The UK’s National Health Service (NHS) is exploring the use of artificial intelligence (AI) to predict when patients are at risk of experiencing extended hospital stays. This initiative, developed in collaboration with the Accelerated Capability Environment (ACE), aims to assist healthcare professionals in identifying patients who may require prolonged hospital care and take preventive measures to improve patient outcomes.

The AI tool was tested at the Gloucestershire Hospitals NHS Foundation Trust, where it was trained on 460,000 anonymized patient records. The objective was to provide reception and clinical staff with an immediate risk score for long hospital stays, enabling them to adjust treatment plans and mitigate known risk factors.

During a 12-week period, the AI tool successfully identified 66% of patients at the highest risk of long hospital stays. This promising result has significant implications for both patient health and cost savings within the healthcare system. Reducing the average hospital stay by just one day could potentially save the NHS in Gloucester £1.7 million.

After successful proof-of-concept testing, the AI tool progressed to an Alpha phase and was integrated into the trust’s electronic health record system. It was also assessed against pandemic data and remained highly accurate.

The project demonstrates the NHS’s commitment to harnessing AI and its potential to enhance patient care and optimize healthcare resource allocation. This development aligns with the broader efforts to modernize healthcare services using technology and data-driven approaches.

Article written by Louis Morris