Fever is an important sign of infection and can be used to work out how to manage patients after they arrive at a hospital Emergency Department (ED) (called a “care pathway”). Often, patients with fever need specific tests or may even be admitted to hospital straightaway (for example if sepsis is suspected; severe infections responsible for approximately 44,000 annual deaths in the UK). Whilst we know that it is essential to correctly select a care pathway and treat fever to improve outcomes, the way that responding to suspected diagnoses affects the ability of hospitals to care for other attending or admitted patients has not been investigated.
Limits imposed by current care pathways for patients presenting with fever are likely to cause congestion within the ED and wider hospital due to delays associated with bed availability. In turn, operational inefficiencies are likely to lead to worse patient outcomes. In this study we will run a controlled analysis to determine the impact that patients with fever have on the operational ability of Oxfordshire hospitals to provide efficient and effective care, using outcomes such as mortality and timely care metrics, so that we can determine ways to better manage patients in future.
See publications:
Improving patient flow during infectious disease outbreaks using machine learning for real-time prediction of patient readiness for discharge.
Hospital admission location prediction via deep interpretable networks for the year-round improvement of emergency patient care.
Predicting individual patient and hospital-level discharge using machine learning.
Addition of macrolide antibiotics for hospital treatment of community-acquired pneumonia.
Community-acquired pneumonia identification from electronic health records in the absence of a gold standard: a Bayesian latent class analysis.