Can we teach a machine to be a cardiologist?

From Derek
Jump to: navigation, search

Supervisors

Honours students

Project guidelines

Project description

Researchers have employed machine learning to several medical data applications. An electrocardiogram (ECG) is a medical test that detects heart abnormalities by measuring the electrical activity. In this project, we aim to classify ECG signals into diseases and normal groups using artificial intelligence. For, example, machine learning algorithms can help us to understand the hidden patterns in ECGs. If you are interested in biomedical signal processing, machine learning and programming come and have a chat with us. Python is the way to go. And maybe some MATLAB.

Useful notes

As useful bits of information come to light, just list them here:

Approach and methodology

The approach for this project should be to investigate ,a range of different Machine Learning methods and pre-processing stages to best categorise ECG signals. Hence the approach should be fairly open-ended, and include investigation into:

  • Cardiac abnormalities and their effect on the ECG,
  • Pre-processing techniques and their usefulness for analysing ECGs,
  • Machine Learning techniques and how effective they are at distinguishing types of ECGs, and
  • Conclusions on the best method or set of methods to do this.

These points could be split between the students, or each student could research different techniques from each area. The investigation should be as in-depth or cover as wide a range as possible, given the time constraints of the project.

Possible extension

After working on this project in 2021, the following areas could be extended further in future:

  • Investigate a wider range of pre-processing, feature extraction and machine learning techniques (or try different combinations of these)
  • Better optimise the parameters of these to ECG analysis
  • Try differentiating between a wider range of cardiac abnormalities
  • Evaluate the possibility of including ML diagnosis software in a wearable device
  • Or other suitable options

Expectations

  • We expect all the written work to be place on this wiki. No paper reports are to be handed up. Just pop your whole project directory into Box and send me the download URL at the end.
  • It is expected that you fill out a short progress report on the wiki each week, every Friday evening, to briefly state what you did that week and what the goals are for the following week.
  • It is important to regularly see your main supervisors. Don't let more than 2 week go by without them seeing your face briefly.
  • You should be making at least one formal progress meeting with supervisors per month. It does not strictly have to be exactly a month, but roughly each month you should be in a position to show some progress and have some problems and difficulties to discuss.
  • The onus is on you to drive the meetings, make the appointments and set them up.
  • You are expected to make a YouTube presentation of your whole project.

Relationship to possible career path

This project could be a suitable start on the path to a biomedical engineering career (particularly with signal analysis and diagnosis), or a career in machine learning (regardless of the specific application). Hence, this project can provide a suitable baseline to a wide range of careers.

See also

Delivered Items

2021:

References and useful resources

If you find any useful external links, list them here:

Back

Retrieved from "https://www1.eleceng.adelaide.edu.au/personal/dabbott/wiki/index.php?title=Can_we_teach_a_machine_to_be_a_cardiologist%3F&oldid=22734"