Skip to main content

AI – safe and effective for everyone: new standards released by BHP members

Written by Louise Stanley on . Posted in Health inequalities.

An international initiative called STANDING Together – led by BHP founder-members University Hospitals Birmingham NHS Foundation Trust, and the University of Birmingham – has released new standards ensuring that medical artificial intelligence (AI) systems are developed with appropriate health datasets.

The STANDING Together recommendations ensure that the full diversity of people that AI systems will be used for, is represented in health datasets. This is imperative as AI systems are less likely to work well for people who aren’t properly represented in datasets – and may even be harmful. People who are in minority groups are particularly likely to be under-represented in datasets.

The recommendations provide guidance on collecting and reporting details such as age, sex, gender, race, ethnicity, and other important characteristics, and have been developed following a two-year research study involving over 350 people from 58 countries, including patients, researchers, healthcare professionals, industry experts, and regulators. They also recommend that any limitations of the dataset should be transparently reported to ensure that developers creating AI systems can choose the best data for their purpose. Guidance is also given on how to identify those who may be harmed when medical AI systems are used, allowing this risk to be reduced.

The research has been conducted with collaborators from over 30 institutions worldwide, including universities, the UK medicines regulator (the Medicines and Healthcare products Regulatory Agency, MHRA), patient groups and charities, and small and large health technology companies. The work has been funded by The Health Foundation and the NHS AI Lab and supported by the National Institute for Health and Care Research (NIHR).

Lead researcher Dr Xiaoxuan Liu, Clinical Scientist in AI and Digital Health Technologies at the University of Birmingham, explained: “AI models are underpinned by data, which captures a wealth of information. When dealing with health data, this information can unfortunately include existing health inequalities. These inequalities can come about in many ways, including underrepresentation of particular groups, or as a reflection of structural biases within wider society. It is vital that anyone using data to develop new innovations (including AI) are aware of any biases, and that they are accounted for. As we move towards an AI-enabled future, we can ensure these technologies don’t just work on average, but that they work for all.”

Dominic Cushnan, Director AI, Imaging & Deployment at the NHS AI Lab, said: “The lack of diversity and inclusivity in our current datasets are major challenges in our ability to ensure AI in health and care works for everyone. These standards are an important step towards transparent and common documentation of represented groups in our data, which can support the responsible and fair development and use of AI.”

The recommendations are available open access at www.datadiversity.org/recommendations to support the development of safe, effective and equitable AI tools for healthcare.

Doctor Showing Patient Test Results On Digital Tablet stock photo

Review of 25 years reveals AI healthtech is beginning to listen to patients

Written by Louise Stanley on . Posted in Health inequalities.

Patients experiences of their health conditions are slowly being integrated into AI studies, a review of 25 years of healthcare publications has found.

Published in the Lancet Digital Health, the new study saw experts from BHP members the University of Birmingham and University Hospitals Birmingham look at more than 600 interventional studies on AI healthcare technologies.

While the team, funded by the National Institute for Health and Care Research (NIHR), found that only 24% of studies have a patient reported outcome element included in their study, there has been an increase in the number in recent years with 2021 and 2022 seeing nearly two thirds of all studies included.

Dr Samantha Cruz Rivera from the Centre for Patient Reported Outcomes Research at the University of Birmingham said: “The opportunities for AI to revolutionise healthcare are only going to make patients’ lives better if those models consider how patients actually feel and respond to healthcare interventions. Our review shows that patient reported outcomes, such as measures of symptom burden and quality of life, are increasingly being incorporated into AI studies which is very encouraging.

“The future could see AI healthcare tech analysing and raising an alert if a patient’s health is declining, but such a future is going to depend on having large-scale patient reported outcome datasets so that AI can support or drive care in a specific condition, and incorporate patient experience. Integrating PROs within AI can support the humanisation of AI for health and ensure that the patient’s voice is not lost in a rush to digitise and automate health care.”

