28 Jan Machine Learning Enhanced Blood Biomarkers Predict Progression of Neurodegenerative Diseases
Posted at 18:17h
in Alzheimer's - Dementia, Author Interviews, Cognitive Issues, McGill, Neurology, Technology
MedicalResearch.com Interview with:
[caption id="attachment_52997" align="alignleft" width="160"]
Dr. Iturria-Medina[/caption]
Yasser Iturria-Medina PhD
Assistant Professor, Department of Neurology and Neurosurgery
Associate member of the Ludmer Centre for Neuroinformatics and
Mental Health McConnell Brain Imaging Centre
McGill University
MedicalResearch.com: What is the background for this study?
Response: As background, two main points:
- Almost all molecular (gene expression) analyses performed in neurodegeneration are based on snapshots data, taking at one or a few time points covering the disease's large evolution. Because neurodegenerative diseases take decades to develop, until now we didn't have a dynamical characterization of these diseases. Our study tries to overcome such limitation, proposing a data-driven methodology to study long term dynamical changes associated to disease.


Dr. Dunn[/caption]
Dr. Amy Dunn, PhD
Kaczorowski lab
The Jackson Laboratory
MedicalResearch.com: What is the background for this study? What are the main findings?
Response: Environmental factors, such as a poor diet, are known risk factors for Alzheimer’s disease. But the mechanisms are complex, and it is not known how such environmental perturbations interact with individual genetic variation to confer disease risk. Previous studies have not adequately addressed how the combination of genetic variant and environmental factors combine to alter cognitive response to a poor diet.
To investigate gene-by-environment interactions, we fed either a normal diet or a high-fat diet to a genetically diverse Alzheimer’s disease mouse model population starting at six months of age and monitored metabolic and cognitive function.
We observed accelerated working memory decline in the mice on the high-fat diet after eight weeks, with substantial gene-by diet effects on both cognitive and metabolic traits.
Metabolic dysfunction was more closely related to cognitive function in mice carrying Alzheimer’s mutations than in those without. Interestingly, the high-fat diet affected metabolic function differently in female versus male mice.

Dr. Mikkola[/caption]
Tomi Mikkola MD
Associate Professor
Helsinki University Hospital
Department of Obstetrics and Gynecology
Helsinki, Finland
MedicalResearch.com: What is the background for this study? What are the main findings?
Response: In Finland we have perhaps the most comprehensive and reliable medical registers in the world. Thus, with my research group I have conducted various large studies evaluating association of postmenopausal hormone therapy use and various major diseases (see e.g. the references in the B;MJ paper). There has been various smaller studies indicating that hormone therapy might be protective for all kinds of dementias, also Alzheimer’s disease.
However, we have quite recently shown that hormone therapy seems to lower the mortality risk of vascular dementia but not Alzheimer’s disease (Mikkola TS et al. J Clin Endocrinol Metab 2017;102:870-7). Now in this upcoming BMJ-paper we report in a very large case-control study (83 688 women with Alzheimer’s disease and same number of control women without the disease) that systemic hormone therapy was associated with a 9-17% increased risk of Alzheimer’s disease.
Furthermore, this risk increase is particularly in women using hormone therapy long, for more than 10 years. This was somewhat surprising finding, but it underlines the fact that mechanisms behind Alzheimer’s disease are likely quite different than in vascular dementia, where the risk factors are similar as in cardiovascular disease. We have also shown how hormone therapy protects against cardiovascular disease, particularly in women who initiate hormone therapy soon after menopause.
