The hospitals which form UCLH combine excellent specialist healthcare with ground-breaking biomedical and clinical research. We are now taking this work further: we want to transform ourselves from a hospital conducting a lot of research into a real research hospital.
So what will be different? What will make us a research hospital rather than a hospital that does lots of research?
UCLH has a massive bank of information and patient data. Up until now this information has been collected in the form of metrics used months later in annual reports and used for research trials that will have taken many years to set up and many months to publish findings from. In the future we will be using our information to constantly and instantly find out what works best and for which people. Where once it took months for lessons learned to change practice and treatment, practice and treatment will be constantly changing in the light of experience and new evidence.
We are setting our data systems up so all the information we collect will be constantly fed into a system that is instantly updated and analysed and immediately accessible. This is a form of artificial intelligence or machine learning that will make the way we run our hospital and treat our patients increasingly better. We will be able to use every patient’s anonymised data for research and to improve our services and safety, and, because we will be able to identify potential research participants, we will be able to offer more and more patients the opportunity to participate in a clinical trial.
If you as a patient spend a long time in an outpatients waiting room, it can be weeks or months before we can review, understand and correct what went wrong in our operational system. But in the future all the information about the clinic and waiting times will be instantly fed into our system. So next time when we organise the clinic, timings and staffing we will be able to avoid the same problem.
One of our researchers has even developed a computer algorithm that can predict which kind of patients will not come to their appointment for a scan on particular days. We can use this kind of learning to organise our appointments so we cut down on missed appointments and make our service more efficient and economic.
Being able to learn in this way will have massive implications for the clinical care UCLH provides. We will be able to learn what treatments work best and for what kind of patients and clinicians will have instant access to this information. Diagnosis will be quicker and more efficient.
So if a doctor is about to prescribe medication, all the information about the patient including test results and lifestyle will be analysed by our computer system in the light of similar information about similar patients and the best treatment identified accordingly. And the doctor will have immediate access to this information in the consulting room. So when MR G, who has a sedentary life style and a blood pressure of A, comes in with x condition, he can be compared with other patients who also have a sedentary life style and blood pressure A. Information on which treatments work best for these kind of patients will mean the doctor can choose the medication most likely to help. Importantly, what happens to Mr G will be fed into the system so for example if he turns out to be an exception, next time someone like Mr G comes in the doctor will be able to be even more precise and effective in their choice of prescription. The system will be able to identify whether Mr G would be eligible for clinical trials and Mr G will be offered the chance to participate.
In the future we will be adding to this information and will collect genetic information about patients. We will ask patients to provide a blood sample for genetic analysis. Understanding a patient’s genetic make up will mean doctors will know which treatments are likely to work best for them and the likely course of their disease - for example, which cancers are likely to be aggressive and need aggressive treatment and which don’t. This means we will effectively be able to personalise medicine and will have the material to research the genetics of disease.
Because research will be based on the data of patients attending the hospital, UCLH will be more in touch with the particular health needs of our local communities. This means we can develop research trials specifically designed to investigate the healthcare problems of our local population, especially people who are disadvantaged including people with problems such as homelessness or substance misuse, and we can improve how we provide them with healthcare.
Examples of how we are already developing this kind of learning.
We recently analysed over 100,000 digital images of MRI brain scans and used these to develop an automated tool to provide detailed reports on the scans. So one day within an instant of the scan being performed an initial report on any abnormalities will produced with more precision and learned expertise than would normally be possible in such a short space of time. We are now working on techniques to automate the process of analysing microscope slides of pathology tests, so images can be analysed in a more consistent and uniform way than humanly possible - indeed, more quickly than it would take the pathologist to load the slide onto the microscope.
Managing patient flows by being able to anticipate rather than reacting to what is happening is crucial when a patient has a stroke - time is pressured in order to provide the most effective treatment and patients are likely to move between several units. So we have developed an application called StrokeNET to enable stroke units and different units within hospital networks to exchange real-time information.
