Artificial intelligence-supported early fracture diagnosis: SBRI competition
Organisations can apply for a share of £240,000, including VAT, to develop an innovative AI solution for radiological diagnosis of fractures of upper and/or lower limbs.
- Competition opens: Monday 20 May 2019
- Registration closes: Wednesday 24 July 2019 12:00pm
This competition is now closed.
This is a Small Business Research Initiative (SBRI) competition funded by Opportunity North East and NHS Scotland. Successful applicants will receive 100% funding and have access to advice from NHS Grampian, NHS Greater Glasgow and Clyde (NHSGGC), the University of Aberdeen, the Canon Medical Research Europe and the funders.
The overall programme will be delivered in 2 phases. A decision to proceed with phase 2 will depend on the outcomes from phase 1. Only successful applicants from phase 1 will be able to apply to take part in phase 2.
NHS Scotland and Opportunity North East (ONE) are investing up to £240,000, including VAT, in innovative data analytics technology. The aim is to improve front-line clinical decision making and patient management in unscheduled care facilities.
The solution will improve clinical workflow and safety by optimising clinical decision making and management pathways. It must use artificial intelligence (AI) or machine learning algorithms to interpret data from upper limb (wrist or hand) and lower limb (ankle or foot) radiographs and linked text-based reports. Accurate determination of the presence or absence of a fracture in these areas has the potential to significantly improve patient care.
Phase 1 research and development contracts will be focused on feasibility studies. Phase 2 contracts will be prototype development and testing.
The competition has 2 phases. Up to £100,000, including VAT, is allocated for phase 1 and up to £140,000, including VAT, for phase 2.
Who can apply
To lead a project, you can:
- be an organisation of any size
- work alone or with others from business, the research base or the third sector as subcontractors
Phase 1 projects must start by October 2019 and last up to 3 months.
It is anticipated that the feasibility study R&D contracts will be in the region of up to £20,000, including VAT. This is for each project for up to 3 months. We expect to fund up to 5 projects. The assessors will consider fair value in making their evaluation.
We would welcome bids that bring together a consortium of sector specialists.
In phase 1, you must:
- demonstrate the technical feasibility of your proposed innovation
- establish ongoing collaboration between technical and clinical members of the project team
- formalise any required ethical approvals, data sharing agreements and contracts
- begin working with clinical and imaging data
Phase 2 projects must last up to 9 months.
Only applicants who complete phase 1 can apply for funding to progress into phase 2. If your application is successful, you must:
- develop and evaluate a prototype of your solution
- test the prototype on real-world data and systems within NHS Grampian to establish clinical utility
- develop a plan for full commercial exploitation
NHS Scotland and Opportunity North East have allocated up to £240,000, including VAT, to fund projects in this competition. There are 2 phases. Up to £100,000, including VAT, is allocated for phase 1 and up to £140,000, including VAT, for phase 2.
Applications must have at least 50% of the contract value attributed directly and exclusively for R&D services. R&D can cover solution exploration and design. It can also include prototyping and field-testing the product or service. R&D does not include:
- commercial development activities such as quantity production
- supply to establish commercial viability or to recover R&D costs
- integration, customisation or incremental adaptations and improvements to existing products or processes
The total funding available for the competition can change. The funders have the right to:
- adjust the provisional funding allocations between the phases
- apply a ‘portfolio’ approach
The challenge is to develop an AI or machine-based learning programme that can help healthcare organisations accurately identify whether a patient has a fracture. This is initially a classification problem (by assigning a value of yes, no or maybe).
In simple terms, the task to begin with is to develop an automatic system that, with a degree of certainty, can remove from clinicians’ workload those that are definitely yes or no, leaving them to focus on the more complex images. This is an initial step towards integrating AI systems into a mainstream clinical workflow within the NHS and could be a platform for building more intelligent learning systems.
Each year in Scotland, the NHS gives some 5,000 patients x-rays of the peripheral upper limb (wrist or hand) and lower limb (ankle or foot), most often looking for a fracture after trauma. Although isolated injuries in these areas are often categorised as ‘minor’, misdiagnosis and consequent mismanagement can result in significant morbidity and financial cost.
The interpretation of peripheral limb x-rays is the remit of a wide variety of clinical staff in many clinical settings, from large urban emergency departments to nurse-led remote cottage hospitals and minor injury units.
