Why Hospitals and ICBs are Seeking New Intel to Find Hidden High-Risk Patients on Waiting Lists

C2-Ai Opinion Article by Dr Mark Ratnarajah, NHS Paediatrician, UK Managing Director, C2-Ai.
Clinical teams continue to work relentlessly to get through the elective backlog. I see it every day with frontline colleagues, and with clinical leads I speak to at organisational and regional levels. Their aim is to help as many patients as possible in the face of a highly complex and enduring peri-pandemic challenge.

Many are doing everything they can to increase capacity to try to help. From creating more theatre capacity, to drawing on the independent sector, to establishing specially focussed weekends where surgeons come in to treat and operate on patients with specific conditions.

I recently heard from one integrated care board chief executive, who explained how the organisation was working to make the most of surgical capacity, and how it was prioritising patients with clinically urgent and time-critical conditions, including cancer, as well as patients who have been waiting a very long time. In line with national priorities, this is reflective of work in many regions, trying to urgently help some of the most vulnerable patients.

Addressing demand, not just supply

With that same mission in mind, there is also now an increasing appetite to better understand the demand component of waiting lists, in addition to opportunities to maximise supply. And for good reasons.

Strong evidence is emerging that patients are becoming increasingly unwell as they wait longer. It is something more and more NHS customers have asked us to examine, and the data consistently confirms that a large number of patients are deteriorating as they wait. That is not just a problem amongst high acuity patients, it is across the board, for all high-volume specialties. In many cases even those who might have been considered routine, and low risk at the point of their referral based on their procedure or surgery priority score, are becoming significantly more unwell because of their comorbidities.

This also means that for some hospitals and regions, waiting lists have actually become longer, with average complexity having gone up, and the range of complexities faced by patients on the waiting list also increasing.

With more complex patients to deal with on the waiting list, clinicians are concerned that some of those patients will inevitably decompensate, and present to A&E, at which point they will require a much more protected course of treatment, referrals for multiple problems, and face worse outcomes.

This could also directly limit the ability to deal with the backlog itself, and lead to financial challenges. Integrated care systems are being financially incentivised to exceed elective surgical capacity, as well as facing penalties for underperforming against pre-COVID targets, all at a time when resources are already stretched, strikes are continuing, and doing more with less is an extremely difficult and almost impossible task.

Hospitals and ICSs are therefore recognising that doing nothing, or doing business as usual, even with increased supply, is not sustainable and may create more problems.

Risk stratifying the entire waiting list

Entirely new ways to manage patients on waiting lists are emerging. National priorities are still in focus. But in addition, regions, trusts, and peri-surgical teams are searching for a much more detailed and granular understanding of the needs, and importantly the risks, of all patients on waiting lists.

They are calling for intelligence on what is coming, and they want to know if individual patients have gotten worse, or if they are at risk of getting worse. In doing so, they are unveiling hidden risk on their lists.

They want to target interventions to patients at most risk, to optimise the care of those patients ahead of their surgery, and focus theatre time.

This is about using data to make surgery more efficient and effective, with increased visibility of those who are decompensating, rather than a broad-brush approach based solely on using a patient's time on the waiting list, as a measurement for when something needs to be done.

The opportunity is to reduce mortality and complications, and prevent people dropping off waiting lists and presenting to the emergency department. And for patients on the list, surgical teams can minimise lengths of stay, convert patients to day cases, and therefore curtail demand and increase throughput.

Emerging models - blueprints ready to scale

This opportunity is being realised. We are working with dozens of trusts in more than a third of ICS regions across England who are doing ground-breaking work by being able to accurately identify patients at risk of complications or death as they wait.

In one NHS England funded initiative, surgeons have saved many thousands of hours by using an AI-based model to risk stratify hundreds of thousands of patients each week. This is helping peri-surgical teams to make informed and consistent decisions on prioritising patients for surgery according to greatest clinical need. A national health economics unit evaluated that the project has freed up at least 125 bed days per 1,000 patients on waiting lists, enabled substantial reductions in emergency admissions, and has seen a 27% reduction in long-waiters and the highest urgency patients, within a matter of weeks of deployment.

And in other cases, more is being done to target patients to keep them well as they wait. Using the same AI technology, one region is leading the way in this, giving clinical and surgical teams a complete understanding of patients likely to deteriorate, and showing them specific risks and how best to focus their intervention whilst empowering the patient at the same time. Targeted prehabilitation resulting from this intelligence is helping to prevent deterioration and prepare patients for surgery, with a mitigation of avoidable harm measured alongside reductions in length of stay, and many patients being discharged within a day.

Scaling these initiatives could go a long way to preventing additional demand from avoidable complexity, as the elective challenge remains a national priority. As one lead surgeon involved continues to stress, the principle of this is simple: Treating the right patient, in the right place, and at the right time.

So, what are they calling for?