Delirium or confusion affects up to 50% of elderly patients in hospital, and yet in an estivated 30-40% of these patients, this confusion is preventable, if we can identify at-risk patients early on. Many patients are too ill to have an MRI scan and clinicians have to rely on the less easy to interpret CT scanning. We have found that by applying machine learning to analyse over 1,000 CT scans we could automatically identify those at risk of delirium or who have dementia. If we could add clinical and blood tests we could be even more accurate in our predictions. If we can develop a tool to identify people at risk we have a greater chance of preventing patients developing delirium.
- Your hospital will be run more efficiently
- We will understand your health condition better and more quickly
- Your treatment will meet your individual needs
- Your care will be better and safer
- UCLH will be more able to meet the needs of its local population
- UCLH will have a bank of information researchers can use.
- Through the UCLH electronic health record system which came live in 2019
- We have set up the CRIU to work with the hospital IT team to make sure the electronic healthcare record can be used and analysed effectively for research
- In May we announced a new partnership with the Alan Turing institute to harness the power of data science and artificial intelligence to support clinical decision making to make services safer, quicker and more efficient.
- Researchers and clinicians have partnered up with our patients and carers so they can input into how the research hospital develops and make sure it is effective and relevant to patient needs.
- The AboutMe project has been set up to work with patients to develop the use of genetic information.
Wednesday, May 13, 2020
UCLH was the top recruiter of patients to studies on the NIHR portfolio last year in the North Thames area – the NIHR region which includes 23 NHS Trusts and 20 Clinical Commissioning Groups in parts of London, Essex, Bedfordshire and Hertfordshire.
20,244 people took part in research studies at UCLH between April 2019 and March 2020 – making up nearly a third of the total number who took part across the whole of the North Thames Clinical Research Network (CRN). UCLH ran 369 studies over the period – also the highest in the region.
The North Thames CRN as a whole had the highest number of studies among the 15 CRNs across England, and had the second highest number of study participants.
The NIHR CRN supports the delivery of high-quality research across the country. They help to increase opportunities for people to take part in clinical research and make sure that studies are carried out efficiently.
UCLH is also in the top 5 recruiters – out of 170 – to the GenOMICC study (Genetics Of Mortality In Critical Care) which at UCLH is led by Dr David Brealey. The NIHR national priority study for Covid-19 is seeking to identify the specific genes that cause some people to be susceptible to specific infections, including Covid-19.
Researchers will compare DNA and cells from carefully selected patients with samples from healthy people.
Finding the genes that cause susceptibility may help us to prioritise treatments to respond to the global crisis. All patients with confirmed COVID-19 in critical care are eligible for GenOMICC.
Read more on the GenOMICC website and view BBC coverage of the trial.
Wednesday, April 29, 2020
Doctors are used to ordering tests for patients – such as bloods or MRI scans – but they will now test out a platform where they can order the analysis of large-scale data relevant to an individual patient and treatment decision they face, with results returned within clinical timescales.
The ‘Informatics Consult’ platform – the first UK prototype of its kind – will have access to UCLH data to begin with. Professor Bryan Williams, Director of Research at UCLH, and Professor Harry Hemingway and Dr Alvina Lai of the UCL Institute for Health Informatics will lead the work, which is a beneficiary of a Better Care Catalyst Award from Health Data Research UK and The Health Foundation.
University Hospitals Birmingham, Barts Health Trust and Great Ormond Street Hospital will also trial the system using their own data.
Patients might reasonably expect that their medical outcomes are used to help doctors make treatment decisions for other patients. However, this is not always the case. A common dilemma facing clinicians is deciding on the most appropriate treatment decision in the absence of evidence from randomised clinical trials (RCTs) or clinical guideline recommendations.
For example, a patient who has both cirrhosis of the liver and atrial fibrillation (AF) poses a treatment dilemma for the doctor because AF is usually treated with anticoagulants to lower stroke risk, but cirrhosis is known to increase the risk of bleeding. There are no trials or guidelines to help the doctor, and currently, there is no mechanism in the NHS to learn from the treatment and outcomes of previous patients with both conditions.
The Informatics Consult will allow clinicians to select relevant conditions from a computer interface, and order an analysis of raw data relating to those conditions that is performed within minutes or hours. The platform will return easily interpretable information to the clinician on outcomes involving patients with the conditions of interest.
