BMET9925: AI, Data, and Society in Health (2021 - Semester 1)

Download UoS Outline

Unit: BMET9925: AI, Data, and Society in Health (6 CP)
Mode: Normal-Day
On Offer: Yes
Level: Postgraduate
Faculty/School: School of Biomedical Engineering
Unit Coordinator/s: Dr Kumar, Ashnil
Session options: Semester 1
Versions for this Unit:
Campus: Camperdown/Darlington
Pre-Requisites: None.
Prohibitions: BMET2925.
Brief Handbook Description: Unprecedented growth in computing power, the advent of artificial intelligence (AI)/machine learning technologies, and global data platforms are changing the way in which we approach real-world healthcare challenges. This interdisciplinary unit will introduce students from different backgrounds to the fundamental concepts of data analytics and AI, and their practical applications in healthcare. Throughout the unit, students will learn about the key concepts in data analytics and AI techniques, and obtain hands-on experience in applying these techniques to a broad range of healthcare problems. At the same time, they will develop an understanding of the ethical considerations in health data analytics and AI, and how their use impacts society: from the patient, to the doctor, to the broader community. A key element of the learning process will be a team-based Datathon project where students will deploy their knowledge to address an open-ended healthcare problem, in particular developing a practical solution and analysing how it's use may change things in the healthcare domain. Upon completion of this unit, students will understand and be able to enlist data analytics and AI tools to design solutions to healthcare problems.
Assumed Knowledge: Familiarity with general mathematical and statistical concepts. Online learning modules will be provided to support obtaining this knowledge.
Additional Notes: Departmental permission will only be required for the first offering of this unit during the Semester 1 2021, when this unit will be piloted. From 2022, the unit will be available to all students via Table S.
Department Permission Department permission is required for enrollment in this session.
Timetable: BMET9925 Timetable
Time Commitment:
# Activity Name Hours per Week Sessions per Week Weeks per Semester
1 E-Learning 2.00 1 13
2 Tutorial 2.00 1 9
3 Laboratory 2.00 1 9
4 Datathon 2.00 2 4
5 Independent Study 3.00 1 13
T&L Activities: E-Learning (Weeks 1-13): Video lectures, online worksheets, and other learning materials will cover the core conceptual knowledge each week. Students will be expected to complete this work prior to class.

Tutorials (Weeks 1-9): E-learning content review, with problem-based activities to support consolidation of knowledge.

Laboratory (Weeks 1-9): Practical exercises that will provide practical experience in AI and data analytics techniques applied to health.

Studio Datathon (Weeks 10-13): Sessions where students will work in teams to propose and prototype a solution to a real-world health data problem.

Attributes listed here represent the key course goals (see Course Map tab) designated for this unit. The list below describes how these attributes are developed through practice in the unit. See Learning Outcomes and Assessment tabs for details of how these attributes are assessed.

Attribute Development Method Attribute Developed
Laboratories will take a problem-based focus, developing practical skills through applying a range of data analytics and AI techniques on real-world datasets.

A set of intensive Datathon sessions will allow teams of students will work together to solve a larger scale real-world challenge.

During tutorial sessions, students will discuss the theories behind data analytics and AI algorithms, focusing on conceptual explanations and examining the appropriateness of each technique to different problems.
(2) Engineering/ IT Specialisation (Level 2)
During the Datathon activities, students will draw upon their knowledge to create data-driven solutions to an open-ended health problem. The solution they will produce will require them to consider not just technical challenges, but the social and ethical considerations that may affect various stakeholders in the healthcare ecosystem.

Assessments will include ongoing exercises where students will be asked to propose solutions to practical health problems.
(3) Problem Solving and Inventiveness (Level 2)
During the Datathon, students will work in a team environment to collaboratively develop a data-driven solution to a health problem. They will present their findings to convince a non-expert audience about the validity of their proposed solution.

Through lectures and tutorials, students will learn and debate ethical, social, and legal impacts that AI and data analytics solutions can have for the healthcare stakeholders.

The Case Study assessment will develop students ability to critically examine and communicate the ethical, social, and legal impacts that AI and data analytics solutions can have for the healthcare stakeholders.
(5) Interdisciplinary, Inclusiveness, Influence (Level 2)
The Case Study assessment will require students to conduct research and write a written report detailing the ethical and social considerations that apply to a data-driven solution in current practice.

