Bookmarks
Evaluating Venous Thromboembolism (VTE) Risk Assessment Pathways & Using Large Language Models to Identify VTE Events: A Feasibility Study
Safe People
Organisation name
Imperial College London
Organisation sector
Academic Institute
Applicant name(s)
Aya Riad
Funders/ Sponsors
Erik Mayer
DEA accredited researcher?
Unknown
Sub-licence arrangements (if any)?
No
Safe Projects
Project ID
NIBDAPC_2024_0038
Lay summary
Venous thromboembolism (VTE) (blood clots that form in deep veins, typically in the lower leg, thigh or pelvis) is a serious condition that can occur in patients during or shortly after a hospital stay as it is caused by factors such as reduced mobility and/or acute illness. These blood clots can travel through the blood vessels to reach the lungs and cause chest pain and breathing difficulties and in extreme cases, potentially cause death. Best clinical practise guidelines suggest that all patients admitted to hospital must have their risk of developing VTEs assessed and hospitals must report on how well they assess and manage VTE risk in patients. Currently, this involves a time-consuming review of patient records to manually determine the number patients who develop VTE whilst in hospital and also how well their risk was assessed. This project aims to explore whether the current way we assess the risk of patients developing VTEs is accurate and whether it actually reduces the chances of patients getting blood clots. We also aim to use artificial intelligence (AI) to help identify patients with blood clots more efficiently and to automatically fill in parts of the VTE risk assessment form using information already available in a patient’s hospital records. As risk assessment forms are currently completed by busy clinicians, we believe this project will not only save clinician time which can be redirected towards patient care but also potentially result in more accurate individual risk assessments – improving patient safety. The AI will be used in a secure data environment and all patient data used in this project will be de-identified, meaning personal details will be removed to ensure privacy.
Public benefit statement
This project aims to streamline the process of VTE event detection and risk assessment which would both contribute to reduced clinician time spent on these activities. This time can be redirected to providing patient care translating to public benefit. The VTE risk assessment process is currently time consuming as it involves reviewing the patient’s past medical history, medications and blood results, this is currently completed to unknown levels of accuracy as the form needs to be completed to prescribe any medication leading to it being seen as a hurdle to prescribing medications. Our project aims to evaluate the current process and allows us to determine if patients are being appropriately risk assessed for an event associated with potential high morbidity and mortality. An algorithm which streamlines aspects of the risk assessment process by pulling data already captured in the Electronic Patient Record may improve the accuracy of risk assessments by ensuring the forms are filled based on data from the patient’s records and highlighting to doctors important aspects of a patient’s history relevant to their risk of developing blood clots which may otherwise be missed if a doctor is not familiar with a patient is having to go through a lot medical notes. This can reduce the occurrence of dangerous events such as the prescription of blood thinning injections when patients are already taking other blood thinning medications which increases their risk of bleeding, avoiding such dangerous events improves patient safety.
Request category type
Public Health Research
Other approval committees
Project start date
20/02/2025
Latest approval date
15/01/2025
Safe Data
Dataset(s) name
TBC
Common Law Duty of Confidentiality
Not applicable
National data opt-out applied?
Not applicable
Request frequency
One-off
Release/Access date
20/02/2025
Safe Setting
Access type
TRE