Professor Williams said: “Data we gather from the platform could transform health and care. There is so much raw data collected by hospitals, and we want to put this data to use, to shed light on the best treatment approaches where there is uncertainty. This will improve treatment for individual patients, and it will also reveal where we don’t have good evidence for treatment approaches, and indicate what trials we need to do. It will also help with recruitment into clinical trials.”
Dr Lai said: "We have taken a 'patients like me' approach to understand how we can improve health outcomes by optimising treatment decisions using population health data. This is particularly useful in situations where randomised trials are not feasible, for example in patients with multiple chronic conditions. Starting from one exemplar (cirrhosis and atrial fibrillation), we hope to use the Better Care Catalyst Award to scale up to look at a wide range of disease combinations where treatment uncertainty persists.”
8 January 2019
UCLH today joined the UK Health Data Research Alliance.
The alliance of health organisations, convened by Health Data Research UK, establishes best practice for the ethical use of UK health data for research at scale, with members working together to develop guidelines and standards in areas such as data security and how to involve patients and the public in research which involves data.
The aim is to accelerate development of new treatments by using health data in research.
Nine other health organisations including Guy’s and St Thomas’ and Great Ormond Street Hospital trusts have joined the alliance at the same time as UCLH, boosting alliance membership to a total of 28, with access to more than 400 datasets.
Professor Bryan Williams, Director of Research and Director of the National Institute for Health Research Biomedical Research Centre at UCLH, said: “As a Research Hospital we are already beginning to explore the enormous potential of health data to improve patient care and experience and the running of the hospital – and engaging our patients on how we do this. We look forward to working with alliance members to ensure the full benefits of data use are felt across the NHS as a whole, in a transparent way.”
25 February 2020
UCLH and UCL researchers are applying artificial intelligence (AI) to improve and personalise treatment of juvenile lupus (known in full as Juvenile Onset Systemic Lupus Erythematosus, or JSLE).
Researchers led by Dr Coziana Ciurtin and colleagues at the Centre for Adolescent Rheumatology Versus Arthritis at UCL, UCLH and GOSH and the UCL Centre for Rheumatology (Bloomsbury) are training computers to learn from concrete examples of the JSLE patient journey to enable them to build models that can predict how any particular JSLE patient’s condition will evolve.
The aim of the computer models – developed through an approach known as machine learning – is to improve treatment selection for individual patients, to personalise their care.
Dr Ciurtin said: “There is currently a lack of specific treatments for children and adolescents with lupus compared to adults – despite clinicians’ concern regarding the long-term use of treatments that suppress the immune system in younger patients. We hope that the power of AI and machine learning can help us address this lack of tailored-treatment options and help to personalise care and look into un-tackled medical problems, such as cardio-vascular risk in juvenile lupus.”
Supporting the work at the Centre for Adolescent Rheumatology is PhD student Mr Junjie Peng, who has expertise in computer science and personalised medicine. He said: “AI and machine learning approaches allow us to rapidly analyse complex data in ways that can make the treatment of lupus (and other conditions) as precise as possible.”
Prof. Liz Jury and Dr. George Robinson, at the UCL Centre of Rheumatology (Bloomsbury) added: “Understanding how the immune cells behave differently in patients with juvenile lupus according to age and gender could help us improve both lupus treatment as well as develop strategies to prevent long-term complications."
Prof Ines Pineda Torra, at the UCL Centre for Cardiometabolic and Vascular Science, said: “We are grateful to the patients who take part in research and consent to the use of their data by researchers. Patients should know that they are contributing to advances in understanding the role of blood lipids and genes in lupus – we couldn’t do this research without them.”
The research is supported by a large Versus Arthritis grant, in partnership with Great Ormond Street Children’s Charity and the NIHR Biomedical Research Centres at UCLH and GOSH.
12 November 2019
Collaborative research projects across the three UCL-linked Biomedical Research Centres which are applying artificial intelligence (AI) to complex problems in cancer, sepsis, hearing loss, neuromuscular diseases and emergency medicine will receive combined funding from the three BRCs to accelerate their progress.
