Biography
Professor Tingting Zhu graduated with the DPhil degree in information and biomedical engineering at Oxford University in 2016. This followed her MSc in Biomedical Engineering at University College London and BEng (Hons) in Electrical Engineering from the University of Malta.
After DPhil, Tingting was awarded a Stipendiary Junior Research Fellowship at St. Hilda's College, Oxford. In 2018, Tingting was appointed as the first Associate Member of Faculty at the Department of Engineering Science; in 2019, following the award of her Royal Academy of Engineering Research Fellowship, she was appointed to full Member of Faculty at the Department of Engineering Science. Tingting is a Non-Tutorial Fellow at Kellogg College and a Stipendiary College Lecturer at Mansfield College.
Most Recent Publications
A Survey of Few-Shot Learning for Biomedical Time Series.
A Survey of Few-Shot Learning for Biomedical Time Series.
DySurv: dynamic deep learning model for survival analysis with conditional variational inference.
DySurv: dynamic deep learning model for survival analysis with conditional variational inference.
Benchmarking Large Language Models in Evidence-Based Medicine.
Benchmarking Large Language Models in Evidence-Based Medicine.
CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks
CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks
Position: reinforcement learning in dynamic treatment regimes needs critical reexamination
Position: reinforcement learning in dynamic treatment regimes needs critical reexamination
Research Interests
Tingting's 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 the developing world.
Current Projects
- Machine learning for improving decision-making with telemedicine
- Prognosis and diagnosis of adversarial events in multimorbid population
- Dynamic modelling for understanding the impact of interventions on the hospital system
- Phenotyping patients with complex diseases via electronic patient information
- Machine learning for early cancer detection as well as treatment response
- Digital twin and its application in healthcare
- Modelling of treatment effect and treatment recommendation
Most Recent Publications
A Survey of Few-Shot Learning for Biomedical Time Series.
A Survey of Few-Shot Learning for Biomedical Time Series.
DySurv: dynamic deep learning model for survival analysis with conditional variational inference.
DySurv: dynamic deep learning model for survival analysis with conditional variational inference.
Benchmarking Large Language Models in Evidence-Based Medicine.
Benchmarking Large Language Models in Evidence-Based Medicine.
CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks
CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks
Position: reinforcement learning in dynamic treatment regimes needs critical reexamination
Position: reinforcement learning in dynamic treatment regimes needs critical reexamination
DPhil Opportunities
Prof Zhu offers a wide range of machine learning projects for healthcare in both developed and developing countries. Prospective DPhil students should get in touch indicating their interest.
Most Recent Publications
A Survey of Few-Shot Learning for Biomedical Time Series.
A Survey of Few-Shot Learning for Biomedical Time Series.
DySurv: dynamic deep learning model for survival analysis with conditional variational inference.
DySurv: dynamic deep learning model for survival analysis with conditional variational inference.
Benchmarking Large Language Models in Evidence-Based Medicine.
Benchmarking Large Language Models in Evidence-Based Medicine.
CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks
CliqueFluxNet: Unveiling EHR Insights with Stochastic Edge Fluxing and Maximal Clique Utilisation Using Graph Neural Networks
Position: reinforcement learning in dynamic treatment regimes needs critical reexamination
Position: reinforcement learning in dynamic treatment regimes needs critical reexamination
