About the Project
The successful candidate will enrol at Coventry University, UK as their home institution and will spend up to 2 years at I2R of A*STAR. Our Coventry group is experienced in the intelligent healthcare. The A*STAR group has rich experiences in AI, deep learning and computer vision. The complementary expertise of both groups will ensure the successful implementation of this collaborative project.
If you are interested in applying, please contact Dr Jiangtao Wang in the first instance. [email protected]
Project DescriptionVarious types of data have been emerging in modern biomedical research, including electronic health records, imaging, sensor data and text, which are complex, heterogeneous, poorly annotated and generally unstructured. Gaining knowledge and actionable insights from complex, high-dimensional and heterogeneous biomedical data remains a key challenge in health care, as traditional data mining and statistical learning approaches typically need to ﬁrst perform feature engineering to obtain effective and more robust features from those data. The latest advances in deep learning technologies provide new effective paradigm to obtain end-to-end learning models from complex data. However, deep learning approaches have not been extensively evaluated for a broad range of medical problems that could benefit from its capabilities. To facilitate its practical usage with health care information workflows and clinical decision support, we must address several challenges uniquely relating to the characteristics of health care data (i.e. sparse, noisy, heterogeneous, time-dependent).
The existing expert knowledge for medical problems is of great value to significantly ease the above challenges. In this PhD project, we aim to develop models and a system with the goal of incorporating the expert knowledge into the deep learning process to guide it toward the right direction. Our solution attempts to perform knowledge transfer learned from similar diseases or patients (called source domain), which will be extracted from data sources (e.g., MIMIC provided by MIT) or medical knowledge bases (such as online encyclopaedia and PubMed). In order to achieve this goal, this project will answer the following specific questions: Given an intelligent healthcare task as target domain (e.g., COVID-19 mortality prediction based on clinical images), (a) WHAT knowledge can be transferred from source domain? (a) HOW to transfer the knowledge into the deep learning task of target domain to maximize its utility.
We are looking for highly motivated candidates who have a strong interest in developing innovative healthcare technologies and has a good understanding of AI and deep learning models. The PhD project requires working with clinicians, biomedical engineers, and computer scientists and AI experts at different stages along the development pathway – and will lead to high-quality publications. It will involve clinical data collection and analysis, and a variety of computing work.
Training and DevelopmentThe successful candidate will receive comprehensive research training including technical, personal and professional skills.
All researchers at Coventry University (from PhD to Professor) are part of the Doctoral College and Centre for Research Capability and Development, which provides support with high-quality training and career development activities.
Entry criteria for applicants to PhD• A minimum of a 2:1 first degree in a relevant discipline/subject area with a minimum 60% mark in the project element or equivalent with a minimum 60% overall module average.
the potential to engage in innovative research and to complete the PhD within a 3.5 years
• a minimum of English language proficiency (IELTS overall minimum score of 7.0 with a minimum of 6.5 in each component)
For further details see: https://www.coventry.ac.uk/research/research-students/making-an-application/
How to applyTo find out more about the project please contact Dr Jiangtao Wang [email protected]
To apply online please visit: https://pgrplus.coventry.ac.uk/studentships/hls-transferring-existing-expert-knowledge-into-deep-learning-based-intelligent-healthcare
All applications require full supporting documentation, a covering letter, plus an up to 2000-word supporting statement showing how the applicant’s expertise and interests are relevant to the project.
Duration of study: Full-Time – between three and three and a half years fixed term
Application deadline: 15 Oct, 2020
Start date: January 2021
Why not add a message here
Based on your current searches we recommend the following search filters.
Based on your current search criteria we thought you might be interested in these.