The five projects across UCLH, Moorfields and Great Ormond Street Hospital BRCs will receive funding made possible by a Wellcome Trust Institutional Strategic Support Fund (ISSF) grant to UCL and are expected to develop proofs of concept or generate preliminary data which can be used to support larger research projects in future.
Projects were chosen which apply AI to challenges which, if addressed, could substantially improve patient care.
Researchers and clinicians involved in the programmes of work will apply AI to:
- Better understand the ‘microbial communities’ which colonise the blood of patients with sepsis, and which ‘microbial profiles’ make up a healthy vs diseased state, so that sepsis treatment can be more targeted (led by Dr Francois Balloux - UCL Genetics Institute)
- Predict demand for beds and other resources (such as imaging) in the emergency department to tackle crowding in the department and improve patient flow (led by Dr Sonya Crowe - UCL Clinical Operational Research Unit)
- Investigate whether AI-based methods of analysing MRI images of muscles are better than manual-based methods for muscle-wasting conditions such as Duchenne muscular dystrophy (led by Dr Baris Kanber, UCL Queen Square Institute of Neurology)
- Detect patterns of disease in cancer to catch the disease more quickly and answer the question: ‘based on this particular patient’s condition, how can we achieve the best outcome for them?’ (led by Dr Alvina Lai - UCL Institute of Health Informatics)
- Analyse data from patients with hearing loss to understand which patients would benefit most from new preventative and curative treatments (led by Nishchay Nehta, UCL Ear Institute)
Projects are due to start in 2020.
14 October 2019
UCL has received a £1 million grant from the British Heart Foundation (BHF) to develop a new team of scientists to apply advances in computer science and big data to tackle cardiovascular disease.
Work funded through the BHF Accelerator Award and led by Professor Aroon Hingorani, Director of UCL Institute of Cardiovascular Science, will focus on machine learning to generate the tools and insights needed to better predict, diagnose and treat heart and circulatory conditions.
Funding will support a number of innovative digital healthcare projects, including a new research centre for artificial intelligence (AI) in partnership with Cisco Systems and innovation through the use of UCLH’s electronic health record system, known as Epic.
Professor Hingorani said: “We are thrilled to be recipients of a £1m 5-year UCL BHF Research Accelerator Award. The UCL Accelerator has been designed with the purpose of fostering multi-disciplinary collaboration across UCL faculties coalescing expertise in cardiovascular and population science, health informatics, computer science, engineering and computational biology through jointly supervised academic posts.”
Professor Metin Avkiran, BHF’s Associate Medical Director, said: “Despite the medical advances powered by research, 420 people in the UK still die every day because of heart and circulatory diseases. That’s why we’re continuing to invest in research and supporting our scientists to make new life-saving discoveries.”
Professor Avkiran added: “The BHF Accelerator Awards empower universities like UCL to attract and nurture the very best young scientists and doctors in cardiovascular medicine and complementary fields – and fuel the exploration of new ideas.”
8 October 2019
UCLH patients shared their views on how patient data should be used for research at the BRC’s sold-out event Your data, our challenge which was streamed across UCLH and UCL.
And they questioned representatives from medicine, academia, the NHS and the pharmaceutical industry on how to ensure data is kept safe and who should have access to it.
Event attendees heard from UCLH’s Dr Gill Gaskin (Medical Director, Digital Healthcare) who said that in the past, data was a report on the past, but now it should become a predictor of the future.
John Whittaker of pharmaceutical company GlaxoSmithKline said allowing industry to access to data sped up the development of new medicines.
Some patients questioned why data needs to be shared with the private sector, asking whether data could be analysed while remaining within the NHS. NHS Digital’s Professor Daniel Ray said that while data sharing can have huge benefits, patients and the public must retain a degree of control over their data.
And Dr Hamish Tomlinson of artificial intelligence company BenevolentAI and Dr Maxine Mackintosh of the Alan Turing Institute and UCL Institute of Health Informatics said data analysed by researchers needs to be representative of all of society – to ensure insights gathered apply to all groups.
