Machine Learning for Biostatistics (STAT7616)

Course overview

Recent years have brought a rapid growth in the amount and complexity of health data captured. Among others, data collected in imaging, genomic, health registries and personal devices call for new statistical techniques in both predictive and descriptive learning. Machine learning algorithms for classification and prediction complement classical statistical tools in the analysis of these data. This unit will cover modern machine learning methods particularly useful for large and complex data. Topics include, classification trees, random forests, model selection, lasso, bootstrapping, cross-validation, generalised additive modelling, and regression splines. The statistical software R package will be used throughout the unit.

Introduction of a course on machine learning in health was recommended in the recent (March 2019) external review of the Master in Biostatistics.ﾠ STAT7616 has been developed and will be offered by the University of Sydney through the Biostatistics Collaboration of Australia (BCA). ﾠ ﾠ

Recent years has seen an explosion in the availability of health data collected routinely in health care via electronic medical records, in disease registries, and in wearable devices (phones, watches). This abundance of data has led to applications of machine learning developed in the computer science and statistics disciplines to be applied to health data for the goals of description, classification, or disease prediction/prognosis. Such modern, computationally intensive skills will be advantageous and of great interest to students studying biostatistics or related areas.

Further information regarding this course is available from the following link https://www.bca.edu.au

ﾠ

Course requirements

Prerequisites

You'll need to complete the following courses before enrolling in this one:

STAT7607

Companion or co-requisite courses

You'll need to complete the following courses at the same time:

STAT7608

Course contact

Course staff

Aims and outcomes

This course aims to teach the application of machine learning algorithms, developed in the computer science and statistics disciplines, to health data for the goals of description, classification, or disease prediction/prognosis.

Learning outcomes

After successfully completing this course you should be able to:

Assessment

Assessment summary

Assessment details

Practical Exercise 1

Mode

Written

Category

Tutorial/ Problem Set

Weight

10%

Due date

2/09/2024

Due date will be confirmed by the BCA Course Coordinator.

Learning outcomes

L01, L02, L03, L04, L05, L06, L07

Task description

Submission guidelines

Please refer to BCA Study Guide for full submission details

Deferral or extension

You may be able to apply for an extension.

Please see 10. Policies & Guidelines

Practical Exercises 2

• Online

Mode

Written

Category

Tutorial/ Problem Set

Weight

10%

Due date

28/10/2024

Due date to be confirmed by the BCA Course Coordinator.

Learning outcomes

L01, L02, L03, L04, L05, L06, L07

Task description

Submission guidelines

Please refer to BCA Study Guide for full submission details

Deferral or extension

You may be able to apply for an extension.

Please see 10. Policies & Guidelines

Major Assignment 1

• Online

Mode

Written

Category

Essay/ Critique

Weight

40%

Due date

16/09/2024

Due date to be confirmed by BCA Course Coordinator.

Learning outcomes

L01, L02, L03, L04, L05, L06, L07

Task description

Submission guidelines

Please refer to BCA Study Guide for full submission details

Deferral or extension

You may be able to apply for an extension.

Please see 10. Policies & Guidelines

Major Assignment 2

• Online

Mode

Written

Category

Essay/ Critique

Weight

40%

Due date

11/11/2024

Due date to be confirmed by the BCA Course Coordinator

Learning outcomes

L01, L02, L03, L04, L05, L06, L07

Task description

Submission guidelines

Please refer to BCA Study Guide for full submission details

Deferral or extension

You may be able to apply for an extension.

Please see 10. Policies & Guidelines

Course grading

Full criteria for each grade is available in the Assessment Procedure.

Supplementary assessment

Supplementary assessment is available for this course.

Additional assessment information

The final grade awarded will be based on the results of the supplementary assessment only, and a passing grade will be awarded if, and only if, the student receives at least 50% of the marks on the supplementary assessment. 

Learning resources

You'll need the following resources to successfully complete the course. We've indicated below if you need a personal copy of the reading materials or your own item.

Library resources

Find the required and recommended resources for this course on the UQ Library website.

Learning activities

The learning activities for this course are outlined below. Learn more about the learning outcomes that apply to this course.

Policies and procedures

University policies and procedures apply to all aspects of student life. As a UQ student, you must comply with University-wide and program-specific requirements, including the:

• Student Code of Conduct Policy
• Student Integrity and Misconduct Policy and Procedure
• Assessment Procedure
• Examinations Procedure
• Reasonable Adjustments - Students Policy and Procedure

Learn more about UQ policies on my.UQ and the Policy and Procedure Library.

Course guidelines

School of Public Health (SPH) Guidelines for late submission of progressive assessment - Preamble

To apply for an extension to the due date for a piece of progressive assessment (eg assignments, oral presentations and computer-based assignments) students should complete the online request at  https://my.uq.edu.au/node/218/1 

Information regarding deferral of in-semester exams and end-of-semester exams is available from https://my.uq.edu.au/information-and-services/manage-my-program/exams-and-assessment/deferring-exam 

If requesting an extension on medical grounds, a medical certificate must be provided. The extension will be approved for the number of days included in the medical certificate that the student was not fit to study or work, eg if the medical certificate is for 3 days, an extension will be approved for 3 days maximum regardless of the student's request.  

