… in the news …

Diagnosing Schizophrenia 2017.07

Computational Psychiatry 2015.10

fMRI (Collaboration with IBM) 2015.09, 06

NMR Spectroscopy 2015.05

MITAC Globalink students 2014.07

ER Status

2013

(for pre-2008: see here)


Diagnosing Schizophrenia

Our team (led by Mina Gheiratmand [UofA] and Irina Rish [IBM]) published an article (in Nature Schizophrenia) describing a way diagnose schizophrenia.

See also Metrics

[Sponsored by CIHR, NSERC, IBM CAS Alberta, AMII]


Computational Psychiatry on Global Edmonton Health Matters

Global's Su-Ling Goh talks to Professors Russ Greiner and Matt Brown about their research into using computers to analyze MRI brain scans to diagnose and treat mental illness (in collaboration with IBM).

Global News Clip (Video [ 1:30 ] - 2015.10.14)


Collaboration with IBM (CAS) -- fMRI

Dr. Russ Greiner and members of his lab at the University of Alberta are applying machine-learning approaches to find patterns in brain imaging that will help predict or diagnose brain dysfunctions such as ADHD, Alzheimers and schizophrenia. “We’re helping to advance the emerging field of ‘computational psychiatry.’ Both diagnostic and prognostic tools have high potential for commercialization, to be further developed in companies in Alberta, and elsewhere,” says Dr. Greiner. Currently diagnoses are typically subjective as they are based on a professional’s assessment of whether a patient exhibits a benchmark combination of behaviours on list of criteria. Using IBM technology, researchers at University of Alberta and the University of Calgary will instead build a bio-based system to help identify and develop better, faster, more reliable treatments for mental health, one of the most expensive disease categories in the developed world.

See IBM News Release (2015.06.24) 

Also Moods magazine (2015.09.01)



Accurately Interpreting NMR Spectroscopy

Many diseases cause significant changes to the concentrations of small molecules (a.k.a. metabolites) that appear in a person’s biofluids, which means such diseases can often be readily detected from a person’s “metabolic profile"—i.e., the list of concentrations of those metabolites. This information can be extracted from a biofluid’s Nuclear Magnetic Resonance (NMR) spectrum. We present a system, BAYESIL, that can quickly, accurately, and autonomously produce a person’s metabolic profile.

News coverage:



Hosting Globalink Internship Students

International undergrads can join U of Alberta research groups for the summer, with funding provided by the Mitacs Globalink program. My lab had the honor of hosting two Mitacs Globalink Summer Students (July 2014).

This was covered by



Accurately Predicting Estrogen Receptor Status

The best treatment for a woman with breast cancer depends on whether her tumor is Estrogen Receptor positive or not (ER+ vs ER-).  A team of researchers, from both Alberta Health Services and AICML, used a machine learning approach to produce a tool that can effectively predict this ER status of a patient, based on the expression values of just 3 genes.   They show that this predictive tool is very robust, as it also works extremely well in multiple other studies, across different platforms.

News coverage:

 The article itself is

Also: