Utilization of Machine Learning in Diagnostic Cardiac Devices - BC-422

Preferred Disciplines: Electrical Engineering (Masters or PhD)
Project length: 4-12 months (1-2 units)
Approx. start date: As soon as possible
Location: Burnaby, BC
No. of Positions: 1
Preferences: None
Company: Anonymous

About Company:

Approximately a third of heart attack patients are misdiagnosed on their first hospital visit. The partner is a R&D medical device company aimed at enhancing the AI associated with electrocardiography (ECG) interpretation to reduce human error and improve testing consistency by improving waveform analysis, utilizing deep learning, and sending critical cases to experienced ECG interpreters, such as ER physicians, Cardiologists, Nurses, and Licensed Cardiology Technologists. 

The partner company also aims to eliminate the need for electrode patches during ECG and Exercise Tolerance Testing (ETT) by developing wireless ECG probe technology. Such developments reduce operating costs of hospitals and clinics, improve testing accuracy, and reduce the time it takes to set up an ECG and make a diagnosis, ultimately saving more lives. 

Summary of Project:

  • Use of waveform analysis to break down aspects of an ECG that indicate a heart attack
  • Use of waveform analysis to determine the type of rhythm abnormalities present and risks associated with sudden cardiac death
  • Development of software that can be implemented on multiple platforms and eventually implemented into the hardware side of my project
  • Use of basic machine learning to test algorithms on raw data to test for accuracy

Research Objectives/Sub-Objectives:

  • To be discussed with the researcher

Methodology:

    • To be discussed with the researcher

    Expertise and Skills Needed:

    • Knowledge of the waveform analysis branch of supervised machine learning
    • Excellent understanding of gradient descent algorithms
    • Ability to determine the optimal learning rate for both precise and timely output variables
    • The ability to teach and mentor someone with limited understanding of computer science

    For more info or to apply to this applied research position, please

    1. Check your eligibility and find more information about open projects.
    2. Interested students need to get the approval from their supervisor and send their CV along with a link to their supervisor’s university webpage by applying through the webform
    Program: