Reviews

No reviews yet. Be the first to review M6036.

Requisite map

Overview

The Master of Health Data Analytics is designed to meet the high demand for data analysts to tackle real-world health questions, such as quantifying the effectiveness of new treatments, implementing sophisticated modelling of patient outcomes and pathways, and developing algorithms for diagnostic imaging classification. A proficient health data analyst requires more than a set of powerful computing tools – they must have a broad understanding of health systems, health data sources, human body systems and epidemiological principles married with core data analytics skills in mathematics, programming, biostatistical theory and modelling, data visualisation and machine learning. The Master of Health Data Analytics enables you to develop these skills and equips you to contribute along the full length of a health data project, from conceptualisation of the health problem, to determining an avenue for solution, implementation of cutting-edge analytical solutions, and communication of the results to stakeholders. Graduates with such skills are in increasingly high demand in academia, government and industry worldwide. This interdisciplinary course allows you to focus your studies by choosing a stream in biostatistics, machine learning or a combination of both.

Course structure

Part A. Advanced expertise54 credit points

You must complete the following units and either EPM5003 or FIT5197

Additional unit

6 credit points

You must complete one of the following units

Part B. Applied health data analytics24 credit points

You must complete the following units and a capstone or project unit below

Capstone or project

6 credit points

You must complete one of the following units.

Note: EPM5031 is available to a limited number of students based on WAM.

Part C. Health data analytics stream18 credit points

You must complete one of the following streams

Biostatistics stream

18 credit points

You must complete the following unit, and two electives from the list below.

EPM5028Regression modelling for biostatistics IINo reviews yet6 cp

Biostatistics stream electives

12 credit points

You must complete two of the following units (12 credit points):

Note: Permission is required to enrol in ETC5523 Communicating with Data

Machine learning stream

18 credit points

You must complete two of the following units (12 credit points), and one elective from the list below.

Machine learning stream elective

6 credit points

You must complete one of the following units.
Note: Permission is required to enrol in ETC5523 Communicating with Data

General stream elecitves

18 credit points

You must complete 18 credit points from the following units

The handbook's description of this structure

The course is structured into three parts: Part A. Advanced expertise, Part B. Applied health data analytics, and Part C. Health data analytics stream.

Part A. Advanced expertise

In these studies you will gain knowledge and skills in the foundation units across health data analytics, programming, biostatistics, epidemiology and data analytics.

Part B. Applied health data analytics

In these studies you will gain expertise and competence in key aspects of health data analytics.

Part C. Health data analytics stream

You will be able to choose biostatistics, machine learning, or complete a general stream in health data analytics.

Course progression map

The course progression map provides guidance on unit enrolment for each semester of study.

The course comprises 96 points structured into three parts: Part A. Advanced expertise (54 points), Part B. Applied health data analytics (24 points) and Part C. Health data analytics streams (18 points).

Units are 6 points unless otherwise stated.

Part A. Advanced Expertise (54 points)

You must complete the following units:

EPM5026 Mathematical foundations for biostatistics
EPM5027 Regression modelling for biostatistics I
EPM5029 Introduction to health data analytics
EPM5033 Programming Principles for Health Data Analytics using Python
ETC5510 Introduction to data analysis
FIT5196 Data wrangling
FIT9136 Algorithms and programming foundations in python
MPH5040 Introductory epidemiology

AND

One of the following units:

EPM5003 Principles of statistical inference
FIT5197 Statistical data modelling

Part B. Applied Health Data Analytics (24 points)

You must complete:

EPM5030 Human health and disease processes
ETC5250 Introduction to machine learning
MPH5289 Professional practice development

AND

One of the following units:

EPM5031 Health data analytics project (limited number of students based on WAM) or
EPM5032 Applied health data analytics group case study

Part C. Health Data Analytics Stream (18 points)

You must complete one of the following streams:

Biostatistics stream

You must complete the following unit (6 points):

EPM5028 Regression modelling for biostatistics II

and two units (12 points) from:

BMS5021 Introduction to bioinformatics
EPM5008 Longitudinal and correlated data analysis
EPM5013 Bayesian statistical methods
EPM5018 Causal inference
ETC5521 Diving deeply into data exploration
ETC5523 Communicating with Data (with permission)
ETC5555 Statistical machine learning
FIT5147 Data exploration and visualisation

Machine learning stream

You must complete two units (12 points) from:

FIT5047 Fundamentals of artificial intelligence
FIT5201 Machine learning
FIT5212 Data analysis for semi-structured data

and one unit (6 points) from:

EPM5013 Bayesian statistical methods
EPM5028 Regression modelling for biostatistics II
ETC5521 Diving deeply into data exploration
ETC5523 Communicating with Data (with permission)
ETC5555 Statistical machine learning
FIT5047 Fundamentals of artificial intelligence
FIT5147 Data exploration and visualisation
FIT5201 Machine learning
FIT5202 Data processing for big data
FIT5212 Data analysis for semi-structured data
FIT5215 Deep learning
FIT5217 Natural language processing
FIT9132 Introduction to databases

General stream

You must complete three units (18 points) from:

BMS5021 Introduction to bioinformatics
EPM5008 Longitudinal and correlated data analysis
EPM5013 Bayesian statistical methods
EPM5018 Causal inference
EPM5028 Regression modelling for biostatistics II
ETC5450 Advanced R programming
ETC5513 Collaborative and Reproducible Practices
ETC5521 Diving deeply into data exploration
ETC5523 Communicating with Data
ETC5550 Applied Forecasting
ETC5555 Statistical machine learning
FIT5047 Fundamentals of artificial intelligence
FIT5147 Data exploration and visualisation
FIT5201 Machine learning
FIT5202 Data processing for big data
FIT5212 Data analysis for semi-structured data
FIT5215 Deep learning
FIT5217 Natural language processing
FIT9132 Introduction to databases

Learning outcomes

These course outcomes are aligned with the Australian Qualifications Framework and Monash Graduate Attributes.

Upon successful completion of this course it is expected that you will be able to:

1
be critical and creative scholars able to produce innovative and creative solutions to health data analysis problems with the application of the appropriate research skills
2
be able to effectively communicate the outcomes of their research to specialist and non-specialist audiences
3
be responsible and effective global citizens who can engage in planetary health research, exhibit cross-cultural competence and demonstrate necessary ethical values related to data and health research
4
be able to apply the major theories in the field of health data analytics to incorporate health related knowledge, critical analysis, expert judgement, autonomy, adaptability and responsibility into practice to address health problems at local, national or global levels.
5
possess a sound understanding of epidemiological study design and the theory and application of key areas of biostatistics and machine learning relevant to professional practice
6
have acquired skills in complex statistical and machine learning analyses to handle a variety of analytical problems using both traditional and modern statistical techniques and program in a range of statistical software, ensuring reproducibility and quality control
7
demonstrate the ability to interpret and understand biostatistical and machine learning techniques to a level of depth and sophistication consistent with contemporary professional practice
8
be able to recognise the necessary sampling, data collection and technical methodologies for real-world problems and translate them into practical solutions
9
possess the programming skills to wrangle and visualise data, fit models, make predictions, and produce high quality reports and presentations
10
be able to effectively and efficiently document and communicate ethical and legal issues, and norms in privacy and security, with regards to the practice of health data analytics

Entry requirements

English language

Monash level A, that is: IELTS (Academic): 6.5 overall (no band lower than 6.0); or Pearson Test of English (Academic): score of 58 overall with no band lower than 50; or TOEFL Internet-based test: score of 79 overall with minimum scores: Writing: 21, Listening: 12, Reading: 13 and Speaking: 18; or Equivalent approved English test

More information

Other information

The Master of Health Data Analytics is designed to meet the high demand for data analysts to tackle real-world health questions, such as quantifying the effectiveness of new treatments, implementing sophisticated modelling of patient outcomes and pathways, and developing algorithms for diagnostic imaging classification. A proficient health data analyst requires more than a set of powerful computing tools – they must have a broad understanding of health systems, health data sources, human body systems and epidemiological principles married with core data analytics skills in mathematics, programming, biostatistical theory and modelling, data visualisation and machine learning. The Master of Health Data Analytics enables you to develop these skills and equips you to contribute along the full length of a health data project, from conceptualisation of the health problem, to determining an avenue for solution, implementation of cutting-edge analytical solutions, and communication of the results to stakeholders. Graduates with such skills are in increasingly high demand in academia, government and industry worldwide. This interdisciplinary course allows you to focus your studies by choosing a stream in biostatistics, machine learning or a combination of both.

Contacts

Academic Coordinator: Professor Andrew Forbes; Dr Joanna Dipnall

Common questions

How long is Master of Health Data Analytics?

2 years full time, 96 credit points. At 24 credit points a semester, that is 4 semesters of full-time study.

Where can I study Master of Health Data Analytics?

At Alfred Hospital.

How do I plan my Master of Health Data Analytics units?

Open the course in the MonMap planner. It lays out your semesters, checks prerequisites as you drag units in, and tracks the credit points each requirement still needs.

Course details

Qualification: Master's Degree (Coursework)
AQF level: Level 9
Credit points: 96
Full time: 2 Years
Part time: 4 Years
Maximum time: 6 years

Faculty: Faculty of Medicine, Nursing and Health Sciences
CRICOS code: 106844H
Abbreviation: MHDA
Award title: Master of Health Data Analytics
Handbook years: 2022 2023 202420252026 2027