AI Skunkworks projects

Arranging a student nursing schedule is complex. There are a range of needs which require consideration before a student nursing schedule can be developed. For example, the universities will have set dates when placements should take place. Some universities will require students to visit specific types of wards over the course of their placements, while others may be more flexible.

The Trust has requirements too. Each ward at a hospital has a maximum student hosting capacity, and this can vary depending on the student’s current year of study. Wards must also keep to internal Education Audit Standards to ensure they can provide necessary support to students.

We worked with Imperial College Healthcare NHS Trust, in conjunction with North West London CCGs, to develop an AI-driven solution to this problem.

These cost-free sessions are aimed at individuals within public sector health and care organisations who are interested in understanding and implementing AI. We welcome everyone from clinicians and technology teams to operations and senior stakeholders.

The Digital team at University Hospital Southampton (UHS) approached us with a request to explore the ethical and safety considerations of applying AI in their work. It is especially critical with AI in health and care that the people affected by its use are confident the tools are robust, and any support for decisions is fair for all patients.

One of the challenges for AI development is that without suitable test data it is not possible to properly demonstrate AI tools, preventing users without data access from being able to see the tool in action. However, using real patient data for research and development carries with it safety and privacy concerns about the anonymity of the people behind the information.

In a partnership project, the NHS Transformation Directorate’s Analytics Unit and the NHS AI Lab Skunkworks team sought to further improve an existing synthetic data generation model (called SynthVAE) and develop a framework for generating synthetic data that could be shared for others to re-use.

We worked with the team at the George Eliot Hospital to research how to identify features in a computerised tomography (CT) scan and automatically align their scan "slices" to enable early detection, diagnosis and, later, the treatment of lesions (tissue growth).

Comparing computed tomography (CT) scans is a labour-intensive task and there are no satisfactory automation tools that can speed up the process. Difficulties in aligning scans 100% accurately make it hard for radiologists to accurately measure changes.

The project aimed to support radiologists by comparing two CT scans taken at different dates, to see if a patient has improved or deteriorated. We explored how AI might identify organs and lesions, report the change in size, and highlight areas of concern to the radiologist.

This project investigated whether AI can support hospitals to manage bed occupancy more efficiently in order to benefit both patients and staff. The aim is to enable staff to schedule the best use of beds more quickly, by providing more information to the scheduler and guiding decision-making.

Fewer bed moves can mean a better experience for the patient as well as cost savings for the hospital. The optimisation method approach taken by this project will allow us to put patient welfare first.

This project created a proof of concept system that presents allocation options visually to the ward staff, alongside an explanation of the different factors and reasons involved, employing explainable AI (also known as XAI, which means ensuring a human can understand the path an AI system took to reach its decision). This also makes sure that the medical team are the final decision-makers, with AI playing a supporting role to keep the “human in the loop”.

NHS Resolution provides expertise to the NHS on resolving concerns and disputes. The organisation holds a wealth of historic data around claims, giving insight and valuable data around the causes and impacts of harm.

The NHS Resolution team wanted to understand whether AI methods could be applied to their data to better understand and identify risk, preventing harm and saving valuable resources.

We aimed to prove the value of machine learning in determining insights from the available data. Automated machine learning was used to run repeated processes on the available data in order to select the AI models that uncovered the most relevant information.

Recruitment for an organisation as large as the NHS is a time-consuming and expensive operation. If artificial intelligence can successfully manage bias while improving the speed and efficiency of selection processes, this could lead to fairer opportunities, greater inclusivity and reductions in time and cost.

The project began some research to explore the various existing approaches to using AI to solve this problem, from chat bots to CV screening, and automated decision-making processes to decision-making support tools, looking at the advantages and disadvantages they offer.

This will allow the London Talent team to make an informed decision about what type of solution might be suitable for the NHS, and the possibilities for overcoming bias in this context. We will then use pseudonymised applications for closed job vacancies to train and test a model to see if a solution can be found that accounts for bias. Pseudonymisation separates data from direct identifiers (e.g. name, surname, NHS number) and replaces them with a pseudonym (for example, a reference number), so that identifying an individual from that data is not possible without additional information.

Identification of Parkinson’s Disease is carried out by neuropathologists who analyse post-mortem brain slices. This process is highly time intensive, and the neuropathologists are highly trained in their field. Being able to look at introducing automation to this process has potential to increase the speed at which Parkinson’s Disease can be diagnosed in a brain, as well as freeing up neuropathologists who are otherwise required to spend hours looking at the brain slices themselves.

Many cases of adrenal lesions, known as adrenal incidentalomas, are discovered incidentally on CT scans performed for other medical conditions. These lesions can be malignant, and so early detection is crucial for patients to receive the correct treatment and allow the public health system to target resources efficiently. Traditionally, the detection of adrenal lesions on CT scans relies on manual analysis by radiologists, which can be time-consuming and unsystematic.

The main aim of this study was to examine whether or not using AI can improve the detection of adrenal incidentalomas in CT scans. Previous studies have suggested that AI has the potential in distinguishing different types of adrenal lesions. In this study, we specifically focused on detecting the presence of any type of adrenal lesion in CT scans. To demonstrate this proof-of-concept, we investigated the potential of applying deep learning techniques to predict the likelihood of a CT abdominal scan presenting as ‘normal’ or ‘abnormal’, the latter implying the presence of an adrenal lesion.

Trusted research environments (TREs) take the form of a secure data environment that allows analysts and researchers to undertake in-depth analysis on rich, joined-up datasets without them seeing any identifiable information. Data is held within a secure server and does not leave that server. Following a recommendation from the Goldacre review TREs form a key part of the Data saves lives: reshaping health and social care with data policy paper.

sing TREs for analytical projects is still a new concept to many analysts. The NHS AI Lab Skunkworks team and NHS England’s Health Inequalities and Evaluation Analytics Team embarked on a partnership project to gain experience of using a TRE to answer key and important questions for a defined project. They used a TRE called OpenSAFELY, an open-source software platform for analysis of electronic health care records data for COVID-19 related research.

People with acute kidney injury (AKI) sometimes experience sudden deterioration and need emergency dialysis or intensive care. Current electronic warning systems can alert healthcare staff shortly ahead of deterioration happening, but this project will explore whether artificial intelligence can be used to predict this further ahead.

University Hospitals Leicester (UHL) has access to a large collection of patient observation data that may allow us to find patterns indicating when sudden deterioration might happen, and the factors that enable its prediction. UHL currently use a team of nurses who specialise in evaluating patients for signs of sudden deterioration, but if this data can allow hospitals to automatically identify those patients most at risk at least 24 hours beforehand it will allow medical staff to focus their time on these patients, and potentially prevent the need for admission to the intensive care unit or emergency dialysis.

When you visit your doctor or attend hospital a lot of information is collected about you on computers, including your symptoms, tests, investigations, diagnosis, and treatments. Across the NHS, this represents a huge amount of information that could be used to help us learn how to tailor treatments more accurately for individual patients and to offer them better and safer healthcare. The challenge is that most of the information held within these records is in written form that is difficult to use.

The process of reading health records and applying standardised codes based on particular words, conditions or treatments, is called "clinical coding". The process of clinical coding is time-consuming, expensive and carries the risk of mistakes.

We are providing data science capability to a joint project with the Royal Free Hospital and Kettering General Hospital. This project aims to understand which open source models are best to support clinical coders by automating part of the clinical coding process using natural language processing (NLP) to teach computers to ‘read’ electronic health records. The aim is for the technology to summarise and suggest the standardised codes that will then be checked by clinical coders.

NLP is a branch of AI used to interpret unstructured text data, such as free-text notes.