As part of the Datathon, the students will produce a flyer to communicate the technical elements of their solution as well as explain why it is appropriate to the specific healthcare context.

As part of the Datathon, students will create an oral presentation to communicate their findings to a non-expert audience.
(6) Communication and Inquiry/ Research (Level 3)

For explanation of attributes and levels see Engineering & IT Graduate Outcomes Table 2018.

Learning outcomes are the key abilities and knowledge that will be assessed in this unit. They are listed according to the course goal supported by each. See Assessment Tab for details how each outcome is assessed.

(5) Interdisciplinary, Inclusiveness, Influence (Level 2)
1. Students will be able to work in teams to apply health data analytics and AI techniques to solve problems for different stakeholders.
2. Students will be able to characterise the impact of AI and data analytics solutions on different health stakeholder groups, in terms of legal, ethical, economic, and social issues.
(6) Communication and Inquiry/ Research (Level 3)
3. Students will be able to discuss the importance of data and AI for modern society in health, using appropriate literature to explain their reasoning.
4. Students will be able to communicate the results of a data analytics pipeline in an oral and written form to an audience that may comprise non-experts.
(3) Problem Solving and Inventiveness (Level 2)
5. Students will be able to select an appropriate data analytics or AI solution for a given health problem, with sufficient justification for their choice.
6. Students will be able to combine different data processing and AI techniques to address specific goals.
(2) Engineering/ IT Specialisation (Level 2)
7. Students will be able to articulate the challenges in working with real-world health datasets and the techniques that can alleviate these issues.
8. Students will be able to explain the general mathematical concepts behind AI and data analytics techniques.
9. Students will be able to interpret and assess the outputs of data analytics and AI pipelines, in the context of the strengths and limitations of the methods employed.
10. Students will be able to employ data analytics and AI toolboxes across a range of tasks.
Assessment Methods:
# Name Group Weight Due Week Outcomes
1 Exercises No 10.00 Multiple Weeks 5, 6, 8, 9, 10,
2 Quiz No 10.00 Week 7 3, 5, 8, 9,
3 Case Study No 15.00 Week 9 2, 3, 7,
4 Datathon - Final Presentation Yes 20.00 Week 13 1, 2, 4, 5, 6, 10,
5 Datathon - Solution Flyer Yes 15.00 Week 13 1, 2, 4, 5, 7, 9,
6 Take Home Exam No 30.00 Exam Period 2, 6, 7, 8, 9,
Assessment Description: Exercises: Ongoing practical work in tutorials and laboratories, assessed based on progress and effort rather than correctness.

Quiz: A short in-class covering conceptual content from the first half of semester.

Case Study: A written report that examines the social and ethical considerations about existing data analytics and AI solutions that are currently being used, the challenges that exist, and how these can be overcome.

Datathon - Final Presentation: A combined oral presentation and practical demonstration where the team of students will showcase the solution they developed during the Datathon, explain how it works, and discuss the social and ethical impacts on the stakeholders for whom the solution was developed.

Datathon - Solution Flyer: Teams will produce a short one-pager flyer the describes the solution they developed during the Datathon.

Take Home Exam: A time-limited exam that will test conceptual knowledge and practical skills in data interpretation.
Assessment Feedback: Feedback for assessments will be provided via Canvas and through in-class discussions.
Grading:
Grade Type Description
Standards Based Assessment Final grades in this unit are awarded at levels of HD for High Distinction, DI (previously D) for Distinction, CR for Credit, PS (previously P) for Pass and FA (previously F) for Fail as defined by University of Sydney Assessment Policy. Details of the Assessment Policy are available on the Policies website at http://sydney.edu.au/policies . Standards for grades in individual assessment tasks and the summative method for obtaining a final mark in the unit will be set out in a marking guide supplied by the unit coordinator.
Policies & Procedures: See the policies page of the faculty website at http://sydney.edu.au/engineering/student-policies/ for information regarding university policies and local provisions and procedures within the Faculty of Engineering and Information Technologies.

