Advanced analytical techniques for intensive care big data
Lead Research Organisation:
UNIVERSITY OF CAMBRIDGE
Department Name: Applied Maths and Theoretical Physics
Abstract
The Intensive Care Unit (ICU) is characterised by state-of-the-art multimodality monitoring. Huge amounts of data are available to the clinician but the data is so complex that it cannot be fully appreciated and much information is discarded in practice. My project aims to develop novel and contemporary statistical and machine learning tools to derive a set of physiologically relevant features of the ICU data and perform online characterisation of a patient's state. The project also aims to deliver a range of software with a view to providing the clinician with a more precise and informed summary of the patient's clinical trajectory and therefore enabling improved clinical care.
Publications
Edinburgh T
(2023)
Bayesian model selection for multilevel models using integrated likelihoods.
in PloS one
Edinburgh T
(2022)
Bayesian model selection for multilevel models using integrated likelihoods
Edinburgh T
(2021)
DeepClean: Self-Supervised Artefact Rejection for Intensive Care Waveform Data Using Deep Generative Learning.
in Acta neurochirurgica. Supplement
Edinburgh T
(2022)
Sepsis-3 criteria in AmsterdamUMCdb: open-source code implementation
Edinburgh T
(2023)
Bayesian model selection for multilevel models using integrated likelihoods.
Edinburgh T
(2022)
Sepsis-3 criteria in AmsterdamUMCdb: open-source code implementation
Edinburgh T
(2022)
Sepsis-3 criteria in AmsterdamUMCdb: open-source code implementation
Edinburgh T
(2021)
Causality indices for bivariate time series data: A comparative review of performance.
in Chaos (Woodbury, N.Y.)
Studentship Projects
| Project Reference | Relationship | Related To | Start | End | Student Name |
|---|---|---|---|---|---|
| EP/N509620/1 | 30/09/2016 | 29/09/2022 | |||
| 2089662 | Studentship | EP/N509620/1 | 30/09/2018 | 30/03/2023 | Thomas Edinburgh |