Development and clinical validation of sepsis prediction algorithm in an ICU
The aim of the project is to first improve and then clinically validate an algorithm for predicting sepsis. The project stakeholders will work together to refine the algorithm, develop a user interface and test the algorithm in a clinical setting in an intensive care unit (ICU). The algorithm is being developed using so called machine learning in a collaboration between AlgoDx AB and Uppsala University.
Expected results and effects: The project will lead to an improvement of the algorithm's accuracy and allow it to be tested in Swedish healthcare for the first time. Use of the algorithm is expected to facilitate earlier detection of sepsis and to more quickly initiate sepsis treatment in patients admitted to ICU.
Expected benefits: Reduction of the number of days patients stay at hospital/ICU, a reduction in the number of patients who contract sepsis and the number of deaths. This in turn is expected to lead to lowered health care costs and lowered economic burden on society.
Approach and implementation: The project consists of three parts. The algorithm will be processed to improve its accuracy. A user interface will be developed together with staff from the ICU in Malmö. Finally, a clinical validation study will be conducted at the ICU.
Project period
2020-04-15 – 2021-10-30
Funding
Vinnova
Project members
At the Department of Statistics:
- Inger Persson, senior lecturer
- Andreas Östling, PhD student