Up to 30% of patients admitted to hospital with COVID (novel coronavirus infection) will require admission to an intensive care unit (ICU) and potentially help with breathing via a ventilator.
We will develop statistical and artificial intelligence approaches to predict which patients are most likely to require admission to ICU and ventilation. These tools will be based on a snapshot of the information available when a patient is admitted to hospital, as well as new information that become available during a patient’s hospital stay.
Our approaches aim to allow patients needing ICU care to be identified earlier to allow their care to be prioritised.
See publications:
An adversarial training framework for mitigating algorithmic biases in clinical machine learning
Self-Aware SGD: reliable incremental adaptation framework for clinical AI models
Development and validation of early warning score systems for COVID-19 patients
Rapid triage for COVID-19 using routine clinical data for patients attending hospital
Real-world evaluation of rapid and laboratory-free COVID-19 triage for emergency care: external validation and pilot deployment of artificial intelligence driven screening
Machine learning generalizability across healthcare settings: insights from multi-site COVID-19 screening