Risk stratifying the entire waiting list

Entirely new ways to manage patients on waiting lists are emerging. National priorities are still in focus. But in addition, regions, trusts, and peri-surgical teams are searching for a much more detailed and granular understanding of the needs, and importantly the risks, of all patients on waiting lists.

They are calling for intelligence on what is coming, and they want to know if individual patients have gotten worse, or if they are at risk of getting worse. In doing so, they are unveiling hidden risk on their lists.

They want to target interventions to patients at most risk, to optimise the care of those patients ahead of their surgery, and focus theatre time.

This is about using data to make surgery more efficient and effective, with increased visibility of those who are decompensating, rather than a broad-brush approach based solely on using a patient's time on the waiting list, as a measurement for when something needs to be done. The opportunity is to reduce mortality and complications, and prevent people dropping off waiting lists and presenting to the emergency department. And for patients on the list, surgical teams can minimise lengths of stay, convert patients to day cases, and therefore curtail demand and increase throughput.

Emerging models - blueprints ready to scale

This opportunity is being realised. We are working with dozens of trusts in more than a third of ICS regions across England who are doing ground-breaking work by being able to accurately identify patients at risk of complications or death as they wait.

In one NHS England funded initiative, surgeons have saved many thousands of hours by using an AI-based model to risk stratify hundreds of thousands of patients each week. This is helping peri-surgical teams to make informed and consistent decisions on prioritising patients for surgery according to greatest clinical need. A national health economics unit evaluated that the project has freed up at least 125 bed days per 1,000 patients on waiting lists, enabled substantial reductions in emergency admissions, and has seen a 27% reduction in long-waiters and the highest urgency patients, within a matter of weeks of deployment.

And in other cases, more is being done to target patients to keep them well as they wait. Using the same AI technology, one region is leading the way in this, giving clinical and surgical teams a complete understanding of patients likely to deteriorate, and showing them specific risks and how best to focus their intervention whilst empowering the patient at the same time. Targeted prehabilitation resulting from this intelligence is helping to prevent deterioration and prepare patients for surgery, with a mitigation of avoidable harm measured alongside reductions in length of stay, and many patients being discharged within a day.

Scaling these initiatives could go a long way to preventing additional demand from avoidable complexity, as the elective challenge remains a national priority. As one lead surgeon involved continues to stress, the principle of this is simple: Treating the right patient, in the right place, and at the right time.

Most Popular Now

AI in Personalized Cancer Medicine: New …

The application of AI in precision oncology has so far been largely confined to the development of new drugs and had only limited impact on the personalisation of therapies. New...

AI can Predict Brain Cancer Patients…

Artificial Intelligence (AI) can predict whether adult patients with brain cancer will survive more than eight months after receiving radiotherapy treatment. The use of the AI to successfully predict patient outcomes...

Max Planck Institute for Informatics and…

The Max Planck Institute for Informatics and Google deepen their strategic research partnership. With additional financial support from the U.S. IT company, the "Saarbr├╝cken Research Center for Visual Computing, Interaction...

JMIR Medical Informatics Invites Submiss…

JMIR Publications has announced a new section titled, "AI Language Models in Health Care" in JMIR Medical Informatics. This leading peer-reviewed journal is indexed in PubMed and has a unique...

Paper Calls for Patient-First Regulation…

Ever wonder if the latest and greatest artificial intelligence (AI) tool you read about in the morning paper is going to save your life? A new study published in JAMA...

Could ChatGPT Help or Hurt Scientific Re…

Since its introduction to the public in November 2022, ChatGPT, an artificial intelligence system, has substantially grown in use, creating written stories, graphics, art and more with just a short...

Evaluating the Performance of AI-Based L…

A new study evaluates an artificial intelligence (AI)-based algorithm for autocontouring prior to radiotherapy in head and neck cancer. Manual contouring to pinpoint the area of treatment requires significant time...

Making AI a Partner in Neuroscientific D…

The past year has seen major advances in Large Language Models (LLMs) such as ChatGPT. The ability of these models to interpret and produce human text sources (and other sequence...

Chapman Scientists Code ChatGPT to Desig…

Generative artificial intelligence platforms, from ChatGPT to Midjourney, grabbed headlines in 2023. But GenAI can do more than create collaged images and help write emails - it can also design...

DMEA nova Award: Wanted - Visionary Solu…

9 - 11 April 2024, Berlin, Germany. The DMEA nova Award is being presented at DMEA 2024 for the first time. The award honours a digital health startup for an outstanding...

New Digital Therapy Reduces Anxiety and …

A therapist-guided digital cognitive behavioural therapy reduced distress in 89 per cent of participants living with long-term physical health conditions, a new King's College London study finds. Researchers at the Institute...

Europe's Digital Health Industry Me…

9 - 11 April 2024, Berlin, Germany. In just over two months, from 9 to 11 April 2024, DMEA, Europe's leading event for digitalisation of healthcare, will gather digital health experts...