For the past 2 months I’ve been travelling across the country and working with partners on their strategies for improving patient flow, specifically alleviating provider and system pressures relating to stranded and super stranded patients. I of course have met people who are doing this well and others who are working towards, with everyone giving it their all. Many of the executives and teams I meet are struggling with a few common things, firstly they can’t seem to get system providers to match their data readiness to support a more lubricated discharge process. Secondly, everyone has a system meeting each week to review the patients who need to be moved to a more appropriate location, social care, community beds etc. However, getting the system to proactively support here still seems to be a challenge.
So how do we get more grit and control to improve flow and system working? We are supporting many partners with their strategies around this whilst ensuring that we have people on the ground working hand in glove to move on the data readiness challenge and accountability across systems. Predicting some of the demand and complexity is key, in my opinion, an opinion which has been informed by 54 executives who spent the day sharing the challenges with D&D.
With the winter months rapidly approaching, the threat of an NHS at full capacity looms as a daunting prospect and potential soon-to-be reality. NHS England and NHS Improvement recently reported some alarming figures relating to stranded and super stranded patients. Particularly striking was the 330,826 super stranded patients that struggled to make their way through hospitals between April 2018 and March 2019. The NHS has outlined a need for trusts to reduce the number of super stranded patients by 25% from their 2017/18 baseline, but a staggering 90% of NHS trusts have yet to meet this target.
The length of stay these patients face is incredibly concerning when you consider that even a 10-day hospital bed stint can severely impact muscle mass in stranded pensioners – a change that equals a decade’s worth of “ageing” in these patients. Alongside the risk to patient health that comes from these excess bed days, the NHS has seen 80,000 operations cancelled at the last minute during this period thanks to a host of non-clinical factors, including lack of bed availability. In light of this, health officials have pledged to improve the speed and efficiency of patient assessment and transitioning back to their homes or care homes. While theoretically a good idea, the means of actually doing so can produce a cycle of strain on the NHS, discharging patients prematurely and increasing the need for readmission, often causing further complications due to insufficient support and post-acute care. It is clear to see that new systems are needed to help support trusts as a whole, and to standardise improved management, care and conditions for patients throughout their journey – enter AI.
What you can likely tell from all of this is that the NHS does not suffer from a lack of data, but rather in what to do with it all. It is my strong belief that intelligent and targeted analysis of the information collected by health care centres is the key to unlocking NHS England and NHS Improvement’s ultimate goal of reducing the number of super stranded patient-occupied beds by a total of 40%, and I am confident that AI platforms are an excellent tool with which to tackle this. Throughout the country, healthcare teams and leadership have already begun to harness these platforms for better understanding of their patient flow. This is a promising step forward in the way health care centres are beginning to strategize the handling of big issues facing the NHS.
The NHSI is currently advising utilisation of tools from the private sector in order to support optimisation of patient care and to help reduce the strain on NHS trusts, bearing the burden of handling, analysing and visualising the large quantities of data produced by hospitals. These algorithms will be a powerful aid to the prediction and monitoring of the range of variables that determine management and flow of patients through a hospital when used alongside the clinical expertise of health practitioners. We are always open to broadening the discussion and possibilities for AI in reducing prolonged hospitalisation, and if you are interested in exploring this potential further please feel free to drop us a note.