• Home
  • Graduate
  • Collaborative Specialization in Machine Learning in Health and Biomedical Sciences

Collaborative Specialization in Machine Learning in Health and Biomedical Sciences

Biomedical research, public health policy, and medical practice all increasingly rely on large sets of genetic, epidemiological, physiological, imaging, and/or behavioral data. This requires the development and application of modern machine learning, artificial intelligence, and statistical techniques that are suited to the problem at hand. To be successful in this rapidly evolving field, graduates need to be equipped both with expertise in machine learning methods, as well as a thorough subject-specific knowledge in the application area.

There are many challenges and opportunities for machine learning in the biomedical sciences that deserve special attention. The confidentiality of medical records, ethical implications of using data science methods for medical decision making, implementation of advanced technologies and analytics in healthcare settings, acceptance of health technologies and machine learning by diverse communities, and specific data formats for biomedical applications are only a few examples.

To provide world-class graduate training for this rapidly growing sector, several graduate programs across the Faculties of Science, Health Sciences, Engineering, and the Schulich School of Dentistry and Medicine have developed a Collaborative Specialization that provides targeted and practice-oriented training.

The program is open for PhD students and Masters students on a thesis-based track in the following programs:

  • Biomedical Engineering (MESc & PhD)
  • Medical Biophysics (MSc & PhD
  • Neuroscience (MSc & PhD)
  • Computer Science (MSc & PhD)
  • Mechanical and Materials Engineering (MESc & PhD)
  • Epidemiology and Biostatistics (MSc & PhD)
  • Electrical and Computer Engineering (MESc & PhD)
  • Physics (MSc & PhD)
  • Health and Rehabilitation Sciences (MSc & PhD)
  • Psychology (MSc & PhD)
  • Biochemistry (MSc & PhD)
  • Anatomy and Cell Biology( MSc & PhD)
  • Pathology and Laboratory Medicine (MSc & PhD)

This program enhances the education and research of a graduate student in one of the participating programs by adding a module to their program. The student receives a degree from his or her home department program along with a transcript notation Machine Learning in Health and Biomedical Sciences., e.g. MESc in Biomedical Engineering with specialization in Machine Learning in Health and Biomedical Sciences.

Students in the program will:

  • develop a solid foundation in modern machine learning techniques,
  • gain a deep understanding of the application of machine learning to genomic, physiological, imaging, and behavioral data,
  • conduct an independent research project in health and biomedical science using modern machine learning approaches,
  • learn how to effectively work inter-disciplinary teams,
  • acquire project management and entrepreneurial skills, and
  • learn how to consider societal and ethical implications in project design.

Requirements

Additional to all requirements of the home graduate program, all students are required to take the following classes. Note that some of these courses can fulfill the requirement of electives in the home program. Please inquire with the individual graduate program chair.

  • Successful completion of an ‘Introduction to machine learning course’ (can be one of the following: DS 9000A/B, ECE 9039A/B, CS 9637A, or equivalent (see note below) at a minimum grade of 70%.
  • At least one of the applied machine learning courses:
    • AM 9624B: Introduction to Neural Networks (Psych9221B)
    • BME 9709B: Biomedical Applications of Neural Networks (Biophys 9709B)
    • CS 9542B: Artificial Intelligence II
    • CS 9873B: Brain Inspired AI
  • DS 9600B: Machine Learning in Health and Biomedical Sciences. Core seminar covering ethics, communication, and project management aspects.

All students are also required to complete an MSc or PhD thesis in their home program. The thesis topic needs to be in the domain of the collaborative specialization. An application of machine learning to a specific Health or Biomedical problem, or the development of a new method that is of special interest to such problems would fulfill this requirement. Before admission to the collaborative specialization, the thesis topic needs to be submitted to the program committee for approval.

Note: Students may petition the collaborative specialization program committee to fulfill select collaborative specialization course requirements with prior graduate-level coursework. This allowance applies to the completion of the Introduction to Machine Learning course only. Students may not substitute prior coursework for applied machine learning courses or the core course DS 9600. Please consult the handbook for more details.

Admission into the Collaborative Specialization

You must first be accepted into one of the listed graduate programs above.

New graduate students (Masters/PhD) are eligible to apply for admission.   Deadline for applic ation is June 1 for Fall admissions; Oct 1 for January Admissions; and Feb 1 for Summer admission.

Seek admission to the collaborative specialization by completing the online  application form, which requires providing information about your graduate program, your supervisor(s), and a description of your thesis topic and how it relates to the specialization.

Faculty supervisors of students in the specialization must also seek membership, using the Faculty Membership Application Form linked below.

Please see the Collaborative Specialization in Machine Learning in Health and Biomedical Sciences, Handbook (2022-2023)   for more complete details on the program.  

Important links for prospective and current students:

The Vector Institute and Vector Scholarship in Artificial Intelligence

The Collaborative Specialization in Machine Learning in Health and Biomedical Sciences is recognized by the Vector Institute as delivering a curriculum that equips its graduates with the skills and competencies sought by industry. Students in the Collaborative Specialization become part of the Vector Institute community and receive access to networking and career events, the Digital Talent Hub , professional development, and other opportunities to grow your AI career!

Vector Institute Scholarship

Exceptional students may be eligible for the Vector Scholarship in Artificial Intelligence, which provides $17,500 towards an AI-related master’s degree at an Ontario university. Both domestic and international students with first-class standing (minimum A- in their last two years of full-time study) are eligible for consideration. Students with an upper second class standing (B+), who also have relevant work experience may be considered.

In order to be nominated, candidates must submit a complete nomination package to the Collaborative Specialization (instructions below) by the deadline date. Instructions and important dates will be posted here when the competition opens each Spring. Learn more about the scholarship and eligibility requirements at vectorinstitute.ai/scholarship or sign up to hear directly from Vector at vectorinstitute.ai/vsai-signup. The Collaborative Sepcialization Program Committee will review all applications for their funding competitiveness and suitability.  Submitting an application does not guarantee a nomination for this award.

The Vector Scholarship Nomination package should include:

  1. Copies of all up-to-date transcripts with the corresponding grading system (both undergraduate, and if applicable, graduate transcripts), as a single PDF
  2. An up-to-date one to two-page CV, as a single PDF
  3. A 250-word statement outlining their reason for pursuing a master’s in AI, relevant AI-related experience, and career aspirations, as a single PDF
  4. Self-Identification Questionnaire
  5. Two Referee forms are to be sent by e-mail to the Program. Please ask your two referees to email their Referee forms directly to the collaborative specialization program at chair-collabspec-ml@uwo.ca .

Links to forms and instructions for applying will be posted here at the start of each competition.

Contact information

Co-directors of the program can be reached at chair-collabspec-ml@uwo.ca .

Ali Khan, PhD   
Associate Professor, Medical Biophysics   
Co-Director, Collaborative Specialization in ML-HealthBiomed    

Angela Roberts, PhD   
Assistant Professor, School of Communication Sciences and Disorders and Department of Computer Science   
Co-Director, Collaborative Specialization in ML-HealthBiomed