DS4SmartDischarge

Project Vision

There are currently around 200 patients at University Hospital Southampton NHS Foundation Trust who are well enough to leave hospital but cannot be due to delays in arrangements for community care – this is using around 20% of hospital beds and is a significant winter pressure. We aim to help the NHS understand what sorts of patients are being delayed including their care needs. The understanding will be used to improve the operational response to acute care winter pressures for 2023/2024 but will also be useful throughout the year. Leaving hospital at the right time is better for patients for many reasons. It reduces physical and mental deconditioning and chance of hospital infections. Understanding what causes discharge problems, or not, helps the NHS improve planning and efficient use of resources.

We will use computer algorithms to help understand what causes patients to be delayed or not. The analysis will be done using statistics and machine learning. Machine learning is a way to train a computer to categorise patients into groups using data about patients and services they use. We will use historical hospital data (health status, procedures, treatments and care needs assessment) to identify patient groups at risk of different discharge outcomes. The patient categories will then be used to inform how to improve discharge processes and onward care service planning.

Patients and public have helped develop the research through workshops exploring experiences of complex discharge and patient choice. PPIE will be involved in one workshop to discuss the findings from this study.