Public Funding for Raiqc Ltd

AI tools have shown promise in being able to analyse medical imaging and aid healthcare professionals with their image interpretation speed and accuracy. However, the uptake of these algorithms by healthcare organisations has been slow for several reasons including: ● Lack of independent clinical testing about the accuracy of the algorithms. ● Lack of training of medical staff in the use of the algorithms which leads to a lack of confidence in the use of algorithms. ● Difficulties in integration of the algorithms with existing hospital IT systems so the tools can be tried before purchase. ● Lack of trust in the real-world performance of the tools. RAIQC Ltd has developed a web-based platform for training of medical staff in image interpretation as well as validation of imaging AI algorithms. Through the project, the company aims to further develop their platform into an end-to-end solution for training, testing and deploying AI algorithms that will: ● Allow AI developers to perform _in silico_ clinical trials to generate evidence around the efficacy, usability and health economic value of their AI tools. ● Train medical staff in the safe and appropriate use of AI in medical image interpretation ● Make it easier for hospitals to trial algorithms without the requirement of full integration with the existing hospital systems. ● Monitor the real-world performance of AI tools after they have been deployed in the clinical environments including their accuracy in different diseases, patient demographics and scanner types. During Phase I of the project, a consortium of AI developers, NHS Trusts, clinicians and academics was put together which will work together to define the technical and clinical requirements of the platform. RAIQC Ltd will then lead the development of the pre-market evaluation and post market surveillance tools and connect them with the hospital IT systems. Once the tools have been developed, they will be used to test algorithms from AI vendors that are part of the consortium. and build AI has the potential of revolutionising healthcare delivery in the NHS and worldwide by improving diagnostic accuracy and increasing productivity. The outputs of the project will help develop trust in AI and in turn accelerate their adoption into clinical practice.

AI tools have shown promise in being able to evaluate medical imaging and aid healthcare professionals with their image interpretation speed and accuracy. However, the uptake of these algorithms by healthcare organisations has been slow for a number of reasons. Primary among this has been a lack of trust in the performance of algorithms. Before making a purchase decision, clinicians want to try algorithms to test their usability and accuracy. This requires integrating algorithms with live clinical IT systems which needs input from technical and information governance teams at the hospitals and is a major barrier to implementation. Moreover, after purchase, there is a requirement for staff to be trained in how touse the algorithms. The project aims to improve NHS diagnostic pathways by accelerating adoption of artificial intelligence (AI) for medical image interpretation. To do this, RAIQC Ltd aims to develop a cloud-based platform that acts as an an end-to-end solution for training, testing and deploying AI algorithms. Using this platform, AI developers will be able to perform _insilico_ clinical trials to generate evidence around the efficacy, usability and health economic value of their AI tools. The platform will also allow healthcare providers to trial algorithms prior to deploying them into clinical practice as well as being able to train their staff in safe use of these tools. During phase 1 of the project, RAIQC Ltd will bring together a consortium of commercial AI developers, academic organisations and end users of medical imaging AI such as hospitals and healthcare professionals. The group will be able to outline needs of each stakeholder in the development and translation of medical imaging AI into clinical practice. RAIQC Ltd will also work with the stakeholders to define the technical requirements for each stage of the AI development and deployment pathway.

Studies from around the world have shown that medical imaging studies such as Chest X-ray and CT scans have a high accuracy in detecting lung changes related to Covid-19\. Unlike the lab based diagnostic techniques which are in shortage world-wide and require at least a few hours to process, imaging investigations are widely available and provide immediate results. In addition to aiding diagnosis, imaging is also used to assess disease severity, identify other underlying lung conditions and monitor disease progression. It also plays a key in providing alternative causes for the patient's symptoms such as pneumonia, heart failure or pulmonary embolism (blood clot in the lung) which are potentially life-threatening conditions that would require a different treatment. However, the accuracy of the diagnosis relies on the ability of the image interpreter to be able to recognise the features of Covid-19 on the imaging study. We propose creating a web-based training and simulation tools that can be used to quickly train a large number of individuals including physicians, junior doctors, radiographers and nurses to recognise the imaging features of Covid-19 to aid with its diagnosis and management. The extension for impact funding will allow us to expand the impact of the beyond the current pandemic. The technical development carried out during the original project gives the platform the ability to host educational material related to other disease areas such as cancer, stroke and trauma. Therefore it can be used to train healthcare staff and act as a standardised quality assessment tool reducing variation in practice and potential for patient harm. It will provide benchmarking at a national level to help address concerns over standards. Additionally, the tool will allow a wider workforce to be trained allowing quicker diagnosis of time critical diseases such as cancer while saving outsourcing costs for NHS which totalled £165milion in 2018.