Collaboration Hub banner

Collaboration Hub

The T-CAIREM Collaboration Hub is a service to connect researchers, clinicians, healthcare practitioners, students and mentors with each other. Please fill out this Collaboration Hub submission form. Once approved, we'll post your listing as soon as possible.

U of T DNA researcher seeks advanced skills in time series prediction models

Researcher: Karim Mekhail seeks skills from another member
Institution: University of Toronto
Website: https://www.mekhaillab.com
Project aims: DNA mobility can contribute to genome stability. Although initially believed to be random, this mobility can exhibit non-random motions consistent with gaining access to repair-conducive factors. The current goal is to predict the motion of DNA and the outcome of repair on a single-cell level.
Desired skills in collaborators: Advanced knowledge of time series prediction models.

POPLAR seeks EMR data research collaborations

Researcher: Dr. Michelle Greiver
Organization: POPLAR (Primary care Ontario Practice-based Learning and Research Network)
Contact: dfcm.utopian@utoronto.ca
Website: UTOPIAN Data Safe Haven
Project aims: Collaboration between seven networks across Ontario that extract and manage primary care EMR data. Data sets provided in secure environment. To request access to data, please see https://www.dfcm.utoronto.ca/getting-utopian-support
Research team currently has these skills: Data managers, epidemiologists, data analysts, primary care clinician-scientists, primary care researchers
Desired skills in potential collaborators: Data science. We welcome applications for use of primary care EMR data. (Linkage with ICES currently underway.)
Learn more and see project collaborators: https://www.poplarnetwork.ca

UHN's DateLab seeks collaborator(s) with skills in machine learning, video analysis, computer vision

Contact: Dr. Arlene Astell
Organization: University Health Network
Website: DATE Lab
Project title and goals: Measuring movement confidence in people with dementia
Movement confidence describes the comfort and confidence people during physical activities, such as exercise. Movement confidence is linked to fall risk, which increases with age, and is even greater for people with dementia. We have collected video data of 66 people with dementia during a 20 session virtual bowling game and conducted observational analysis of their movement confidence. We wish to further analyze the data to create a measure of movement confidence that can be used to identify risk and measure the impact of exercise rehabilitation.
Research team currently has these skills: Human data collection, observational analysis of video data, psychology, kinesiology, rehab sciences, physiotherapy, occupational therapy.
Desired skills in potential collaborators: Machine learning, video analysis, computer vision. At this stage we want to know if the data we have are suitable for using machine learning to train a model to detect/assess movement confidence. If so would like to work with collaborators to develop the funding proposal to conduct the modelling and develop the measure of movement confidence.
Other collaborators on this project:
• Erica Dove, PhD candidate, Rehabilitiation Sciences Institute, University of Toronto
• Dr. Kara Patterson, Physical Therapy, University of Toronto
• Dr. Amy Hwang, Occupational Sciences & Occupational Therapy, University of Toronto

Sunnybrook Health Sciences Centre researcher seeks data analysts for neuroimaging project

Contact: Dr. Fa-Hsuan Lin
Organization: Sunnybrook Health Sciences Centre
Website: https://linbrainlab.org
Funding available: NSERC, MITACS
Project title and aims: Encoding and decoding the human brains under complex naturalistic stimuli
We are interested in measuring neuronal responses under complex and naturalistic stimuli, such as movie clips and musical pieces. The goals include the modeling of brain responses with sensory inputs (brain coding) and estimating the behavioural responses and sensory inputs based on brain activity (brain decoding). We hypothesize that relationships between brain activity, sensory input, and behavioural responses implicate the mental states, which are different between age groups, lifestyles, and disorders. We aim at classifying and predicting their subjective feelings, behaviours, and treatment responses based on neuroimaging measurements.
Research team currently has these skills: Our lab is specialized in neuroimaging data acquisition and analysis. The modality we used includes magnetic resonance imaging (MRI) and electroencephalography (EEG). We are specialized in recording MRI and EEG with high spatiotemporal resolution and sensitivity on healthy adults, schizophrenic patients, and teenagers suffering from attention deficit disorders.
Desired skills in potential collaborators: We are enthusiastic in collaborating with experts in data analysis. We are interested in learning data modeling methods capable of generating robust results with our sample size (tens to hundreds of participants) and analytic strategies that support adaptive models with evolving data samples.
Other project collaborators: We are collaborating with international industrial partners and major medical imaging vendors to provide infrastructure (AI computations) and technical development (parts and information for imaging hardware) supports.

Duchenne muscular dystrophy not-for-profit seeks AI advisors 

Contact: Andrew Semihradsky <andrew.sedmihradsky@utoronto.ca>
Telephone number: 289-527-5608
Website: https://www.maxsbigride.com/
Project Aims: I hope to create an intelligent online platform that captures information about completed, ongoing and recently funded Duchenne research from online databases, journals and various other sources. This platform will utilize the power of artificial intelligence to find synergies between existing research projects and suggest connections between researchers with the aim of promoting communication, collaboration and promising new directions for research.
Desired skills in collaborators: At the moment I am just interested in talking through this project to see if it is possible — I do not know enough about AI to determine its feasibility or potential.

Automated medical billing startup seeks Natural Language Processing expertise

Contact: Adam Kepecs (Tel: 647-812-6678)
Organization: IntelAGENT
Project aims: This project aims to use Machine Learning to parse a clinician's unstructured free-text patient encounter note in their Electronic Medical Record (EMR) system to identify billable OHIP services. This will alleviate administrative overhead and help physicians spend more time in clinical practice.
Desired skills: Expertise in Natural Language Processing models for unstructured clinical notes.
Other collaborators in this project: Prof. Frank Rudzicz