The event – facilitated by founding chair of the Health Research Authority Professor Sir Jonathan Montgomery – was the first in a series which will involve patients and the public in discussions on how UCLH manages and shares data. Events will run until mid-2020.
Due to high demand for tickets, which sold out within a few days of release, the event was livestreamed within the UCH Education Centre, the UCL Institute of Education and the UCL Institute of Health Informatics. It can be watched on the UCL Youtube page.
Details of further events will be announced on the BRC webpage for the initiative.
25 September 2019
Analysis of heart structure and function using MRI can be performed significantly faster with similar precision to experts across a wide range of diseases when using automated machine learning, new research shows.
Analysing heart function on cardiac MRI scans takes approximately 13 minutes for humans. Utilizing machine learning, a scan can be analysed with comparable precision in approximately 4 seconds, according to a paper co-authored by UCL and UCLH researchers and published in Circulation: Cardiovascular Imaging, an American Heart Association journal.
Healthcare professionals regularly use cardiac MRI to make measurements of heart structure and function. These measurements guide clinical decisions including timing of cardiac surgery and implantation of defibrillators.
Improving the performance of these measures is therefore likely to improve patient management and potentially outcomes.
In the UK, it is estimated that close to 150,000 cardiac MRI scans are required each year. Based on this number of scans and the amount of time saved from analysing scans, researchers believe that utilizing artificial intelligence (AI) to read scans could potentially lead to 54 clinician-days per year being saved at each UK health centre.
Researchers trained a neural network to read the cardiac MRI scans and results of close to 600 patients. When tested for precision on 110 separate patients from multiple centres, researchers found that there was no significant difference between the fully automated AI and an expert, or trainee.
Dr Charlotte Manisty, Senior Lecturer at UCL and a Consultant Cardiologist at the Barts Heart Centre and UCLH, said: “Cardiovascular MRI offers unparalleled image quality for assessing cardiac structure and function, however current manual analysis remains crude. Automated machine learning techniques offer the potential to change this and radically improve efficiency, although demonstrating superiority over human observers has yet to be shown.
“Our dataset of patients with a range of cardiac diseases scanned twice enabled us to demonstrate that the greatest sources of measurement error arise from human factors, and that automated techniques are at least as good as humans, with the potential soon to be ‘super-human’ – transforming clinical and research measurement precision.”
This document was composed with the free HTML beautifier which can be accessed here. Use it every time for document editing.
12 September 2019
A new UK-wide partnership has been set up to transform use of cancer data to improve patient care.
DATA-CAN – The Health Data Research UK Hub for Cancer, which the National Institute for Health Research Biomedical Research Centre at UCLH played a key part in setting up, will be hosted by UCLPartners and will work with patients across the UK to bring their clinical data together and use this data to help develop improved cancer treatments, give patients faster access to clinical trials, and understand how we can improve NHS cancer services. The Hub will be supported by patients, charities, clinicians, academic and industry-based researchers and innovators, and will involve cancer hospitals across the UK.
DATA-CAN aims to transform the ability of researchers to use high-quality cancer data, while ensuring all data is held securely and patients can decide how their data might be used. It is one of seven Health Data Research Hubs being set up across the UK to speed up research for new medicines and treatments, support quicker diagnoses and potentially save lives
The Health Data Research Hubs are part of a four-year £37million investment from the Government Industrial Strategy Challenge Fund (ISCF), led by UK Research and Innovation, to create a UK-wide system for the safe and responsible use of health-related data on a large scale. The national hub has been founded by researchers in London, Belfast and Leeds.
DATA-CAN will support the use of data to deliver benefits for patients and healthcare professionals, improve the health of UK citizens, enable world-leading medical research and create new investment in healthcare.
19 August 2019
Find a Study – UCLH’s new clinical trials database developed to provide equitable access to research and boost study recruitment at the Trust – has been featured in the online magazine Digital Health.
The database has been designed to use structured clinical terminology to match available clinical trials to diagnosed conditions in patients’ electronic medical records – the first time this has been done in the NHS.
Trials available to individual patients will also be suggested from within UCLH’s electronic patient record system.
