Artificial Intelligence in the Healthcare Setting
South Australia’s health research sector is among the best in the world, with its renowned infrastructure and applications of new and advanced technologies having a global impact. South Australia has world-leading Artificial Intelligence research capability and a range of other world-class researchers in multiple areas in biomedical research.
There is great enthusiasm in both sectors for collaboration. South Australia is exceptionally positioned in terms of datasets and registries because our healthcare services are interconnected, unlike any other state, with efforts underway to improve accessibility. AI is one of the key technologies that has potential to improve health outcomes, while reducing the associated costs, across a wide range of medical areas. It is also driving the majority of the disruptive innovation in the area currently, with significant potential for commercialisation.
Artificial Intelligence (AI), and more specifically machine learning, are one of the most trending topics in technology of today.
AI is a bigger concept to create intelligent machines that can simulate human thinking capability and behaviour, whereas machine learning more specifically is an application or subset of AI that allows machines to learn from data without being programmed explicitly.Unknown
Machine learning provides systems the ability to automatically learn and improve from experience without being explicitly programmed by humans. Machine learning focuses on the development of computer programs that can access data and use it learn for themselves. The primary aim is to allow the computers learn automatically with assistance, or even without human intervention, or assistance and adjust actions accordingly. Research is exploding in the AI space and Dr Johan Verjans is combining his medical training, molecular research background and experience in engineering and computer science to advance health care and improve patient outcomes, most recently exploring the use of Artificial intelligence in Imaging. He recently authored the Cardiovascular Diseases chapter in Springer Nature’s first book of Artificial Intelligence in Medical Imaging.
Examples of Dr Verjans application of AI and medicine are:
- Advancing one of world’s best algorithms for Visual Question Answering (VQA) that was developed by the AIML (Winner worldwide Facebook VQA Challenge 2.0), towards a medical VQA tool that allows medical professionals to access key information by asking questions using natural language and receiving real-time answers that bring together information from multiple diagnostic systems from a patient. In this context, Johan’s group won the global medical VQA challenge (IMAGECLEF 2020).
- The use of existing data from ECG (electrocardiogram), biomarkers and AI to determine if AI can improve decision support in patients presenting with chest pain to the emergency department (2020 NHMRC partnership grant);
- Advanced cardiovascular molecular imaging to reduce heart attacks through using technology and imaging to detect plaque in diseased heart vessels which have previously not been able to be identified, providing an opportunity for detection, prevention and early intervention (PREFFIR trial).
Dr Verjans is part of several international expert panels.
Here are two examples:
- A expert panel writing a state-of-the-art review of 3D Printing, Computational Modelling, and Artificial Intelligence for Structural Heart Disease
- Proposed Requirements for Cardiovascular Imaging-Related Machine Learning Evaluation (PRIME): A Checklist: Reviewed by the American College of Cardiology Healthcare Innovation Council
Johan Verjans is a consultant cardiologist at the Royal Adelaide Hospital and Dr Jones & Partners. He is a physician-scientist combining cutting-edge research and patient care. His research career (PhD Maastricht University/University of California; Post-doctoral fellow, Harvard Medical School) has focused on translational pre-clinical and clinical imaging biomarkers using advanced invasive and non-invasive molecular imaging strategies to detect, track and predict disease at an early stage.
His recent research has focused on imaging biomarkers from large datasets using supervised and unsupervised machine learning strategies. As Deputy Director of Medical Machine Learning at the Australian Institute for Machine Learning, his main role is to connect world-class machine learning capabilities to the Biomedical Precinct in Adelaide.
Story initially posted here by Ms Brooke Lee.