Variation in COVID-19 care and outcomes between hospitals now understood

Using our established systems which risk-adjust for the case-mix of patients and their comorbidities, C2-Ai’s regular detailed analysis across multiple hospitals in our global network (inc. in the UK) has identified:

  • Major variations in Covid-19 care between hospitals
  • The factors that most influence patient outcomes

Cambridge-based C2-Ai, one of ‘10 Essential Digital Health Ideas for COVID-19’ - Healthcare UK, has award- winning systems that benchmark individual and Trust performance, built around 140m records from 46 countries.

We are approaching you prior to publication of our findings to drive your region forward and help position the NHS and British innovation at the forefront of effective COVID-19 management internationally. We propose:

  • An immediate wider deployment of this validated system that is already providing accurate analysis of hospital COVID-19 performance, outcomes and issues - with deliverable solutions and the benefit of supporting a comprehensive plan to have the NHS insulated from the worst of ‘Wave 2’. No integration required.
  • Immediate tactical deployment of approved, rapid triage tools that free up to 20% of CCU capacity, can reduce deaths by 500 and save £7m per hospital (‘phenomenal and works incredibly fast’ – NHS Consultant).


  1. Raw hospital mortality rates for Covid-19 (which may vary from 20% to 40%+) do not reflect the underlying case-mix of patients treated, how seriously ill they are on admission and other conditions they may have. This makes it impossible to understand variations in performance between hospitals, identify those that are managing Covid-19 most effectively (and why), and drive down mortality and harm.
  2. C2-Ai award-winning systems resolve this challenge - uniquely reporting patient-level, risk-adjusted outcomes in hospital care, identifying best practice, problems, root causes and solutions. Today’s standard hospital reporting has been shown to provide visibility on as little as 10% of the issues we track.
  3. Detailed findings across our NHS and other partner hospitals to date have confirmed specific areas of concern linked to mortality while also dispelling some myths.
  4. This is not a new idea or a request for data. The systems have been delivering in 11 countries for 10 years, including the US and NHS. They have been used for detailed analysis and surveillance nationally e.g. by Sir Bruce Keogh and Sir Mike Richards.
  5. We have the largest patient dataset in the World (140m records from 46 countries), have the highest access to NHS Digital Data already and have spent years developing and validating these unique solutions with hospitals like Imperial and Karolinska.
  6. C2-AI has featured on BBC News, was presented with the COGX Overall COVID-19 Innovation and Health Innovation Awards by the SofS - DCMS, is ‘leading the way in the UK's cutting edge, health tech sector’ (Graham Stuart in the Commons) and is one of ‘Healthcare’s Most Innovative Companies’ (US media).


  • Almost immediate delivery of a regional comparative analysis (with access to the latest data) supporting
    effective strategic planning and risk mitigation to get the NHS acute sector wave-2 ready - highlighting evidence-based best practice, hospitals needing the greatest support and specific underlying performance issues.
  • This can be combined with instant-access digital tools deployed to front line hospital staff to enhance their ability to address and manage issues that are emerging as critical in reducing Covid-19 mortality.



It is critical to quickly identify those hospitals that have managed Covid-19 most effectively (and why), along with hospitals that have had difficulties, the reasons for this and the support they will need to cope with further waves of the virus, in order to drive down mortality and harm overall.

CRAB OBSERVATORY resolves this challenge – and provides insights across almost the entirety of inpatient care.

It provides, risk-adjusted, horizon scanning for system-wide patterns & trends in avoidable harm and variation built around tracking 146 surgical complications, 32 triggers of avoidable harm, 16 maternity metrics and unique Covid-19 mortality metrics.

Full profile of each hospital to identify major clinical risk areas, financial efficiency and resource capacity outliers, as well as Covid-19 performance:

  • Risk adjusted surgical deaths and complications at specialty level
  • Overall incidence of avoidable harm and key triggers (AKI, HAP, sepsis etc)
  • Quarterly tracking for meaningful trends and seasonal variations
  • Route map for smart, targeted inspection
  • Mirrored by smart, targeted quality improvement interventions to reduce variation and unnecessary
  • Track impact in real time and replicate winning interventions.

2. C2-AI Overview

Our mission is to create the best possible value in hospital care, by providing the analytics and tools for every hospital to improve outcomes for patients in a way that also releases capacity and cost savings.

Hospitals exist to save lives and make people better - and they need to do so in a way that is as cost effective as possible. This should be the fundamental metric of hospital performance around the world - but no one has been able to do it until now. If every patient was the same and had the same treatments, it would be easy to measure and compare performance. But they are not.