The database is publicly available at https:/
Find a Study has been developed by a team led by Dr Wai Keong Wong, consultant haematologist and chief research information officer at UCLH.
Dr Wong told Digital Health that UCLH researchers will now be able to tell anyone interested in research at the Trust: “this is the best way to find a study at UCLH.”
Find a Study runs on a platform known as Keytrials – also developed by Dr Wong’s team – which could be used by other NHS Trusts to run their own versions of Find a Study.
9 August 2019
The Department of Health has announced a £250 million funding boost for the development of artificial intelligence (AI) in the NHS to solve some of the biggest healthcare challenges.
AI is already being developed in some hospitals in partnership with universities, including the partnership between UCLH and UCL, where researchers have so far:
NHSX, the new organisation which will oversee the digitisation of the health and care service, will oversee the use of the £250 million, in partnership with the Accelerated Access Collaborative, which fast-tracks “breakthrough” medicines and technologies for the NHS.
Interviewed on the BBC News Channel, Professor Bryan Williams, NIHR University College London Hospitals BRC Director and Director of Research at UCLH, stressed the opportunities were “enormous” for the use of AI in the NHS, including in terms of diagnosing patients. He said: “There are many examples where computational processes in the background are going to speed up diagnostics.”
Professor Williams said hospitals placed the highest priority on the security of patient data, and development work can be done without the use of identifiable patient data, adding that in many cases synthetic data – which is not real patient data but has been modelled on patient data – is used.
Health Secretary Matt Hancock said: “The experts tell us that because of our NHS and our tech talent, the UK could be the world leader in these advances in healthcare, so I’m determined to give the NHS the chance to be the world leader in saving lives through artificial intelligence and genomics.”
This document was edited with the instant web content composer. Use the online HTML converter to convert the documents for your website.
2 July 2019
UCLH has been placed in the top 10 NHS trusts for clinical research activity in 2018/19.
With 448 research studies recruiting participants (up from 427 last year) and 14,620 study participants (a 28% increase on last year’s figure of 11,418) UCLH is ranked ninth in England according to the National Institute for Health Research in its league table of research-active trusts.
And in terms of commercial research studies UCLH is ranked third, with the second largest increase in commercial studies nationally.
UCLH continues to have a high ranking in terms of total research studies and participants despite the fact that 1 in 4 of its studies in 2018/19 were early phase trials, which only include a small number of participants.
Professor Bryan Williams, Director of Research at UCLH, said: “We are pleased to be recognised as one of the top research hospitals, and to have increased the number of research studies and study participants at UCLH compared with last year.
24 June 2019
UCL and UCLH are set to apply artificial intelligence to tackle the global threat of anti-microbial resistance (AMR) after being awarded £3.3m in government funding.
Prof Judy Breuer at UCL will lead a team of researchers and clinicians at UCL, UCLH – including AMR expert at UCLH Prof Peter Wilson – and Great Ormond Street Hospital (GOSH) for the ‘Precision AMR (anti-microbial resistance)’ initiative to improve tests for antimicrobial resistance and to develop AI (artificial intelligence) algorithms to rapidly interpret test results.
They aim to enable earlier diagnosis and treatment with the right antibiotic; ensure treatment with the right dose and combination of drugs; and prevent the spread of antibiotic resistant infections.
They also hope to be able to confirm more quickly cases where no antibiotic resistant infection is present in patients, so that unnecessary treatment is not given.
The funding to UCL, UCLH and GOSH is part of a total of £32m committed by the Department of Health and Social Care (DHSC) to research centres across the country to improve prescribing and identify patterns of resistance.
For the ‘Precision AMR’ initiative, UCL, UCLH and GOSH researchers will improve tests for infections which are resistant to antibiotics, develop algorithms to analyse results of these tests, and conduct clinical trials of diagnostic tools which improve identification of antimicrobial resistance.
The team will apply machine learning approaches to the analysis of AMR tests, where algorithms make better predictions over time as they analyse more data.
And the team will link up this data with electronic patient records to gain information on how clinicians are using test results in clinical care so that prescribing and management of patients can be improved.
