Boosting power for clinical trials using classifiers based on multiple biomarkers

NEUROBIOLOGY OF AGING

卷:31

Article

Kohannim, Omid¹  Hua, Xue¹  Hibar, Derrek P.¹  Lee, Suh¹  Chou, Yi-Yu¹  Toga, Arthur W.¹  Jack, Clifford R., Jr.²  Weiner, Michael W.^3,4,5  Thompson, Paul M.¹ 

[1] Univ Calif Los Angeles, Sch Med, Dept Neurol, Lab Neuro Imaging, Los Angeles, CA 90095 USA

[2] Mayo Clin, Dept Radiol, Rochester, MN USA

[3] Univ Calif San Francisco, Dept Radiol & Biomed Imaging, San Francisco, CA 94143 USA

[4] Univ Calif San Francisco, Dept Med, San Francisco, CA USA

[5] Univ Calif San Francisco, Dept Psychiat, San Francisco, CA 94143 USA

关键词: Clinical trial enrichment;    Alzheimer's disease;    Mild cognitive impairment;    Magnetic resonance imaging;    Neuroimaging;    Biomarkers;    Classification;    Support vector machines;   

DOI  :  10.1016/j.neurobiolaging.2010.04.022

来源: Elsevier

【 摘 要 】

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 A beta(42)), ApoE genotype, age, sex, and body mass index. MRI measures contributed most to Alzheimer's disease (AD) classification; PET-FDG and CSF biomarkers, particularly A beta(42), 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. (C) 2010 Elsevier Inc. All rights reserved.

【 授权许可】

Free