DS4SmartDischarge

DS4SmartDischarge logo

Data Science Informing Complex Discharge Winter Policy

Health & Wellbeing Artificial Intelligence

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 /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.

Project Objectives

  • Use statistical methods and machine learning to explore association and correlation of patient variables (hospital episodes, onward care assessments) with discharge outcomes (patient elongated length of stay, readmission, discharge to assess pathway, onward care needs/demand).
  • Use these data to identify causes of discharge pressure
  • Characterise early warning signals to predict discharge pressure including relationship to “Discharge to Assess” intervention D) Inform DHSC, NHS policy makers and system representatives about insights as input to operational response to acute care winter pressures for /2024.

IT Innovation's Role

IT Innovation leads the project

Project Funding

HDRUK Logo

NHS Southampton logo This project is a collaboration with the University Hospitals Southampton Foundation Trust

Related Projects

Read More

PARIEDA

Health & Wellbeing, Artificial Intelligence
Read More

PHILOSARIP

Health & Wellbeing, Artificial Intelligence
Read More

PROCED

Health & Wellbeing, Artificial Intelligence