Mohammed A. Mohammed
Why is this project important?
Considering safer decision in a digital world, we are looking at the safety of algorithms embedded within clinical systems.
As patient safety specialists, we are also interested in the broader questions around dependability, success factors and understanding un-intended consequences.
What are we doing?
We are developing and evaluating computer-aided risk tools to improve patient safety within secondary care. We hope that our tools can bring the risks to the attention of healthcare staff so that they can address problems early.
Specifically, we have developed automated risk scores that provide clinicians with real time estimates of the patients’ risk of death and sepsis during their stay in hospital.
Outputs and Impact
- We have developed four validated automated risk scores.
- We have shown that staff view our automated scores favourably because the scores (a) are automated, (b) require no additional data collection, and (c) combine 16 clinical variables whilst aiming to support the clinical decision-making process with real time estimates of the patient’s risk of death and sepsis.
- We have published our work in peer-reviewed scientific journals:
- Faisal et al. (2018). Development and validation of a novel computer-aided score to predict the risk of in-hospital mortality for acutely ill medical admissions in two acute hospitals using their first electronically recorded blood test results and vital signs: a cross-sectional study. BMJ Open. [https://bmjopen.bmj.com/content/8/12/e022939.info]
- Faisal et al. (2018). A comparison of modern computationally intensive modelling methods with a simple multivariable logistic regression approach to predict the risk of in-hospital mortality in acutely ill medical admissions. [https://bradscholars.brad.ac.uk/handle/10454/16623]
- Faisal et al. (2018). Development and external validation of an automated computer aided risk score for predicting sepsis in emergency medical admissions using the patient’s first electronically recorded vital signs and blood test results. [https://journals.lww.com/ccmjournal/fulltext/2018/04000/Development_and_External_Validation_of_an.18.aspx#pdf-link]
Contact for more information
If you have any questions about our CARS research, please contact Carolyn McCrorie via email at firstname.lastname@example.org.