Every patient has different health issues and different care needs and every hospital has a unique blend of services, staffing, and processes. Our systems strip out all those contextual differences to get a clear, risk-adjusted picture or what’s going well (objectively reinforcing reputations for high-performing hospitals with global benchmarking) and also what’s going wrong, where, and why. We can then also provide straightforward solutions - including a suite of simple smartphone tools - for front-line clinicians to make improvements.

The easiest analogy is to an MRI scanner: our systems carry out the MRI scan of a health system. It takes a series of precise, scientific slices of the organisation at every level to pinpoint best practice, and also where the problems are. It’s also picking up the myriad, often low-grade avoidable harms occurring day to day which are routinely overlooked by standard Business intelligence systems, but which collectively add up to significant wastage running to billions of pounds and significant capacity lost.

But you can’t fix it if you can’t see it. We’ve worked with hospitals around the world, and even the best performers in the US that had been on a decades-long journeys to high reliability healthcare found that they were only picking up 10% of what C2-Ai can show. So, there is a lot of the iceberg under the surface, and therefore also a huge opportunity to make things better - for patients and economically. We’re typically finding millions in savings per hospital per year. And we can do so in any country, in any scenario - including the latest challenges created by COVID.

We have created what we believe is the world’s most clinically robust, accurate, risk-adjusted analysis of hospital performance in managing COVID-19 patients and have won a series of awards this year for what we do.

Our work is backed up by over30 years of research, led by world experts (including – Mr Graham Copeland – former Audit Tsar for NHS England and who has advised governments around the world, and algorithms underpinned by the world’s largest referential data set of its kind spanning 46 countries.

We are also delighted to have testimonials from senior clinicians around the world in support of C2-Ai’s systems.

Finally: this is not a massive EMR-style IT project that takes years and millions of pounds. Our systems run on off-the shelf data, require no integration at all, and so we can be up and running in as little as 2-4 weeks.


Named by Healthcare UK as one of "10 Essential Digital Health Ideas for a COVID-19 UK National Response"

Healthcare UK refer to C2-Ai as an 'Essential Digital Health Solution

Referenced in parliament - "Leading the way in the UK's cutting edge, health tech sector"

Winners | COGX Best Covid-19 Health Innovation at COGX 2020

Winners at COGX2020 AI and Emerging Technology Summit as Best Overall Innovation for Covid-19 – presented by the Secretary of State (DCMS) – Oliver Dowden

Featured on BBC News / BBC Click (July 2020)

Winner of Health Tech Digital Innovation for Covid-19 Award

Named by Healthcare UK as a "Top 100 Digital Health Company" in the elite ‘essential’ category

Health Efficiency Innovation Finalist in HTN (Oct 2020 announcement)


Companies like Cambridge-based C2-AI, which last week won the COGX Health Innovation for COVID-19 Award, are leading the way in the UK's cutting edge, health tech sector. C2-AI save lives by predicting avoidable harm and mortality, so they free up capacity in intensive care units for COVID-19 patients.

Government minister Graham Stuart in the House of Commons, UK Parliament June 2020
"C2-Ai have the most robust software approach to comparing safety and quality across hospitals, systems and physicians that I have ever seen. The algorithms are backed up by years of published international research. I believe their approach could be most useful as a solution for providers across any network”.
James Bonnette, MD (USA), Executive Vice President, the Advisory Board
“I’m often asked about artificial intelligence (AI) in the UK. When I do I always point to C2-AI - saving lives all over the planet by predicting avoidable harm and mortality with world-leading AI based on a dataset of 140 million patients from 46 countries. They are globally unique, innovative, British award-winners. I consider them to be essential for any nation which wants to take digital health seriously.
If their innovation was scaled across the NHS I estimate it would save 70,000 lives and £1bn.”
Hassan Chaudhury, Digital Health Lead at Healthcare UK

