Identification of Gender Specific Biomarkers for Alzheimer’s Disease

Abstract

The paper presents experiments with a novel clustering methodology that enables identification of subpopulations of the Alzheimer’s disease patients that are homogeneous in respect of both clinical and biological descriptors. It is expected that recognition of relevant connections between clinical and biological descriptors will be easier within such subpopulations. Our dataset includes 317 female and 342 male patients from the ADNI study that are described by a total of 243 biological and clinical descriptors recorded at baseline evaluation. The constructed clusters clearly demonstrate differences between female and male patient subpopulations. An interesting result is identification of a cluster of male Alzheimer’s disease patients that are, surprisingly, characterized by increased intracerebral and whole brain volumes. The finding suggests existence of two different biological pathways for the Alzheimer’s disease.

ADNI—Data used in preparation of this article were obtained from the Alzheimers Disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf