CDT Postgraduate Studentship in Healthcare Innovation (RCUK Digital Economy Programme grant number EP/G036861/1)
Mortality Prediction in the ICU
Severity of illness scores have gained considerable interest for their use in predicting outcomes such as mortality and length of stay. The most sophisticated scoring systems require the collection of numerous physiologic measurements, making their use in real-time difficult. A severity of illness score based on a few parameters that can be captured electronically would be of great benefit. By developing a particle swarm optimized severity score, which uses variables selected by a genetic algorithm, I have reduced the number of physiologic parameters collected in the Acute Physiology, Age, and Chronic Health Evaluation (APACHE) IV system and developed a new score without losing predictive accuracy.
We called the score developed from the cascaded machine learning methods the Oxford Acute Severity of Illness Score (“OASIS”). Predictive models of intensive care unit mortality using OASIS were developed on admissions during 2007-2009, and validated on admissions during 2010-2011. The most parsimonious OASIS score consisted of 7 physiologic measurements, elective surgery, age, and prior length of stay. Predictive models of intensive care unit mortality using OASIS achieved an area under the receiver operating characteristic curve of 0.88, and calibrated well