“It took 2 years and a very costly investigation to deal with a competence issue in our organization some time ago. We set C2-Ai the blind challenge of seeing if they could have found the problem in our historical data. They did so in 20 minutes. Needless to say, we have invested in the system”
Dr. Michael Roberts, Chief Medical Officer, Northland District Health Board, New Zealand
“I have used Compass [pre-operative, risk assessment] tool for about one year and I am very pleased with the level of information that it provides. It also helps with the decision-making process when we consider fracture neck of femur surgery. Indeed, we had a couple of cases when we decided to postpone the surgery to optimise the patient based on the results we had on Compass.”
Dr. Bozena Lassota-Korba, Consultant Anaesthetist, Yeovil District Hospital NHS Foundation Trust
“C2-Ai can identify outcomes that are better than expected, as well as those that are worse, and thus can be used as an improvement tool as well as to assure clinicians and others of the standard of care being provided, and to measure productivity”
Professor the Lord Darzi, PC, KBE, FRS, FMEDSCI, HONFRENG, Currently Director of the Institute of Global Health Innovation at Imperial College London, Chair of Surgery at Imperial College London, the Royal Marsden Hospital and the Institute of Cancer Research
“I’ve been trialling the new C2-Ai App for AKI & HAP, both of which are phenomenal and work incredibly fast...delighted and excited as to how this tool can help us identify these patients early and put in place simple measures, which all have a significant impact”.
Sunjay Kanwar, Consultant General Surgeon, St Helen’s & Knowsley Teaching Hospitals NHS Trust, UK
“CRAB just makes sense. It presents data in a way that is easy to understand and interpret. It has been immensely useful for me both personally in my appraisal and in my role as a Clinical Director. It helps me to pick up early warning of problems with intelligence that can be believed and acted upon”
Jeremy Cundall, Executive Medical Director - Consultant Colorectal and General Surgeon, CDDFT
“CRAB® is 100% better than any solution available to us at the moment. It has turned out to be a very useful tool in analysing and understanding our case-mix and where our complications are occurring.”
Per Svedmark MD, PhD, Senior Consultant, Stockholm Spine Centre, Sweden
“CRAB® is generating trusted data which we can use to flag up areas of concern. From there we are able to take action in a much more sophisticated way than we have in the past.”
Dr. Timothy Ho, Medical Director, Frimley Health NHS Foundation Trust, UK
We are thrilled to receive this [Patient Safety] award, which reflects a great deal of hard work and support from within and [...] the support of C2-Ai who enabled us to benchmark our Trust’s Acute Kidney Injury rates against national levels - and then measure the significant impact of our AKI Programme, which coincided with a significant and sustained fall in AKI rates our Trust, especially across surgical wards”.
Dr Jonathan Murray, Renal Consultant at South Tees Hospitals NHS Foundation Trust, UK
“Accurate benchmarking of outcomes was a real challenge [...] however our work with [C2-Ai] has provided invaluable quality assurance. The risk adjusted reporting has provided confidence that our outcomes are better than comparable organisations and the level of detail enables us to focus on improvements in specific areas. It was particularly useful during our regulatory inspection and follow up meetings with the CQC to show how this strengthens our clinical governance...”
Dr Jenny Davidson, Director of Governance, King Edward VII’s Hospital.
"CRAB® predictions have proved accurate in my primary external research validation of the system. I currently don’t know of any other electronic system in use that can deliver this kind of overall and detailed qualitative feedback to the department and the individual surgeon. It has been a great benefit for our clinic and helped develop our work on patient safety.”
Wilhelmina Ekström, MD, PhD, Senior Consultant, Karolinska University Hospital, Sweden
“The problem with [HSMR systems] is that they tell you there might be a problem, but not where or why. CRAB® tells you exactly what and where the problem is, and even which patients are involved. Then you can do something about it.”
Dr. Aresh Anwar, Medical Director, Royal Perth Hospital, Australia
“CRAB has allowed real time review of data, which has raised awareness and led to change in both clinical practice and hospital culture. I think it will become an essential part of the appraisal and governance structures of secondary care.”
David Williams, Consultant Surgeon, Northern Devon Hospital Trust, UK
“It is strikingly clear to me that you know more about how to fix this hospital than I do”
Chief Medical Officer, Nashville based US health system

5. Usage by national authorities and formal review bodies

The CRAB system has been used in a number of reviews, including the significant Keogh Review in 2013. Sir Bruce Keogh and Sir Mike Richards (former head of inspectorate at the CQC) are supporters of our approach and the insights/improvements they enable.

From the Keogh Review1 where C2-AI’s CRAB system was used for the detailed analysis at a hospital level...

6.3 Conclusion My overall conclusion is that these reviews have found problems and areas for improvement that other reviews have missed. This model of review – based around a clear trigger for action; skilled data analysis leading to Key Lines of Enquiry, rather than inspection against a pre-determined framework; intensive visits to hospitals by experienced, multi-disciplinary teams; talking in-depth to patients and staff – works well. It should inform the way in which all hospital reviews and inspections are carried out in future.

1Review into the quality of care and treatment provided by 14 hospital trusts in England: overview report Professor Sir Bruce Keogh KBE

Get in touch

Contact us today with any questions! We’re here to help .

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.