Research IT

CORONET COVID-19 Risk in Oncology Evaluation Tool - Phase II

In January 2021, our Research Software Engineers worked with the Digital Experimental Cancer Medicine Team (dECMT) to create a tool to support decisions regarding hospital admissions or discharge in cancer patients presenting with symptoms of COVID-19. The tool has been so successful that multiple improvements are now planned.

The COVID-19 vaccination programme is quickly rolling out nationally but cancer patients are still at increased risk of severe COVID-19. To help tackle this, Research IT has been working with the Digital Experimental Cancer Medicine Team (dECMT) based within the Cancer Research UK (CRUK) Manchester Institute to improve the recently launched tool CORONET. This tool aims to support decisions regarding hospital admissions or discharge in cancer patients presenting with symptoms of COVID-19 and the likely severity of illness.

The existing CORONET decision-making tool has been shown to be critical for hospital admission, severity prediction and increased monitoring for early intervention with over 400 visitors to the site so far. After consultation with clinicians and Project Lead, Dr Rebecca Lee, several areas of improvement have been identified for Phase II of the project.

In Phase II the team plans to:

  1. Plug in an updated machine learning model - which has now been trained with 1000+ patients - using data that captured patient's cancer stage, symptoms, test results and crucially their subsequent treatment and ultimate outcome.
  2. Update the input form fields to expand and improve the data collected and improve the calculation of risk factors and potential outcome for the patient when compared with the patient cohort.
  3. Update the resulting output explanation, improving the context and decision-making process, including data from the new fields and model.
  4. Improve the final explanation to the consultant and patient by linking their results with the five nearest/similar patients, based not just on score but all criteria combined.

Dr Lee said “Research IT have been fantastic in creating a user-friendly tool in a very short space of time to help health care professionals with their daily challenges in managing patients with cancer and COVID-19. We have had extremely positive feedback about how easy and informative the tool is to use. Excited in the next phase to really build on the excellent work so far.”

If you are interested in having a Research Software Engineer work with you on your research project please get in touch with us for an initial consultation.