28 Jan Machine Learning Enhanced Blood Biomarkers Predict Progression of Neurodegenerative Diseases
MedicalResearch.com Interview with:
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
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.
Also, we still lacked robust minimally invasive and low-cost biomarkers of individual neuropathological progression. Our method is able to offer both in-vivo and post-mortem disease staging highly predictive of neuropathological and clinical alterations.
MedicalResearch.com: What should readers take away from your report?
- The fact that it is possible to study long-term changes underlying pathological progression based on the machine learning analysis of population data, and without the need to follow each participant for decades.
- Also, the possibility to obtain individual molecular scores of disease evolution based on minimally invasive blood tests.
- Both previous points could imply a better understanding of neurodegeneration, considering dynamical gene roles in disease, and, importantly, could facilitate also the use of molecular scores on the daily clinic and the continuous evaluation of clinical trials.
MedicalResearch.com: What recommendations do you have for future research as a result of this work?
Response: To consider as much data as possible on the study of neurological disorders. For instance, from just a blood test, we can infer now multiple brain properties and the potential clinical decline of a patient. I believe the models will get better with the inclusion of other data modalities.
MedicalResearch.com: Is there anything else you would like to add?
Response: We are moving forward to further extend and validate this model, considering other relevant biological variables (e.g. electrophysiology, proteomics) and different diseased populations.
Yasser Iturria-Medina, Ahmed F Khan, Quadri Adewale, Amir H Shirazi, Alzheimer’s Disease Neuroimaging Initiative, Blood and brain gene expression trajectories mirror neuropathology and clinical deterioration in neurodegeneration,
Brain, awz400, https://doi.org/10.1093/brain/awz400
The information on MedicalResearch.com is provided for educational purposes only, and is in no way intended to diagnose, cure, or treat any medical or other condition. Always seek the advice of your physician or other qualified health and ask your doctor any questions you may have regarding a medical condition. In addition to all other limitations and disclaimers in this agreement, service provider and its third party providers disclaim any liability or loss in connection with the content provided on this website.