Conference Paper

Ensemble Based Data Fusion from Parietal Region Event Related Potentials for Early Diagnosis of Alzheimer's Disease

Rowan Univ., Glassboro
DOI: 10.1109/IJCNN.2007.4371335 Conference: Neural Networks, 2007. IJCNN 2007. International Joint Conference on
Source: DBLP

ABSTRACT As a natural consequence of steady increase of average population age in developed countries, Alzheimer's disease is becoming an increasingly important public health concern. The financial and emotional toll of the disease is exacerbated with lack of standard diagnostic procedures available at the community clinics and hospitals, where most patients are evaluated. In our recent preliminary results, we have reported that the event related potentials (ERPs) of the electroencephalogram can be used to train an ensemble-based classifier for automated diagnosis of Alzheimer's disease. In this study, we present an updated alternative approach by combining complementary information provided by ERPs obtained from several parietal region electrodes. The results indicate that ERPs obtained from parietal region of the cortex carry substantial complementary diagnostic information. Specifically, the diagnostic ability of such an approach is substantially better, compared to the performance obtained by using data from any of the individual electrodes alone. Furthermore, the diagnostic performance of the proposed approach compares very favorably to that obtained at community clinics and hospitals.

  • [Show abstract] [Hide abstract]
    ABSTRACT: Non-target, deviant stimuli generate an earlier latency, front-central novelty P3, whereas correctly detected task-relevant stimuli generate a parietal maximal target P3. We examined whether the P3 component to novel stimuli is affected by dementing processes, and is therefore useful for distinguishing Alzheimer's type dementia (AD) from vascular dementia (VD). We recorded ERPs to task-relevant stimuli (target P3) and novel task-irrelevant stimuli (novelty P3) in an auditory oddball task in AD (n = 16), VD (n = 16), and age-matched controls (n = 18). The amplitude, latency, and scalp topography of target and novelty P3 were compared among 3 groups using ANOVA. The relationship between P3 measures and intelligence scores were evaluated by correlation analysis. The amplitude, latency and scalp topography of the target P3 were comparably affected by both AD and VD. However, the amplitude of the novelty P3 was markedly reduced in VD, but not in AD, and the scalp topographics were different in the 3 groups. The amplitude was maximal at frontal sites in controls, at central sites in AD, and at parietal sites in VD. The target P3 latency was prolonged in both AD and VD, whereas the novelty P3 latency was only prolonged in VD. AD was discriminated satisfactorily from VD by using the novelty amplitude at Cz and the ratio of the amplitudes at Fz and Pz as independent variables. These results suggest that the response to novel stimuli is differentially affected by dementia with degenerative and vascular etiology.
    Clinical Neurophysiology 03/2000; 111(2):195-203. · 3.14 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Intracranial recordings, lesion studies, and the combination of functional imaging with source analysis have produced a solid body of evidence about the generators of the P300 event-related potential. Although it is impossible to square all findings obtained across and within methodologies, a consistent pattern of generators has emerged, with target-related responses in the parietal cortex and the cingulate and novelty-related activations mainly in the inferior parietal and prefrontal regions. Stimulus modality-specific contributions come from the inferior temporal and superior parietal cortex for the visual and from the superior temporal cortex for the auditory modality. The P300 continues to be an important signature of cognitive processes such as attention and working memory and of its dysfunction in neurologic and mental disorders. It is increasingly being investigated as a potential genetic marker of mental disorders. Knowledge about the generators of the P300 will be crucial for a better understanding of its cognitive significance and its continuing clinical application.
    The Neuroscientist 01/2006; 11(6):563-76. · 5.63 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We explored the ability of specifically designed and trained recurrent neural networks (RNNs), combined with wavelet preprocessing, to discriminate between the electroencephalograms (EEGs) of patients with mild Alzheimer's disease (AD) and their age-matched control subjects. Twomin recordings of resting eyes-closed continuous EEGs (as well as their wavelet-filtered subbands) obtained from parieto-occipital channels of 10 early AD patients and 10 healthy controls were input into RNNs for training and testing purposes. The RNNs were chosen because they can implement extremely non-linear decision boundaries and possess memory of the state, which is crucial for the considered task. The best training/testing results were achieved using a 3-layer RNN on left parietal channel level 4 high-pass wavelet subbands. When trained on 3 AD and 3 control recordings, the resulting RNN tested well on all remaining controls and 5 out of 7 AD patients. This represented a significantly better than chance performance of about 80% sensitivity at 100% specificity. The suggested combined wavelet/RNN approach may be useful in analyzing long-term continuous EEGs for early recognition of AD. This approach should be extended on larger patient populations before its clinical diagnostic value can be established. Further lines of investigation might also require that EEGs be recorded from patients engaged in certain mental (cognitive) activities.
    Clinical Neurophysiology 09/2001; 112(8):1378-87. · 3.14 Impact Factor

Full-text (2 Sources)

Available from
May 29, 2014