King, Zella; Gillham, Jon; Utley, Martin; Lundell, Sara; Graham, Matt; Crowe, Sonya; (2025) patientflow: a Python package for real-time prediction of hospital bed demand from current and incoming patients. The Journal of Open Source Software , 10 (116) , Article 9187. 10.21105/joss.09187.

Preview

Text 10.21105.joss.09187.pdf - Published Version Download (192kB) | Preview

Abstract

patientflow is a Python package available on PyPi(King et al., 2025) for real-time prediction of hospital bed demand from current and incoming patients. It enables researchers to easily develop predictive models and demonstrate their utility to practitioners. Researchers can use it to prepare data sets for predictive modelling, generate patient level predictions of admission, discharge or transfer, and then combine patient-level predictions at different levels of aggregation to give output that is useful for bed managers. The package was developed for University College London Hospitals (UCLH) NHS Trust to predict demand for emergency beds using real-time data. The methods generalise to any problem where it is useful to predict non-clinical outcomes for a cohort of patients at a point in time. The repository includes a synthetic dataset and a series of notebooks demonstrating the use of the package.

Download activity - last month

Export as XMLJSONCSV

Download activity - last 12 months

Export as XMLJSONCSV

Downloads by country - last 12 months

Export as CSVJSONXML

Archive Staff Only

View Item