C4TS undertakes modelling and prediction work in the areas of Mass Casualty Event (MCE) planning, amputation prognostics, and coagulopathy. 

Good judgement and decision-making are essential to safe and effective practice of medicine. However, decisions surrounding the trauma patient are often made under challenging conditions that may affect the accuracy of judgement. Inadequate information, high degrees of uncertainty, critical time constraints, and high levels of risk, commonly affect doctors treating trauma patients.

Challenges to the clinician include diagnosing problems, assessing the level of risk the problem poses, estimating the time available to solve the problem, and identifying possible solutions. Accurate identification of potential problems is paramount to effective medical care, and misinterpreting the situation during this stage of decision-making is a common cause of medical errors.

Once a problem is identified, the next stage is to decide on an appropriate course of action or treatment. If the situation is interpreted correctly, then decisions on appropriate action have a much greater chance of being correct too (Croskerry, 2013).

Despite the rapid expansion in medical knowledge, clinical decisions will continue to be based on uncertain information. C4TS seeks to develop methods to understand, communicate, and reason with uncertainty in trauma care environments, and how these methods can be used to reduce judgement errors and support rational decision-making.

We work in collaboration with Risk and Information Systems Research Group, School of Electronic Engineering and Computer Science, at QMUL. We are taking advantage of the development of machine learning. A major application of this developing technology is in prediction. To date this group has worked on Mass Casualty Event (MCE) planning, limb salvage decision support, and predicting the likelihood of coagulopathy.

 

Share this page