Machine Learning Applications for Health (COMP90089)

Graduate courseworkPoints: 12.5Dual-Delivery (Parkville)

You’re viewing the 2022 Handbook:
Or view archived Handbooks
You’re currently viewing the 2022 version of this subject
Subjects taught in 2022 will be in one of three delivery modes: Dual-Delivery, Online or On Campus.
From 2023 most subjects will be taught on campus only with flexible options limited to a select number of postgraduate programs and individual subjects.
To learn more, visit COVID-19 course and subject delivery.

Overview

Availability
Semester 2 - Dual-Delivery
FeesLook up fees

Artificial Intelligence (AI) is an ever growing field that holds the promise to revolutionise the way we develop drugs, treat and manage patients. In particular, Machine Learning has become an important tool to make sense of clinical data that is routinely collected and stored as electronic health records to enable personalised medicine.

This subject aims to introduce students to different AI applications in health, using different clinical data sources and computational techniques, discussing their idiosyncrasies and the main challenges in the area.

INDICATIVE CONTENT

Topics covered may include: supervised, unsupervised learning and their applications in health scenarios, interpretable machine learning in health, natural language processing in health, process mining, data sources and clinical information modelling, data wrangling, harmonising and filtering, clinical image data and deep learning.

Intended learning outcomes

On completion of this subject, students should be able to:

  • Describe the application of Artificial Intelligence concepts in the context of health problems
  • Demonstrate familiarity with challenges associated with health data and data modelling
  • Design, implement, and evaluate an AI system addressing a healthcare problem
  • Critically assess Artificial Intelligence applications for health

Generic skills

  • Develop critical thinking and analytical skills
  • Improve problem-solving skills
  • Enhance programming skills
  • Improve communication skills
  • Develop skills to enable problem identification, solution formulation for health applications

Last updated: 30 October 2023

Eligibility and requirements

Prerequisites

Admission into or selection of one of the following:

  • Admission into or selection of one of the following:
    • MC-SCICMP Master of Science (Computer Science)
    Admission into or selection of one of the following:
    • MC-SOFTENG Master of Software Engineering
    Admission into or selection of one of the following:
    • MC-IT Master of Information Technology
    Admission into or selection of one of the following:
    • MC-DATASC Master of Data Science
    Admission into or selection of one of the following:
    • GD-CS Graduate Diploma in Computer Science
    Admission into or selection of one of the following:
    • MC-ENG Master of Engineering
  • Admission into the MC-CS Master of Computer Science

OR

Completion of one of the subjects below

Code Name Teaching period Credit Points
COMP90059 Introduction to Programming
Semester 2 (Dual-Delivery - Parkville)
Summer Term (Dual-Delivery - Parkville)
Semester 1 (Dual-Delivery - Parkville)
 12.5
COMP90038 Algorithms and Complexity
Semester 1 (Dual-Delivery - Parkville)
Semester 2 (Dual-Delivery - Parkville)
 12.5

Or equivalent

OR

Permission of the coordinator is required prior to enrolling in this subject (some programming experience in Python is required)

Corequisites

None

Non-allowed subjects

None

Inherent requirements (core participation requirements)

The University of Melbourne is committed to providing students with reasonable adjustments to assessment and participation under the Disability Standards for Education (2005), and the Assessment and Results Policy (MPF1326). Students are expected to meet the core participation requirements for their course. These can be viewed under Entry and Participation Requirements for the course outlines in the Handbook.

Further details on how to seek academic adjustments can be found on the Student Equity and Disability Support website: http://services.unimelb.edu.au/student-equity/home

Last updated: 30 October 2023

Assessment

DescriptionTimingPercentage

Regular (weekly) quizzes - Equivalent to 500 words in total

  • 10 hours (of work required)
From Week 2 to Week 1120%

Two individual assignments - Equivalent to 2000 words (2x1000 words). These will be individual programming assignments about one of the AI applications in health presented during the subject. Due in Week 4 &10.

  • 40 hours (of work required)
Hurdle requirement: 50% - Students are required to obtain at least 50% collectively on the two individual programming assignments 		During the teaching period30%

AI in health project proposal (group activity, 3 to 4 students) - Equivalent to 500 words per group

  • 10 hours (of work required)
From Week 7 to Week 810%

AI in health project report (group activity, 3 to 4 students) - Equivalent to 2000 words per group. Due at the start of the exam period.

  • 40 hours (of work required)
Hurdle requirement: 50% - Students are required to obtain at least 50% on their group activity		End of semester40%

Last updated: 30 October 2023

Dates & times

  • Semester 2
    CoordinatorsDaniel Capurro Nario and Douglas Valente Pires
    Mode of deliveryDual-Delivery (Parkville)
    Contact hours36 hours comprising 24 hours of lectures (2 hours per week) and 12 hours of tutorials (1 hour per week)
    Total time commitment200 hours
    Teaching period25 July 2022 to 23 October 2022
    Last self-enrol date 5 August 2022
    Census date31 August 2022
    Last date to withdraw without fail23 September 2022
    Assessment period ends18 November 2022

    Semester 2 contact information

    douglas.pires@unimelb.edu.au


    dcapurro@unimelb.edu.au

Last updated: 30 October 2023

Further information

Last updated: 30 October 2023