Technology UK CU – As Artificial Intelligence (AI) further rearranges our lives with AI inspired algorithms that suggest content according to our viewer history, AI inspired financial market predictors and even AI inspired human voice generators. A new AI inspired tool produced at the University College London and the University College London Hospitals (UCLH) could possibly forecast the number of patients arriving at the emergency department that will be required to be admitted into the hospital, helping planners manage demand on beds.
Details of the study was published in Nature Digital Medicine which indicated the number of hospital beds required in 4 and 8 hours can be predicted by looking at live data on patient arrivals in emergency department.
The tool had the possibility of surpassing the accuracy of conventional tools used by planners related to the average number of beds needed on the same day of the week for the previous 6 weeks.
The tool also had the ability account for patients expected to come in, with more precise details. Instead of a single number forecasting for the overall day, the tool adds a probability distribution for the number of beds needed in 4- and 8-hours’ time and delivers its predictions 4 times a daily, and sent to hospital planners.
The researchers are currently working with UCLH on optimizing the models so that they can estimate how many beds will be needed in different areas of the hospital.
Dr Zella King who was the lead author said “Our AI models provide a much richer picture about the likely demand on beds throughout the course of the day. They make use of patient data the instant this data is recorded. We hope this can help planners to manage patient flow – a complex task that involves balancing planned-for patients with emergency admissions. This is important in reducing the number of cancelled surgeries and in ensuring high-quality care.”
