Classification of dementia types from cognitive profiles data

Corani, Giorgio and Edgar, Chris and Marshall, Isabelle and Wesnes, Keith and Zaffalon, Marco (2006) Classification of dementia types from cognitive profiles data. In: Knowledge Discovery in Databases: PKDD 2006 10th European Conference on Principle and Practice of Knowledge Discovery in Databases, 18.09.2006-22.09.2006, Berlin, Germany.

[img]
Preview
Text
Classification of dementia types from cognitive profiles data.pdf - Published Version

Download (126kB) | Preview

Abstract

The Cognitive Drug Research (CDR) system is specifically validated for dementia assessment; it consists of a series of computerized tests, which assess the cognitive faculties of the patient to derive a cognitive profile. We use six different classification algorithms to classify clinically diagnosed diseases from their cognitive profiles. Good accuracy was obtained in separating patients affected by Parkinson’s disease from demented patients, and in discriminating between Alzheimer’s disease and Vascular Dementia. However, in discriminating between Parkinson disease with dementia (PDD) and dementia with Lewy bodies (DLB), the accuracy was only slightly superior to chance; the existence of a significant difference in the cognitive profiles of DLB and PDD is indeed questioned in the medical literature.

Actions (login required)

View Item View Item