A Predictive Model for Identifying Possible MCI to AD Conversions in the ADNI Database

Alzheimer's disease (AD) is one of the most common forms of dementia and has become a serious issue among the elderly in the aging society. Since AD is incurable and degenerative, early diagnosis is essential, which can give patients and their family more opportunities to arrange their lives. In the meantime, histopathologic studies have found that MCI (Mild Cognitive Impairment) subjects usually have intermediate levels of AD pathology. In this paper, a predictive model is developed for identifying possible conversions from MCI to AD based on the ADNI (Alzheimer's Disease Neuroimaging Initiative) database. It is shown that, with the help of a range of advanced data mining techniques, the developed model can achieve promising performance with AUC around 0.88.

[1]  J. Schneider,et al.  Mild cognitive impairment is related to Alzheimer disease pathology and cerebral infarctions , 2005, Neurology.

[2]  S. Bookheimer,et al.  Structural and functional neuroimaging in Alzheimer's disease: an update. , 2002, Current topics in medicinal chemistry.

[3]  Pat Langley,et al.  Estimating Continuous Distributions in Bayesian Classifiers , 1995, UAI.

[4]  Nitesh V. Chawla,et al.  Editorial: special issue on learning from imbalanced data sets , 2004, SKDD.

[5]  Kaizhu Huang,et al.  Learning classifiers from imbalanced data based on biased minimax probability machine , 2004, CVPR 2004.

[6]  C. Gillberg,et al.  Looking Backward to Move Forward: Early Detection of Neurodegenerative Disorders , 2003 .

[7]  Aiko M. Hormann,et al.  Programs for Machine Learning. Part I , 1962, Inf. Control..

[8]  David W. Aha,et al.  Instance-Based Learning Algorithms , 1991, Machine Learning.

[9]  Bennett P Leifer.  Early Diagnosis of Alzheimer's Disease: Clinical and Economic Benefits , 2003, Journal of the American Geriatrics Society.

[10]  B. Miller,et al.  CME Practice parameter : Diagnosis of dementia ( an evidence-based review ) Report of the Quality Standards Subcommittee of the American Academy of Neurology , 2001 .

[11]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[12]  Charles Elkan,et al.  The Foundations of Cost-Sensitive Learning , 2001, IJCAI.

[13]  A. Demetriades.  Functional neuroimaging in Alzheimer's type dementia , 2002, Journal of the Neurological Sciences.

[14]  S. Bookheimer,et al.  Structural and functional neuroimaging in Alzheimer's disease: an update. , 2002, Current topics in medicinal chemistry.

[15]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[16]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[17]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..