C2-AI a software group for ORSafety

Harris Unit Calculations for Orsafe.pdf

What are C2 Ai and what do they do?

C2-AI is a leading clinical analytics software company based in Cambridge UK (www.c2-ai.com)

C2-Ai provides globally unique (according to various governments around the World) Ai-backed systems that help hospitals to demonstrably reduce avoidable harm, mortality and variation.  We do this while generating significant savings on operating expenditure (potentially USD millions per hospital) and reducing complaints/clinical negligence claims by up to 10%.

Saving lives, reducing harm and lowering costs

Hospitals exist to save lives, make people better and not make them worse. These fundamental outcomes should be the primary focus of what is measured.  However, hospitals have not been able to measure these outcomes with existing information systems, as they cannot and do not measure them in a sophisticated and meaningful way.

This is the challenge we have overcome.

C2-Ai systems deliver unique insights by objectively and accurately risk adjusting for each patient and can tell which hospitals, specialties, consultants etc are doing well (given their specific case-mix), where the hospital has issues for mortality and complications, avoidable harm and variation, what the causes are, their economic impact.

We can then provide recommendations and tools for resolving any problems, with forward-looking applications to triage and manage patients more effectively, thereby optimising outcomes and cost-effectiveness.

This means we help improvement teams and activities focus where problems really exist (as opposed to the false positives of more simplistic approaches) and deliver the information on the financial and care impact of resolving these problems.  

Moreover, we also identify good practice – providing the opportunity to share this across other specialties/hospitals, and to promote hospitals that are doing well with an objective, international benchmark.

We have been quietly developing and validating these systems for more than 10 years.  We have delivered our expert system to dozens of hospitals in 11 countries around the world and we have the world’s largest referential dataset of its kind, spanning 30 years, 46 countries and 120 million records.

Every year our client Hospitals treat millions of patients, saving thousands of lives and ensuring that hundreds of thousands have better outcomes that will last a lifetime. We do this while saving our clients hundreds of millions of dollars in operational costs, unwarranted practice variation and litigation fees.

Extrapolating from the improvements in our NHS hospitals in the UK, a full NHS deployment would save around 5,500 lives and nearly $1bn annually.  

Our retrospective reporting system is transformative but not disruptive, as we take the feed of clinical coding data already created for each patient on discharge. No extra resources are required, and no workflows change in the slightest.  This means implementing the systems in hospitals is simple and fast.

We work with…

C2-Ai established itself by working with high reputation organisations - such as Imperial Healthcare and Guys & St. Thomas’ Hospital in London. We work with the Karolinska University Hospital in Stockholm, who have remained with us for years as we continue to add value for their governance, safety and quality improvement, as well as helping them to understand how they can make quality based savings and provide true value-based care. More recently, we have been brought in by King Edward VII hospital, which treats the Royal Family.

Our reputation spread by personal recommendation and we were, as a result, taken up by Sir Bruce Keogh to provide the detailed root cause analysis and key lines of enquiry for his national review of high mortality hospitals for the NHS. And subsequently by Sir Mike Richards to provide national level reporting on avoidable harm for the Care Quality Commission (Hospital Inspectorate).

For these reasons, we have also been asked to perform due diligence investigations for a range of mergers and acquisitions in the UK and in the US. We provide valuable and actionable insights to help an acquiring organisation uniquely improve the bottom line of the acquired hospitals, and then accrue these financial and care benefits faster and with less disruption than would otherwise be possible. By looking across all hospitals, we help logically prioritise which issues to tackle first on an accurate and evidentiary basis. Detailed monthly/quarterly reports and an expert system then allow improvements to be tracked over time, so this is a closed loop.

We are the only company in the world to be able to do this: we have been assessed as unique in the market by authorities and governments around the world.

"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) - EVP, the Advisory Board

“[C2-Ai] 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

“Accurate benchmarking of outcomes was a real challenge to us as an independent hospital with limited access to big data sets, however our work with CRAB analytics 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 and contributes to our ‘effective’ and ‘well led’ domains”

Dr. Jenny Davidson, Director of Governance, King Edward VII Hospital, London

The C2-AI software offers two programs that will save the average hospital 1.5 million dollars per year through implantation solutions using “Crab and Compass”. Safety for users and patients alike are indeed quantifiable.

