Ensemble Based Data Fusion for Early Diagnosis of Alzheimer's Disease

We describe an ensemble of classifiers based data fusion approach to combine information from two sources, believed to contain complimentary information, for early diagnosis of Alzheimer's disease. Specifically, we use the event related potentials recorded from the Pz and Cz electrodes of the EEG, which are further analyzed using multiresolution wavelet analysis. The proposed data fusion approach includes generating multiple classifiers trained with strategically selected subsets of the training data from each source, which are then combined through a weighted majority voting. Several factors set this study apart from similar prior efforts: we use a larger cohort, specifically target early diagnosis of the disease, use an ensemble based approach rather then a single classifier, and most importantly, we combine information from multiple sources, rather then using a single modality. We present promising results obtained from the first 35 (of 80) patients whose data are analyzed thus far

[1]  F E Bloom,et al.  P300 assessment of early Alzheimer's disease. , 1990, Electroencephalography and clinical neurophysiology.

[2]  M. Folstein,et al.  Clinical diagnosis of Alzheimer's disease , 1984, Neurology.

[3]  Josef Kittler,et al.  Multiple expert system design by combined feature selection and probability level fusion , 2000, Proceedings of the Third International Conference on Information Fusion.

[4]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[5]  Vasant Honavar,et al.  Learn++: an incremental learning algorithm for supervised neural networks , 2001, IEEE Trans. Syst. Man Cybern. Part C.

[6]  R. Polikar,et al.  Multiresolution analysis for early diagnosis of Alzheimer's disease , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  Ahmet Ademoglu,et al.  Analysis of functional components of P300 by wavelet transform , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[8]  Arthur Petrosian,et al.  Power frequency and wavelet characteristics in differentiating between normal and Alzheimer EEG , 2002, Proceedings of the Second Joint 24th Annual Conference and the Annual Fall Meeting of the Biomedical Engineering Society] [Engineering in Medicine and Biology.

[9]  Ludmila I. Kuncheva,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2004 .

[10]  Robert A. Jacobs,et al.  Hierarchical Mixtures of Experts and the EM Algorithm , 1993, Neural Computation.

[11]  Ludmila I. Kuncheva,et al.  A Theoretical Study on Six Classifier Fusion Strategies , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Luis O. Jimenez,et al.  Classification of hyperdimensional data based on feature and decision fusion approaches using projection pursuit, majority voting, and neural networks , 1999, IEEE Trans. Geosci. Remote. Sens..

[13]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Johannes R. Sveinsson,et al.  Use of multiple classifiers in classification of data from multiple data sources , 2001, IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No.01CH37217).

[15]  S. Kobayashi,et al.  Event-related brain potentials in response to novel sounds in dementia , 2000, Clinical Neurophysiology.

[16]  Linda Teri,et al.  Clinico‐Neuropathological Correlation of Alzheimer's Disease in a Community‐Based Case Series , 1999, Journal of the American Geriatrics Society.

[17]  Ben H. Jansen,et al.  An exploratory study of factors affecting single trial P300 detection , 2004, IEEE Transactions on Biomedical Engineering.

[18]  A Ademoglu,et al.  Decomposition of Event-Related Brain Potentials into Multiple Functional Components Using Wavelet Transform , 2001, Clinical EEG.