We are featured as one of Scientifica’s picks of must-read neuroscience stories from October 2018

We are pleased to announce that the work by Nikhil Bhagwat et al. about an artificial intelligence algorithm that can predict an individual’s cognitive decline leading to Alzheimer’s, has been selected as one of Scientifica’s best neuroscience stories from October 2018! Every month Scientifica collates a selection of the best neuroscience research stories released that month, that are breakthroughs in research.

For more information check out the links below!

Happy Halloween from the CoBrA Lab!


Predicting Alzheimer’s disease with artificial intelligence

Check out the video below where Dr. Mallar Chakravarty talks to Global’s Laura Casell about recent research from our group where cognitive decline towards Alzheimer’s disease can be predicted 5 years in advance. For more information about the original research, click the link to read the published paper Bhagwat et al. (2018). You can also click here for the full article on Global News.

Predicting Alzheimer's Disease

Check out the following articles (from The London Telegraph, UK express, and Radio-Canada) describing recent research from our group, where a Artificial Intelligence algorithm can detect patterns across MRI images, genetics, and cognitive data to recognize changes in cognition that may be putting individuals on the path towards Alzheimer’s disease. We are very proud of the attention that this important work by Nikhil Bhagwat et al. is receiving!

The Telegraph: AI could spot Alzheimer’s five years before major symptoms appear

UK Express: Dementia test: Alzheimer’s could be spotted five years before symptoms appear using this

Radio-Canada: Prédire le déclin cognitif menant à l’alzheimer grâce à l’intelligence artificielle

For more information about the original research, click the link to read the published paper Bhagwat et al. (2018)

Modeling and prediction of clinical symptom trajectories in Alzheimer’s disease

New research from our group describes a computational model that can be used for early detection of individuals at risk for clinical decline. This machine-learning model is capable of combining longitudinal, multimodal data (MRI, cognitive, genetic and demographic data) to predict the symptom progression patterns at the single subject level.

With the prevalence of Alzheimer’s disease rapidly increasing, the identification of the declining individuals a priori would provide a critical window for early intervention and preventative treatment planning. While this work holds crucial clinical utility for Alzheimer’s disease, this model can be applicable to other neurodegenerative diseases .

For more information about this research, click the link to read the paper Bhagwat et al. (2018)