Translational AI for Healthcare
The past decade has seen substantive progress in artificial intelligence (AI) technological development, most notable in machine learning. In the application space, intelligent systems that use deep neural network architectures are now emerging from clinical trial and slowly moving into routine care.
The Translational AI for Healthcare research program addresses the challenges of developing and implementing real-world intelligent systems that support human decision-making. Our team uses advanced statistical and machine learning / deep learning methods to exploit patterns in large-scale and multi-modal healthcare data-sets, such as imaging data, electric health records (EHRs) and multi-omics data, and to extract medically relevant information from the data to support clinical tasks, such as diagnosis, treatment recommendation, and workflow optimization.
In addition to the creation of new AI-enabled systems, our team is also committed to addressing the transportability problem in healthcare AI. One of the biggest risks for clinical services adopting AI is that the technology they acquire may not be fit for their specific purpose, and lead to decision-making errors that could seriously harm their patients. This is because AI algorithms that demonstrate excellent performance in one setting may exhibit degraded performance elsewhere. Our goal is to research, develop and evaluate a new generation of statistical and machine learning methods for assessing and enhancing the transportability of healthcare AI into real life settings.
For more information or to join our team
Contact Dr Sidong Liu: sidong.liu@mq.edu.au
Team members
| Dr Sidong Liu | Stream Lead |
| Dr Priyanka Rana | Postdoctoral Research Fellow |
| Dr Thomas Cong | Postdoctoral Research Fellow |
| Ms Yiqiao Yan | Research Assistant |
| Ms Mehnaz Tabassum | PhD Candidate |
| Ms Homay Danaei Mehr | PhD Candidate |
| Ms Somayeh Farahani | PhD Candidate |
| Ms Sahar Moradi | PhD Candidate |
| Mr Wenjin Zhong | Masters Research |
| Mr Xingnan Li | Masters Research |
Selection stream projects
- Automated severity assessment of COVID-19 based on clinical and imaging data
- AI-assisted digital histopathology image computing for tumour diagnosis
- AI improves diagnosis and treatment of brain diseases
- Predicting MND patient status by machine learning, MQRAS Grant, 2022.
- Computational analysis and AI in brain tumour imaging: towards the augmented diagnostics of the future, NHMRC Ideas Grant, 2023.
- MND-Biotyper: machine learning applied to molecular protein patterns for diagnosis and prognosis of MND. MQRAS Grant, 2023.
