Massive amounts of genomic data are created for the advent of Next Generation Sequencing technologies. Great technological advances in methods of characterising the human diseases, including genetic and environmental factors, make it a great opportunity to understand the diseases and to find new diagnoses and treatments. Translating medical data becomes more and more rich and challenging. Visualisation can greatly aid the processing and integration of complex data. Genomic data visual analytics is rapidly evolving alongside with advances in high-throughput technologies such as Artificial Intelligence (AI), and Virtual Reality (VR). Personalised medicine requires new genomic visualisation tools, which can efficiently extract knowledge from the genomic data effectively and speed up expert decisions about the best treatment of an individual patient's needs. However, meaningful visual analysis of such large genomic data remains a serious challenge. Visualising these complex genomic data requires not only simply plotting of data but should also lead to better decisions. Machine learning has the ability to make prediction and aid in decision-making. Machine learning and visualisation are both effective ways to deal with big data, but they focus on different purposes. Machine learning applies statistical learning techniques to automatically identify patterns in data to make highly accurate prediction, while visualisation can leverage the human perceptual system to interpret and uncover hidden patterns in big data. Clinicians, experts and researchers intend to use both visualisation and machine learning to analyse their complex genomic data, but it is a serious challenge for them to understand and trust machine learning models in the serious medical industry. The main goal of this thesis is to study the feasibility of intelligent and interactive visualisation which combined with machine learning algorithms for medical data analysis. A prototype has also been developed to illustrate the concept that visualising genomics data from childhood cancers in meaningful and dynamic ways could lead to better decisions. Machine learning algorithms are used and illustrated during visualising the cancer genomic data in order to provide highly accurate predictions. This research could open a new and exciting path to discovery for disease diagnostics and therapies.
Date of Award | 2019 |
---|
Original language | English |
---|
- visual analytics
- machine learning
- artificial intelligence
- virtual reality
- genomics
- information visualization
Using machine learning to support better and intelligent visualisation for genomic data
Qu, Z. (Author). 2019
Western Sydney University thesis: Doctoral thesis