15 April 2019
Researchers at UCLH and UCL have developed artificial intelligence to predict which patients are most likely to miss appointments.
A team from UCLH and UCL created an algorithm using records from 22,000 appointments for MRI scans, allowing it to identify 90% of those patients who would not attend.
“On average we estimate this could save £2-3 per appointment,” Parashkev Nachev, of UCL Queen Square Institute of Neurology and the National Hospital for Neurology and Neurosurgery at UCLH, told The Guardian. “Given that a big hospital could have nearly a million scheduled events per year, that could potentially be a lot of resource.”
The project is part of a broader programme at UCLH and UCL that aims to bring the benefits of the machine-learning revolution to the NHS.
The health secretary, Matt Hancock, called for AI-based approaches to be rolled out more widely. “Missed hospital appointments waste patient and staff time, prevent sick people from being seen at the earliest opportunity and cost our amazing NHS an unjustifiable amount of money,” he said.
“Artificial intelligence has enormous potential to revolutionise healthcare and this is exactly the type of innovation our NHS needs to embrace to ensure every penny goes further as part of the Long Term Plan.”
11 June 2019
UCL and KCL researchers supported by the UCLH BRC have devised a new artificial intelligence-based method for detecting the brain’s response to treatment in multiple sclerosis (MS) that is substantially better than what a human expert is able to do using conventional techniques, representing potentially ‘superhuman’ performance in the task.
The researchers – led by Dr Parashkev Nachev and Prof Olga Ciccarelli, both of the UCL Institute of Neurology – hope in future this method will be used to predict an individual’s response to a drug before they start treatment, and which drug a patient should be given.
One way of assessing MS treatment response is by analysing patients’ MRI scans. At present, radiologists assess scans by counting the number of lesions and measuring lesion volumes, comparing these observations with those made on scans done before treatment started.
But the researchers’ new AI-based method of analysing scans means that regions of the brain can be analysed in much greater detail, and in a way which more closely reflects the complexity of the brain.
21 May 2019
UCL researchers have produced the first ‘chronological map of human health’.
Researchers said that the timeline of disease showing which sections of the population are susceptible to which health conditions and at which ages should improve diagnosis and help target research priorities.
For the paper published in The Lancet Digital Health, researchers co-led by Dr Valerie Kuan and Dr Spiros Denaxas analysed the digital health records of 4 million people in England to chart the occurrence of the 50 most common conditions in each decade of life from birth to old age, and the median age at diagnosis for 308 conditions.
Earlier studies attempting to do the same thing suffered from problems such as small or unrepresentative sample sizes.
Key findings were that:
- Hospital-admitted infections affected individuals at the beginning and end of life (<10 years and ≥80 years)
- Allergies were common in childhood (<10 years)
- Mental health disorders were most prevalent from early adulthood (≥20 years)
- Menstrual disorders and migraine were common women of childbearing age (20–49 years)
- Metabolic conditions such as obesity and dyslipidaemia, together with hypertension, increased in prevalence from middle age (≥40 years)
- Cardiovascular diseases emerged later in life (≥60 years), following the surge in metabolic conditions in middle-age
Wednesday, May 15, 2019
UCL has opened a new centre to train leaders in medical imaging research in a bid to encourage translation of imaging innovation into better clinical care.
The Engineering and Physical Sciences Research Council (EPSRC) Centre for Doctoral Training (CDT) in Intelligent, Integrated Imaging in Healthcare (i4health) is offering scholarships to PhD students to develop innovations in imaging technology – including the application of artificial intelligence, robotics and ‘big data’ to imaging.
Dr Gary Zhang, Director of the CDT, said: “We’re excited to launch our new CDT. UCL is already home to cutting edge research in imaging with a track record of innovation in healthcare, meaning our centre will be ideally placed to develop future leaders in imaging who can develop new technologies and translate them into improved clinical care.”
“Students who come to work with us will make a real impact on patients’ lives,” Dr Zhang added. Scholarships will be funded by the EPSRC, charity and industry partners, and NIHR Biomedical Research Centress at UCLH, Great Ormond Street Hospital and Moorfields.
