AI for Time-series Patient monitoring and Risk Prediction
The recent availability of Electronic Health Records and information collected from wearables allows for the development of monitoring and predicting patient risk of deterioration and trajectory evolution. However, prediction of disease progression with the aforementioned patient data is challenging since they are sparse, heterogeneous, multi-dimensional, and multimodal time-series. The talk will describe methods used in artificial intelligence to overcome these challenges.
Tingting Zhu is a Royal Academy of Engineering Research Fellow (equivalent to Assistant Professor) and Member of Faculty in the Department of Engineering Science. She is a Fellow of St. Hilda's College, Oxford and a Lecturer at Mansfield College, Oxford.
She graduated with the DPhil degree in information and biomedical engineering within the Institute of Biomedical Engineering at Oxford University, following degrees in Biomedical Engineering and Electrical Engineering. Her research interests lie in machine learning for healthcare applications and she has developed probabilistic techniques for reasoning about time-series medical data. Her work involves the development of machine learning for understanding complex patient data, with an emphasis on Bayesian inference, deep learning, and applications involving low-income countries.