Search

A generalized strategy is developed to predict the occurrence of a multicategory-multifactorial disease from a set of medical risk factors that are most often used to screen patients for the disease. The prediction problem is formulated as an M-class classification problem. The strategy employs fusion to combine risk factors into a single feature vector, normalization to fuse risk factors which have different formats and ranges, rank-sum ordering for feature selection, discrete Karhunen-Loeve transform-based transformation to facilitate parametric classifier development, and the design of parametric classifiers. Two methods, which differ on how the features are selected, are developed. In the first method, features are selected from a set consisting of linear combinations of all risk factors. In the second method, the features are linear combinations of a preselected subset of the risk factors. The methods are applied to predict the occurrence of Alzheimer's disease (AD) into three classes: Probable-AD, Possible-AD, and Uncertain. It is shown that a classification accuracy of over 71% can be obtained. This result is quite encouraging given that AD is very difficult to clinically diagnose. Higher classification accuracies can be expected for diseases that are not as complex to diagnose as AD. Most importantly, it is concluded that the generalized strategy can not only be applied to the multicategory-multifactorial disease prediction problem but also to other multiclass pattern recognition problems involving diverse information collected from different sources. [ABSTRACT FROM AUTHOR]

Objective: This study examined the clinical features of patients with clinical diagnoses of probable Alzheimer disease (AD), possible AD, and uncertain.Design: Case study comparing three groups of AD patients diagnosed at their initial visit to an Alzheimer outpatient clinic.Setting: Southern Illinois University School of Medicine's Center for Alzheimer Disease and Related Disorders (CADRD) assessment sites (20) in rural Illinois.Participants: 300 patients assessed at CADRD between January 1, 1994 and July 1, 2000.Measurements: Patients were given an extensive clinical battery consisting of physical and neurologic examination, mental status testing including the Mini-Mental State Exam (MMSE), Short Blessed Dementia (SBD) and Blessed Dementia Scale (ADL), medical history evaluation, and laboratory tests. Other data included age at visit, gender, and medical history variables.Results: Mean MMSE, SBD, and ADL scores differed significantly between groups (p's < 0.01). In all three cognitive tests, the uncertain group was the least impaired while the probable AD group was the most impaired. A Rasch model indicated that only the cognitive measures were useful in discriminating between the three diagnostic groups.Conclusion: In general, probable AD patients were distinguished from possible AD patients by the severity of their dementia as measured by the MMSE, ADL and SBD as well as Hachinski-Ischemic Score (HIS) scores. A Rasch model did well at predicting group membership based upon dementia measures only. The uncertain group differed from the AD groups in age and dementia severity as measured by the MMSE, ADL and SBD. Noting differences between this and previous studies, we speculate disparity may be related to differences in population ethnicity. [ABSTRACT FROM AUTHOR]

Objective Since patients with dementia with Lewy bodies (DLB) tend to have greater impairment of attention and construction and better memory ability on neuropsychological tests than patients with Alzheimer's disease (AD), we determined if the items that measure attention, memory, and construction in the Mini-Mental State Examination (MMSE) help to distinguish DLB from AD early in the course of the dementia. Design We retrospectively studied the first available MMSE exam for each of our patients with DLB or AD and compared their MMSE subscores for attention, memory, and construction. Setting A university dementia brain bank in central Illinois, USA. Patients All patients with neuropathologically-proven DLB or AD with MMSE scores≥13. Results We identified 17 DLB and 27 AD patients for whom we had MMSE exams. The attention and construction subtest scores of the DLB group were worse (p =0.0071 and p =0.0038, respectively) than those of the AD group. The memory subscores of the DLB group were better, although the difference did not reach statistical significance (p =0.22). When a mathematical equation was used to combine the three subscores with equal weighting ($Attention-{5\over 3}\;Memory+5\cdot Construction$), the scores of the DLB group were worse (p =0.00007). Using this equation, a score less than 5 points was associated with DLB with a sensitivity of 0.82 (95% Confidence Interval (CI)=0.57–0.96) and a specificity of 0.81 (95% CI=0.62–0.94). Conclusions Our findings support the work of others regarding the relative neuropsychological impairments of DLB and AD and indicate that the MMSE may be helpful in the differentiation of DLB and AD. Copyright © 2002 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

The strategy of delaying or retarding the progression of Alzheimer's disease requires early diagnosis and treatment. Previous research indicates that measurement of changes in olfaction and cognition will play an important role in the early detection of AD and in the monitoring of therapy effectiveness. Using the data of 177 subjects, our objective was to study the measurement properties of the University of Pennsylvania Smell Identification Test (UPSIT) using a Rasch scaling framework. The results indicate that the UPSIT can yield a linear, unbiased, and unidimensional Rasch measure of human smell recognition abilities. As expected, olfactory recognition ability decreased with age, and at the rate of about 0.05 Logits per year. Also, Alzheimer's patients showed a decrease in smell recognition equivalent to that experienced by healthy subjects over the course of 30 years. Hormone replacement therapy was not found to affect healthy women's olfactory recognition ability. Additional diagnostic information can be extracted from the analysis of incorrect responses patterns that is relevant to group membership. [ABSTRACT FROM AUTHOR]

Presents a letter to the editor on the use of the Mini-Mental State Examination to differentiate Alzheimer's disease from dementia with Lewy bodies.

Objective: To determine the capability of patients with Alzheimer's disease (AD) and age-matched controls to discriminate and recognize odorants equilibrated for strength and familiarity, and to determine if immediate corrective-feedback can improve performance in either task. Major results: No significant differences between elderly controls (EC) and AD patients were apparent for the discrimination task regardless of feedback condition. The EC group outperformed the AD group on the recognition task. Feedback enhanced EC group performance but failed to benefit the AD group. Conclusions: Early in the disease process, AD subjects have a deficit in processing olfactory cues at levels beyond that necessary for discrimination. This deficit is specifically related to the olfactory system and is in addition to any general cognitive deficits they may have. Feedback is ineffective for AD subjects but can greatly enhance the performance of the intact elderly on tasks requiring the verbal mediation of olfactory cues. [ABSTRACT FROM AUTHOR]