The CDT is backed by the BRC, which will fund 50% of 6 studentships this year.
Dr Nick McNally, UCLH BRC Managing Director, said: “These studentships will emphasise clinical translation of novel medical imaging technologies – very much in keeping with the BRC’s focus on translational research – and we’re delighted to be supporting the CDT in this way.”
21 February 2019
The UCLH Biomedical Research Centre will form part of a new centre to apply artificial intelligence (AI) to healthcare, and healthcare to AI.
UCL has been awarded £12.6m in funding from UK Research and Innovation (UKRI) which will be used to establish two new Centres for Doctoral Training (CDTs) at UCL, to enable a new generation of PhD students to create new AI technology, transforming healthcare and creating new commercial opportunities.
The BRC will be involved in one CDT focussing on ‘AI-enabled Healthcare Systems’ which will be led by Prof Geraint Rees, Professor of Cognitive Neurology (UCL life Sciences), along with NIHR BRCs at Moorfields Eye Hospital and Great Ormond Street.
The CDT will also be supported by numerous commercial partners, including Benevolent AI, along with the Whittington and Royal Free Hospitals and Public Health England.
“We will not only apply AI to healthcare but also apply healthcare to AI. This will drive innovation in the AI field while also using AI to transform healthcare by extracting more information from patient data to accelerate diagnosis and improve patient outcomes,” said Professor Rees.
25 October 2018
Machine learning could help to find new treatments for dementia, according to researchers at UCL.
A new algorithm that can automatically disentangle different patterns of progression in patients with a range of different dementias, including Alzheimer’s disease, will enable individuals to be identified that may respond best to different treatments.
For the paper, published in Nature Communications, researchers devised and applied a new algorithm called SuStaIn (Subtype and Stage Inference) to routinely acquired MRI scans from patients with dementia.
The algorithm was able to identify three separate subtypes of Alzheimer’s disease, which broadly match those observed in post-mortems of brain tissue, and several different subtypes of frontotemporal dementia. Critically, however, this subtyping could be done in life, using brain scanning, and very early in the disease process.
Being able to identify the subtypes early on in the disease process and using non-invasive MRI scanning means there is a better chance of identifying the best treatment for individuals.
12 October 2018
UCLH clinicians and UCL computer scientists have got together at a sell-out UCLH/UCL workshop event to discuss challenges in healthcare ripe for the application of artificial intelligence (AI) and data science.
The event was aimed at matching up clinicians with computer scientists to find ways of using AI to improve diagnosis, speed up treatment or personalise care.
Staff from across UCLH and UCL attended the workshop, and consultant haematologist Dr Wai Keong Wong was among the clinicians to put forward suggestions for projects. His idea involved using AI and machine learning to derive additional information from the raw data produced by full blood count analysers.
6 August 2018
A researcher at UCL/UCLH has received a 5 year NIHR Research Professorship to optimise the treatment of multiple sclerosis (MS) through the use of machine learning.
Professor Olga Ciccarelli, from the UCL Institute of Neurology, and her NIHR-funded team will develop a computer tool which predicts which drugs a patient with MS will respond to.
There are many drugs licensed for MS, but doctors and researchers currently cannot predict which will work best for an individual.
As a result, the choice about which medication to start is based on personal preference.
Professor Ciccarelli’s team will collect all the information which makes up the ‘profile’ of patients with MS, including age, gender, genetic factors, diet, scans and other health conditions patients may have.
The new computer tool will be able to predict which treatments work best for different patient profiles.
In May 2018 we announced our vision to be a research hospital – not just a hospital that does a lot of research. Read our full report.
As a research hospital, practice and treatment will constantly evolve in the light of experience and new evidence. In addition, staff will channel first-hand experience of patient care straight into the design and running of research studies.
We will harness the power of data science and artificial intelligence to do this.
This intertwining of clinical practice and research will be critical as we confront COVID-19. We will rapidly translate new evidence and insights into improvements in care, and the experience of our clinical teams caring for Covid-19 patients is feeding rapidly and directly into decisions around COVID-19 research.