The Software solution is based on 140 million patients in a proprietary database, gleaned from 146 countries submitted over a 10 plus year period of time.

“We have empirical evidence showing how we can: save money, reduce mortality and reduce morbidity through our retrospective auditing tool: CRAB.” A once a month report is generated highlighting clinical variations of outcomes and reducing those variations of outcomes by 90%. These reports allow you to intervene and correct courses of action resulting in savings.

Avoidable harm reports are key and in particular AKI (acute Kidney injuries) in the hospital along with HAP (hospital acquired pneumonia) are reduced by ½ on average. The data to support this conclusion is readily available.

COMPASS, the second solution allows hospitals to improve outcomes and avoid AKI and HAP issues going forward. This system is a Surgical Triage System that not only warns of potential complications based on a number of variables related to the patient’s current pre-op condition but also offer Risk Assessment as a tool to determine the best course of action going forward. Further the analysis is excellent as an ‘informed consent tool’ to allow the patient insight into what is expected from the procedure and how he/she can influence outcomes positively.

Reduction of Variations, Avoidable Harm and certainly reduced mortality and morbidity are an outcome of implementation of the software packages. The savings per hospital is over 1 million dollars and the savings in being able to free beds to meet COVID-19 onslaughts are demonstrably evident.

Increasing bed space availability in light of Covid-19 reduces pressure on a system already overtaxed; while reducing morbidity and mortality is a positive for both patients and hospital systems.

Safety 2:  C2-AI.net is new to the US marketplace offering significant savings and improved safety for both Staff and Patients. While known in Europe with support from the U.K.’s National Health System and Karolinska University Hospital in Stockholm, Sweden, few US Institutions are aware of their existence nor understand the impact on safety and costs this company offers. The following piece was submitted by C2-AI as a introductory paper on the impact they can have on any Institution wishing to increase safety while reducing costs. Any comments welcome, or certainly directly to www.c2-ai.net.

“Why measuring surgeons frequently gets the wrong results…and leads to harm and mortality”

What gets measured gets improved. That’s what quality professionals say. However, that requires the ability to measure performance in a meaningful way and this is a problem in hospitals, and particularly with surgery.  Unlike in a manufacturing process, these issues have serious financial and human consequences.  Simply put, how we measure performance in US hospitals is leading to unfair judgements about the quality of surgeons, and also to avoidable harm and mortality.

“At least one in three heart surgeons has refused to treat critically ill patients because they are worried it will affect their mortality ratings if things go wrong.”


The 2016 report in the Daily Telegraph (quoted above) found that one in three heart surgeons was avoiding high risk patients because of the way they are measured.  That is true for both mortality and complications, as both are typically judged on a ‘percentage of procedures’ basis.

It’s not isolated to just cardiac surgery by any means. Surgeons that dedicate their lives to saving others are acting against their nature because of a system of measurement that punishes them for caring for the most vulnerable or highest-risk patients. These are the patients that need them the most.  If hospitals can’t accurately risk-adjust to the difficultly presented by a patient and their prospective procedure/surgery, how can they make the best care improvements and decisions for their patients?

So, what’s the problem?

Simple statistical approaches, widely used in hospitals, are good for providing pretty pictures and a false sense of security. They are deeply flawed. Measuring mortality as a percentage of admissions does not consider any differences in the case mix of patients from one hospital to the next or how this changes over time.  

Consider hospitals in New York.  The simple mortality percentage will have increased significantly suggesting a drop in performance that does not factor in the impact of the Covid-19 crisis.  That’s an extreme example but measuring mortality and complications as simple percentage of admissions or procedures is similarly flawed.  A UK government report expressly states that metrics [like this] should only be treated as a “smoke alarm” – accepting that these tools deliver significant ‘false positives’.