The diagnosis of a fracture in the wrist or ankle is made from 2 standard radiographic views taken at right angles to each other. Radiographic fracture assessment of the hand or foot may include a third oblique view.
Recently published studies have successfully used machine learning to analyse radiographs to detect fractures. They have shown the ability to perform at the same diagnostic standard as an expert.
AI or machine learning could be included in clinical workflows to interpret peripheral limb radiographs for the presence of fractures, which in most cases are not reported for several days. This would help:
- improve diagnostic accuracy and treatment
- improve patient pathways and outcomes
- reduce the growing deficit between radiology reporting workloads and staffing levels
This competition draws on Scotland’s expertise in:
- clinical and academic digital radiology
- advanced data storage
- data governance and access
- interoperable healthcare databases
John Doe has a swollen right wrist after falling on an outstretched hand in the street. He lives in a rural location and attends his local minor injury unit where he is seen by a nurse who requests x-rays.
The films are placed on a digital archiving system but both the nurse and the radiographer are unsure if there is a fracture. Mr Doe is keen to get back to his activities, including driving. The staff decide to let him keep his wrist free but say they will contact him if an abnormality is found on the formal radiology report. After 4 weeks the formal radiology report shows there was a fracture. Mr Doe is recalled and given more x-rays. They show the bones have moved and he will need an operation.
The initial reading of the radiology image is made by a variety of grades of staff with wide experience. While local departments often have safeguard systems to minimise risk, some fractures have a delayed diagnosis. Peripheral limb injuries may have significant morbidity and often financial or lifestyle implications.Example: in 2020
Following the application of machine learning, John Doe’s x-ray is displayed to the clinician with an augmented image highlighting the presence of a fracture or abnormality. The clinician can use this information alongside other clinical details and, if necessary, seek a specialist review.
If no fracture is found, patient management is simpler as the films do not have to go for formal radiology reporting.
This real-time system of augmentation has:
- significantly and reliably improved the confidence the patient and the clinician have in the diagnosis of ‘no fracture’
- reduced the number of specialist consultations for patients with a suspected fracture who do not have a fracture
- sizeably and safely reduced radiology reporting, letting the department concentrate on more complex image interpretation
Successful applicants must use an available dataset of peripheral limb x-rays and linked text-based reports from the University of Aberdeen’s accredited secure Grampian Data Safe Haven (DaSH). With these they will develop AI algorithms to:
- interpret the existing text-based report to categorise as fracture or no fracture
- interpret the radiograph image to identify the presence of fracture
- develop an AI product with the required level of real world accuracy to enhance to enhance radiology image interpretation in mainstream clinical practice
The competition is looking for proposals that:
- improve peripheral limb fracture detection by non-radiology experts in out of hours environments within NHS Grampian
- transform peripheral limb injury clinical pathways to improve patient outcomes and increase productivity by at least 20%
- use the relevant NHS, academic and commercial expertise, data and infrastructure offered by Grampian
- have clinical and commercial potential locally, nationally and globally
We are looking for industrial innovators. You must confidently collaborate and use multiple data sources to develop clinically relevant and commercially practicable solutions. There is potential to commercialise outputs directly through NHS Scotland and globally through the sales and marketing channels of Canon Medical.
Any adoption and implementation of a solution from this SBRI competition would be the subject of a separate, possible competitive, procurement exercise. This competition only covers R&D not the purchase of any solution.
The performance of models trained on the dataset that is made available during the programme will be validated against an unseen dataset. There will be a further dataset available to demonstrate generalisability.
In phase 1 you must work closely with the stakeholders to develop a solution. In phase 2 the outcome of your project will be a prototype of the solution.
Phase 1: technical feasibility studies
This means planned research or critical investigation to gain new knowledge and skills for developing new products, processes or services.
Phase 2: prototype development and evaluation
This can include prototyping, demonstrating, piloting, testing and validation of new or improved products, processes or services in environments representative of real-life operating conditions. The primary objective is to make further technical improvements on products, processes or services that are not substantially set.
- 20 May 2019
- Competition opens
- 27 June 2019
- Briefing event. Sign up by 21 June
- 24 July 2019 12:00pm
- Registration closes
- 31 July 2019 12:00pm
- Competition closes
- 4 October 2019
- Feedback and phase 1 contracts awarded.
