Abstract
BACKGROUND: Identification of biomarkers for the Alzheimer's disease (AD) is a challenge and a very difficult task both for medical research and data analysis. METHODS: We applied a novel clustering tool with the goal to identify subpopulations of the AD patients that are homogeneous in respect of available clinical as well as in respect of biological descriptors. RESULTS: The main result is identification of three clusters of patients with significant problems with dementia. The evaluation of properties of these clusters demonstrates that brain atrophy is the main driving force of dementia. The unexpected result is that the largest subpopulation that has very significant problems with dementia has besides mild signs of brain atrophy also large ventricular, intracerebral and whole brain volumes. Due to the fact that ventricular enlargement may be a consequence of brain injuries and that a large majority of patients in this subpopulation are males, a potential hypothesis is that such medical status is a consequence of a combination of previous traumatic events and degenerative processes. CONCLUSIONS: The results may have substantial consequences for medical research and clinical trial design. The clustering methodology used in this study may be interesting also for other medical and biological domains.