Developing a mobile screening tool that could predict impairment by leveraging the power of machine learning models

There is a growing need for law enforcement agencies and safety sensitive workplace environments to be able to evaluate impairment. Impairment due to mental cognitive deficits, drugs or alcohol use, prescription medications, or fatigue could all limit a person’s ability to perform a hazardous task safely.
Current testing tools utilize saliva, breath, blood or urine to measure levels of substances that may impair a person’s judgement. These types of tests are invasive, and in many cases not reliable. Ingested cannabis for example does not have the same effect as smoked cannabis, and current testing techniques are not adapted for both.
To date, 126,000 real-world assessments have been performed by DriveABLE on legacy proprietary testing hardware. Machine learning is being applied to the results of the assessments to gain a deeper understanding of cognition in the context of complex human behavior. A screening tool will be developed and tested, leveraging mobile platforms such as tablets and phones, making it accessible where it is needed most. A core component to meeting this objective will be leveraging the skills of mobile game developers to help with the development of 4 proprietary cognitive tasks based on existing real-world assessments.

Faculty Supervisor:

Steve Chattargoon

Student:

Marshall Clowater;Christopher Popowich

Partner:

DriveABLE Inc

Discipline:

Medicine

Sector:

Professional, scientific and technical services

University:

Northern Alberta Institute of Technology