Note that the "Weeks" referred to in this Schedule are those of the official university semester calendar https://web.timetable.usyd.edu.au/calendar.jsp

Week Description
Week 1 E-learning: Introduction to the unit, and the learning activities. Health data and their stakeholders.
Tutorial: Stakeholders, their perspectives, and data curation needs.
Lab: Introduction to software tools.
Week 2 Lab: Types of health data. Data linkage.
E-learning: Data fragmentation and linkage. Health data standards and classifications. Privacy and security.
Tutorial: Data ownership and responsibility. Working with highly-confidential data (privacy, security).
Week 3 Lab: Data denoising and imputation
E-learning: Health data quality. Noise and missing data in health data, and addressing them with imputation and denoising strategies.
Tutorial: Concept explanation and discussion - imputation and denoising in the context of health data quality
Week 4 E-learning: Numerical health data and descriptive statistics.
Tutorial: Concept explanation and discussion - descriptive statistics, and examples of healthcare applications
Lab: Numerical health data: descriptive statistics and visualisations
Week 5 Lab: Image health data and predictive analytics - classification and prediction
E-learning: Image health data and predictive analytics - classification and prediction
Tutorial: Concept explanation and discussion - classification, forecasting, and prediction, and examples of healthcare applications
Week 6 Tutorial: Concept explanation and discussion - inference, and examples of healthcare applications
E-learning: Numerical health data and predictive analytics - inference
Lab: Numerical health data and predictive analytics - inference
Week 7 Tutorial Assessment: Quiz
Lab: Evaluating data and AI tools in healthcare - metrics, cross-validation
E-learning: Diagnostic and prescriptive data models in healthcare. Demonstrating value of new tools to different health stakeholders: the patient, the doctor, the administrator.
Assessment Due: Quiz
Week 8 E-learning: Advanced toolbox - natural language for health text data, longitudinal data for signal data, neural networks
Tutorial: Concept explanation and discussion - natural language for health text data, longitudinal data for signal data, neural networks
Lab: Advanced toolbox - natural language for health text data, longitudinal data for signal data, neural networks
Week 9 Lab: Considering stakeholder perspectives in data analytics
E-learning: AI and data analytics in health - responsibility for decisions and ethical considerations. AI and data risks in healthcare.
Tutorial: Prejudices and preconceptions around AI. What happens when an AI gets it wrong?
Assessment Due: Case Study
Week 10 Studio: Datathon - Challenge Reveal & Team Formation
E-learning: AI and data analytics in health: force multiplier or crutch?
Studio: Datathon - Project Work
Week 11 Studio: Datathon - Project Work
E-learning: AI and Data in Health Today
Studio: Datathon - Project Work
Week 12 Studio: Datathon - Project Work
E-learning: AI and Data in Health Tomorrow
Studio: Datathon - Project Work
Week 13 Studio: Datathon - Project Work
E-learning: Review
Studio: Datathon - Final Presentations
Assessment Due: Datathon - Final Presentation
Assessment Due: Datathon - Solution Flyer
Exam Period Assessment Due: Take Home Exam

Course Relations

The following is a list of courses which have added this Unit to their structure.

Course Year(s) Offered
Graduate Certificate in Digital Health and Data Science 2022
Master of Digital Health and Data Science 2022
Master of Engineering 2019, 2020, 2021, 2022
Master of Professional Engineering (Accelerated) (Biomedical) 2019, 2020, 2021, 2022
Master of Professional Engineering (Biomedical) 2018, 2019, 2020, 2021, 2022

Course Goals

This unit contributes to the achievement of the following course goals:

Attribute Practiced Assessed
(5) Interdisciplinary, Inclusiveness, Influence (Level 2) Yes 19.5%
(6) Communication and Inquiry/ Research (Level 3) Yes 17%
(4) Design (Level 2) No 0%
(3) Problem Solving and Inventiveness (Level 2) Yes 22.5%
(2) Engineering/ IT Specialisation (Level 2) Yes 41%
(1) Maths/ Science Methods and Tools (Level 2) No 0%

These goals are selected from Engineering & IT Graduate Outcomes Table 2018 which defines overall goals for courses where this unit is primarily offered. See Engineering & IT Graduate Outcomes Table 2018 for details of the attributes and levels to be developed in the course as a whole. Percentage figures alongside each course goal provide a rough indication of their relative weighting in assessment for this unit. Note that not all goals are necessarily part of assessment. Some may be more about practice activity. See Learning outcomes for details of what is assessed in relation to each goal and Assessment for details of how the outcome is assessed. See Attributes for details of practice provided for each goal.