Xue Hua and Hibar, {Derrek P.} and Suh Lee and Chou, {Yi Y.} and Toga, {Arthur W.} and Jack, {Clifford R Jr.} and Weiner, {Michael W.} and Thompson, {Paul M.}",
year = "2010",
month = "8",
doi = "10.1016/j.neurobiolaging.2010.04.022",
language = "English (US)",
volume = "31",
pages = "1429--1442",
journal = "Neurobiology of Aging",
issn = "0197-4580",
publisher = "Elsevier Inc.",
number = "8",

}

TY - JOUR

T1 - Boosting power for clinical trials using classifiers based on multiple biomarkers

AU - Kohannim, Omid

AU - Hua, Xue

AU - Hibar, Derrek P.

AU - Lee, Suh

AU - Chou, Yi Y.

AU - Toga, Arthur W.

AU - Jack, Clifford R Jr.

AU - Weiner, Michael W.

AU - Thompson, Paul M.

PY - 2010/8

Y1 - 2010/8

N2 - Machine learning methods pool diverse information to perform computer-assisted diagnosis and predict future clinical decline. We introduce a machine learning method to boost power in clinical trials. We created a Support Vector Machine algorithm that combines brain imaging and other biomarkers to classify 737 Alzheimer's disease Neuroimaging initiative (ADNI) subjects as having Alzheimer's disease (AD), mild cognitive impairment (MCI), or normal controls. We trained our classifiers based on example data including: MRI measures of hippocampal, ventricular, and temporal lobe volumes, a PET-FDG numerical summary, CSF biomarkers (t-tau, p-tau, and Aβ42), ApoE genotype, age, sex, and body mass index. MRI measures contributed most to Alzheimer's disease (AD) classification; PET-FDG and CSF biomarkers, particularly Aβ42, contributed more to MCI classification. Using all biomarkers jointly, we used our classifier to select the one-third of the subjects most likely to decline. In this subsample, fewer than 40 AD and MCI subjects would be needed to detect a 25% slowing in temporal lobe atrophy rates with 80% power-a substantial boosting of power relative to standard imaging measures.

AB - Machine learning methods pool diverse information to perform computer-assisted diagnosis and predict future clinical decline. We introduce a machine learning method to boost power in clinical trials. We created a Support Vector Machine algorithm that combines brain imaging and other biomarkers to classify 737 Alzheimer's disease Neuroimaging initiative (ADNI) subjects as having Alzheimer's disease (AD), mild cognitive impairment (MCI), or normal controls. We trained our classifiers based on example data including: MRI measures of hippocampal, ventricular, and temporal lobe volumes, a PET-FDG numerical summary, CSF biomarkers (t-tau, p-tau, and Aβ42), ApoE genotype, age, sex, and body mass index. MRI measures contributed most to Alzheimer's disease (AD) classification; PET-FDG and CSF biomarkers, particularly Aβ42, contributed more to MCI classification. Using all biomarkers jointly, we used our classifier to select the one-third of the subjects most likely to decline. In this subsample, fewer than 40 AD and MCI subjects would be needed to detect a 25% slowing in temporal lobe atrophy rates with 80% power-a substantial boosting of power relative to standard imaging measures.

KW - Alzheimer's disease

KW - Biomarkers

KW - Classification

KW - Clinical trial enrichment

KW - Magnetic resonance imaging

KW - Mild cognitive impairment

KW - Neuroimaging

KW - Support vector machines

UR - http://www.scopus.com/inward/record.url?scp=77954032616&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954032616&partnerID=8YFLogxK

U2 - 10.1016/j.neurobiolaging.2010.04.022

DO - 10.1016/j.neurobiolaging.2010.04.022

M3 - Article

VL - 31

SP - 1429

EP - 1442

JO - Neurobiology of Aging

JF - Neurobiology of Aging

SN - 0197-4580

IS - 8

ER -