If requesting an extension using a Student Access Plan for Disability (SAPD) as evidence, a maximum of 7-day extension will be approved in the first instance. Updated medical documentation, as well as a copy of the SAPD, is required if requesting an extension for more than 7 days. 

The maximum time for an in-semester extension is four weeks.  

The following SPH guidelines are consistent with the UQ policy. However, the SPH Guidelines contain specific rules and interpretations for SPH courses, and requests for extension and penalties for late submissions will be judged according to the guidelines outlined in this document. You should read both the information in your my.UQ at the following link: https://my.uq.edu.au/information-and-services/manage-my-program/exams-and-assessment/applying-assessment-extension?p=1#1 and the SPH guidelines (below) before submitting a request for an extension. The SPH Guidelines apply to all courses offered by the School of Public Health unless the ECP explicitly states otherwise.

SPH Guidelines for late submission of progressive assessment

Initial extension for an individual item of assessment – the SPH Teaching & Assessment Support Team and/or the Course Coordinator decides.

This could be for medical or compassionate reasons, or if, in the opinion of the Course Coordinator, there are exceptional circumstances.

Acceptable and unacceptable reasons for an extension are listed at the following link, along with the required evidence to be provided: https://my.uq.edu.au/information-and-services/manage-my-program/exams-and-assessment/applying-assessment-extension?p=1#1 

All requests should be lodged at least 24 hours prior to the due date for the assessment.

If applying for an extension after the due date and time of the assessment item, your request may not be approved. An explanation as to why your request was not submitted prior must be included.       

If approved, a new due date will be set. This would generally be no later than 7 days after the original due date, however this can be modified to take account of the circumstances of the request and the time that would have been lost from studies.

If the new due date is past the date for submission of end-of-semester results, the student will receive an INC (incomplete) result.

Second and all subsequent extensions for an individual item of assessment – the SPH Teaching & Assessment Support Team and/or the Program Director together with the Course Coordinator decides.

This would only be approved for exceptional circumstance with supporting documentation.

• Online requests must be made at least 24 hours prior to the due date from the first extension.
• The SPH Teaching & Assessment Support Team and/or the Course Coordinator will consult with the Program Director, who will make the final decision.
• If approved, the new due date would generally be no later than 7 days after the first extension due date.
• The Program Director should consider if remedial or other support should be offered to the student.
• The Program Director should provide a report on these matters as needed at SPH Examiners’ Meetings.

Please Note: In order to support course progression, extensions that total more than 14 calendar days from the original due date of an assessment item will only be approved in very exceptional circumstances. These requests are assessed and approved or denied on a case-by-case basis. 

If you have been ill or unable to attend class for more than 14 days, we advise you to carefully consider whether you are capable of successfully completing your courses this semester. You might be eligible to withdraw without academic penalty.

Penalty for late submission

Submission of assignments, practical reports, workbooks, and other types of written assessments after the due date specified in the Electronic Course Profile (ECP) will receive a penalty.

The penalty will be a deduction of 10% RELATIVE PERCENTAGE per day (24 hour period or part thereof, including weekends and public holidays) or for work graded on a 1-7 scale, a deduction of one grade per day, e.g If the original mark is 73%, then 10% relative percentage is 10% of this value, ie 7.3%, The final mark for this assessment item after applying the penalty for 1 day late submission would be 73 -7.3 = 65.7% The same outcome is achieved by multiplying the original score by .9; ie 73 x .9 = 65.7%

The penalty for multiple days late is the relative percentage multiplied by the number of days late. 

A submission that is not made within 10 days of the due date will receive a mark of 0% for that assessment item.

Where a student has sought more than one extension, the due date for calculating the penalty will be the due date for the most recently approved extension.

Submission of Medical Certificates

Students are responsible for ensuring that any medical documentation they submit is authentic and signed by a registered medical practitioner. Such practitioners can be identified via the AHPRA website. Also note that:

• Not all online medical services are staffed by registered practitioners
• If the registration status of the practitioner cannot be verified, then an alternative practitioner should be sought
• Students will be held fully responsible for all documentation they submit, even if done so in ignorance of the practitioner's registration status

Medical documentation may be subjected to an audit by the University.

SPH Assessment Guidelines

The School of Public Health assessment tasks have been designed to be challenging, authentic and complex. While students may us AI technologies, successful completion of assessment in this course will require students to critically engage in specific contexts and tasks for which artificial intelligence will provide only limited support and guidance.

A failure to reference AI use may constitute student misconduct under the Student Code of Conduct.

To pass this assessment, students will be required to demonstrate detailed comprehension of their written submission independent of AI tools.