Detection and Treatment to Prevent the Progression of Coronary Artery Disease (CAD)

Summary

Are you excited by the opportunity to apply machine learning techniques to discover new solutions to human health?

Supervisor

Professor Stefan Williams.

Research location

Aerospace, Mechanical and Mechatronic Engineering

Synopsis

Early detection and treatment can prevent the progression of coronary artery disease (CAD) and, consequently, heart attacks. While this can help individuals who display traditional risk factors such as diabetes, hypertension, high cholesterol, and smoking, many people develop CAD over years without the presence of any obvious risk factors. They remain unaware of their susceptibility to the disease and miss out on the opportunity to reduce their risk of a heart attack through taking lifesaving drugs.

CAD Frontiers is an Australian-led, global team composed of clinicians, researchers, data scientists, healthcare and industry leaders with a track record of discovery, innovation and translation. CAD Frontiers is partnering with the Digital Sciences Initiative (DSI) at the University of Sydney to explore the convergence of digital sciences in information, algorithms and machine learning for enhancing the impact and success of diagnostic intervention. By partnering with DSI, CAD Frontiers will build capacity to achieve rapid and demonstrable outcomes in research and commercialisation. The Digital health imaging team within DSI will support CAD Frontiers to improve the understanding, diagnosis and treatment of subclinical disease through developing multimodal AI algorithms that incorporate multiple data sources. AI algorithms for cardiac imaging data, co-designed with multidisciplinary domain expertise, can aid in image understanding and in extracting 'deep' image feature for 'image-omics' - an approach that associates imaging features with complementary -omics data for new biomarker discoveries. This work will revolutionise the clinical approach to early diagnosis of CAD through the discovery of novel biomarkers and the more efficient and affordable analysis of diagnostic imaging data. DSI's established dynamic digital business ecosystem is expected to provide CAD Frontiers with an important interface with start-ups through to multinational industry partners during the commercialisation phase. The partnership aims to maximise industry investment, competitiveness and the likelihood of delivering economic and health outcomes.

We have secured funding through the Vonwiller Foundation to support up to three Vonwiller stipends to support PhD students to develop novel clinical and data science approaches to CAD diagnostics. Working collaboratively, these students will accelerate research in applied machine learning to ultimately identify the molecular biosignatures of patients with silent atherosclerosis, and the application of these AI algorithms to imaging held in data banks such as BioHeart. Working in an interdisciplinary manner will bring together medical, computer science and engineering mindsets to apply a smart digital solution to a devastating physical problem.

For more information on the CAD Frontiers, see here. More information about the DSI research-oriented mission in medical imaging can be found here.

Additional information

The University values courage and creativity; openness and engagement; inclusion and diversity; and respect and integrity. As such, we see the importance of recruiting talent aligned to these values and are looking for students interested in working to develop either one of the following skill sets:

Student 1

• tertiary qualifications in Medical Informatics, Computer Science, Machine Learning / Deep Learning / AI
• skills in software development including work with Python, C/C++ and the latest machine learning packages
• prior experience working with medical imaging modalities, in particular coronary artery disease imagery and related biomarker data, is desirable

Student 2

• tertiary qualifications in Data Science, Bioinformatics, Computer Science, applied machine learning or similar
• skills in applied machine learning development with medical imaging data using R or Python packages
• prior experience on recent platforms of omics data such as next generation sequencing or mass spectrometry is desirable
• high-dimension data analysis experience is desirable

Successful candidates must have:

• skills and experience necessary to manage the processes for testing and validation of machine learning algorithms in a clinical environment
• ability to conduct research / scholarly activities as part of a multidisciplinary research team
• experience managing large volumes of multi-modality data and a demonstrated track record of supporting high quality academic publications and clinical uptake
• the ability to liaise effectively with both scientific/technical and clinical colleagues
• ability to assist researchers from other disciplines as well as working with PhD students.

How to Apply:

To apply, please email stefan.williams@sydney.edu.au the following:

• CV
• transcripts

 

Want to find out more?

Opportunity ID

The opportunity ID for this research opportunity is 3479

Other opportunities with Professor Stefan Williams