Before you start
- register online using the green button
- read the guidance for applicants for this competition
- consider attending one of the briefing events listed in ‘Dates’
- complete and upload your online application to our secure server
We will not accept late submissions. Your application is confidential.A selected panel of experts will assess the quality your application. Please use Microsoft Word for the application form or it will be ineligible.
Background and further information
Diagnostic imaging is an essential, central component in delivery of safe modern medical care, confirming or excluding a diagnosis. As part of the growing diagnostic services it is quickly evolving, driven largely by technological developments and delivering significant improvements to patient care.
This improved care potential is halted by the worldwide shortage of radiologists and radiographers needed to cope with the expansion. In Scotland, 8% of consultant radiologist posts are unfilled and 19% of the current workforce are due to retire in the next 5 years.
The increasing demands placed on our radiology service and reduced in-house workforce have led to many hospitals across the world outsourcing radiology reporting to external private agencies in their country or abroad. In 2014, the outsourcing bill for Scotland was estimated to cost NHS Scotland £5.25 million. Although less than 1% of this cost relates to wrist and ankle reporting there is an expectation that using AI to review the large number of images relating to wrist and ankle fracture will free up clinical time that can be redirected to other areas.
The radiology report is a critical and legally required component of the patient health record. All referrals for radiology which result in an examination must be read by a radiologist or a qualified radiographer. Their interpretation of the diagnostic image can be written in many styles, as would be expected from human writing. The complexity of reporting and consequent effort for the radiologist is variable, from highly intricate multimodality imaging with hundreds, if not thousands of scan slices, to single image radiography.Industrial context
With Edinburgh-based Canon Medical Research Europe we are developing the Safe Haven Artificial Intelligence Platform (SHAIP), which will be deployed in NHS data safe havens from 2019. By locating appropriate hardware and software to support AI training in-situ, SHAIP adopts the approach of “bringing the algorithm to the data” rather than “bringing the data to the algorithm”. This will support a federated approach to training AI whilst ensuring identifiable patient data stays inside the NHS. It will let micro, small and medium-sized enterprises (SMEs) work closely with clinicians at a local level.
Scotland’s national infrastructure will support this competition in Aberdeen. Applicants can draw on the newly formed Industrial Centre for Artificial Intelligence Research in Digital Diagnostics (iCAIRD), which comprises NHS Grampian, NHS Greater Glasgow and Clyde, the universities of Aberdeen, Glasgow, St Andrews and Edinburgh, major industrial sponsors Canon and Philips, and several partner SMEs.
iCAIRD adopts an ethical framework based on current best practice within Health Data Research UK (HDRUK). This ensures patient data is securely held within the NHS whilst enabling companies, researchers and clinicians to work together to develop more effective and efficient diagnostic tools for patients.
Competition funder ONE is developing a Digital Hub in central Aberdeen and a Biotherapeutic Hub for Innovation within the Foresterhill medical campus at the University of Aberdeen. Innovative businesses in the north-east can access business support programmes linked to the hubs to help with start-up and growth. The hub aims to help SMEs work on healthcare challenges through the development of an Accelerator Programme. It will provide access to expertise on regulations and help find a route to market for our partner companies, creating economic growth and patient benefits. Successful applicants will have the opportunity to link into the programmes and support offered through these innovation hubs.
About SBRI competitions
SBRI provides innovative solutions to challenges faced by the public sector. This can lead to better public services and improved efficiency and effectiveness. SBRI supports economic growth and enables the development of innovative products and services. It does this through the public procurement of research and development (R&D). SBRI generates new business opportunities for companies and provides a route to market for their ideas. It also bridges the seed funding gap experienced by many early-stage companies.
Further help and information
You can find information on how to enter this competition in the invitation to tender document, which is available for download on our secure site after registration.
Questions related to this competition should be addressed directly to email@example.com.
You can watch a video by NHS consultant Jamie Cooper outlining the competition brief.
A LinkedIn group has been set up for this competition. Presentations and a transcript of the Q&A from the launch event are available on the LinkedIn page, which can also be used to seek partners and establish collaborations.
If you want help to find a project partner, contact the Knowledge Transfer Network or Scottish Enterprise.If you need more information, email firstname.lastname@example.org or call the competition helpline on 0300 321 4357.
Need help with this service? Contact us