The ‘traditional’ blunt approach to measurement does not account for any underlying physiological factors of the patient that can increase the risk of mortality and complications.  For example, having low sodium and blood pressure leads to a ten-fold increase in the risk of mortality for patients of the same age and having the same procedure.  Without factoring in these conditions, measuring surgical performance cannot hope to be fair.  
C2-Ai takes a different approach with evidence-based, monthly reporting that shows clearly how the hospital is doing and where issues may be developing.  The systems uniquely, objectively and accurately risk adjust for patients and can tell which hospitals, specialties, consultants etc. are doing well (given their specific case-mix), where the hospital has issues for mortality and complications, what the causes are, their economic impact, and how to resolve them.

CASE STUDY:  As an example of how this approach supports accurate, evidence-based measurement of outcomes, a national regulator contacted C2-Ai to look at the case of a suspended neuro-surgeon. He had been suspended because of a high complication rate. Looking at the distribution of his operations against the risk of complications showed an interesting pattern. The other surgeons tended to do fewer operations at the higher risks of complication levels. This surgeon did roughly three times as many in the 90%+ risk of complication bracket than others. He operated on 13 patients and saved 12. Risk-adjusting, his results were actually exceptional  and he was the best surgeon in the local health system, three years running.   The raw complication figures ignored his case-mix. In this case the system would have been down a surgeon for a period and the surgeon’s skills likely eroded during what could have been a suspension of many months.

There is a similar argument for complications/harm as there is for mortality statistics, and there’s certainly more to life than death in considering hospital performance.  In the US, there are sites where you can ‘assess’ performance of surgeons.  ProPublica and Consumers’ Checkbook provide information on the number of procedures and the complication rates but the lack of consideration of the patient’s underlying age, health, etc. will similarly lead to results that do not provide the full picture.


Where’s the problem?

Many issues leading to mortality and complications occur post-operatively.  Why should a surgeon be marked down for an issue that is not under their direct control?   However this happens frequently because

This is part of a broader issue as currently, hospital administrators in US health systems can only identify about 10% of the variation that leads to avoidable costs, harm and mortality. Up to 90% goes undetected by monitoring and reporting systems in a typical hospital and 6 out of 7 instances of variation/harm are undetected even in a system with a reputation for outstanding quality.  These are the issues that C2-AI’s CRAB system can detect, locate within the hospital and help resolve.

So, what should be happening?

In a ‘get it right first time’, ‘do no harm’, healthcare environment, hospital teams should be supported with the right information, not pretty (meaningless) graphs, and should be searching to improve the accuracy and quality of the information they use.

In the context of surgery, the focus should be on measurement of correctly risk-adjusted outcomes that reflect individual physiology of patients, identify issues with mortality and complications and can located where and why they are occurring in the hospital.  

In the era of Covid-19…a three-step road to recovery

There are three distinct phases of care that can be taken to minimise clinical variation, harm and mortality.

1. Managing the non-urgent backlog

In the US, the Center for Disease Control has issued guidelines that ‘facilities should establish a prioritization policy committee ...to develop a prioritization strategy appropriate to the immediate patient needs’. One component of this is ‘objective priority scoring’

COMPASS Surgical List Triage System offers a solution, supporting the return to normalcy as rapidly as possible using automated, evidence-based triage and individualised risk assessment of patients:

  • Built on the extensive research of Graham Copeland, inventor of the POSSUM surgical risk assessment methodology, former patient safety ‘tsar’ in the UK and advisor to the V.A., the American Surgical Association and governments around the world
  • Bulk-loads pre-authorisation information to generate clinical analysis of patients based on their individual risk of mortality and complications and provides a detailed breakdown of most likely complications to inform care pathway decisions

2. Ensure patients are appropriate for surgery

The COMPASS Pre-operative Risk Assessment system provides an evidence-based risk of mortality and complications for a patient built on the type of operation and key physiological variables.  It Incorporates Ai algorithms drawn from the world’s largest international data set (140m records, 46 countries) and support truly informed consent while identifying patients who might benefit from optimisation prior to operating, creating crucial breathing space from operations that can legitimately be deferred.

3. Measure hospital outcomes fairly and objectively

CRAB provides retrospective audit information on 146 surgical complications and 32 triggers of avoidable harm in hospitals, as discussed above.

"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

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.