Melanie Calvert, Professor of Outcomes Methodology at the University of Birmingham said: “Managing long term health conditions places a huge burden on patients and their families, but also the NHS and social care system. AI systems can help support patients and healthcare systems to aid decision-making, improve workflow and lead to more efficient care with improved outcomes.

“Encouragingly, we are seeing more research into AI tech solutions for chronic conditions incorporating patient reported outcomes.

“It’s clear that having technology that can analyse and predict patient outcomes to help prioritise care is going to be a part of healthcare’s future. However, we must ensure that the patient reported outcome data used to train the AI systems are applicable to the population they are intended to serve. If we don’t do this, the gaps between advantaged and disadvantaged populations will only get worse.”

First Midlands research collaboration to focus on patient safety

Written by Louise Stanley on . Posted in Early diagnosis and detection, Health inequalities, Maternal health.

Expectant mums and anyone needing emergency treatment will both benefit from funding for new research to improve patient safety and reduce the risk of harm.

BHP founder-members the University of Birmingham and University Hospitals Birmingham NHS Foundation Trust will be establishing the first research collaboration focused on patient safety based in the Midlands, thanks to new funding from the National Institute for Health and Care Research. The announcement made today by the Department for Health and Social Care will see £3.4m invested in world-leading research that supports patient safety in maternal and acute care settings.

The newly announced NIHR Midlands Patient Safety Research Collaboration (PSRC) will bring together NHS trusts, universities, and private business to evaluate how digital tools can support clinical decision making and reduce risks for patients.

Professor Alice Turner is a Professor of Respiratory Medicine in the Institute for Applied Health Research at the University of Birmingham, Honorary Consultant Respiratory Physician at University Hospitals Birmingham, and Co-Director of the NIHR Midlands Patient Safety Research Collaboration along with Professor Richard Lilford, Professor of Public Health at the University of Birmingham.

She commented: “Patient safety is at the forefront of every clinician’s mind and runs at the heart of the whole healthcare system. The power of new technology available to us means that we can address one of the ongoing areas of risk for patients, which is effective communication and clinical decision making.

“Thanks to the new funding from NIHR and with the support of partners, the new collaboration will be looking at how digital tools can make a real difference to reduce risks and support patient safety in the key areas of acute medicine and maternal health.”

Acute Care

Patients requiring emergency medical care in acute services will benefit as new digital decision-making tools could improve prescribing and personalised management.

Thanks to the funding, the NIHR Midlands PSRC will trial digital clinical decision support tools which will provide smoother flow of information between healthcare professionals in acute care. Working with acute care hospitals, primary care providers and the West Midlands Ambulance Service, the researchers will review how the digital tools can reduce risks of patient harm at key points in acute care management.

Professor Elizabeth Sapey, Director of the Institute of Inflammation and Ageing at the University of Birmingham and an Honorary Respiratory Consultant at the University Hospitals Birmingham said: “The vision is that every healthcare professional involved in a patients journey in acute care has access to the same information, the same decision-making support, and is able to both spot and flag any point where patients might be at increased risk of harm.

“We know that a disproportionate number of medical errors happen in acute services, and around half of patients experience a clinical error in what can be a complex journey. As acute care becomes more heavily relied on, it is critical that we use technology available to us to ensure that our patients are kept safe and risk is managed.”

Maternal Health

Mothers and babies will benefit from the new research collaboration to look at how digital tools can support antenatal decision making.

The collaboration will examine the effectiveness of clinical decision-making tools to recognise risks among expectant mothers, particularly among marginalised groups who experience worse outcomes and quality of care compared to the general population.

Professor Shakila Thangaratinam, Co-Director of WHO Collaborating Centre for Global Women’s Health at the University of Birmingham and Consultant Obstetrician at the Birmingham Women’s Hospital said: “Maternal and perinatal mortality reports in the UK have highlighted that there are real issues when it comes to identifying and responding to risk. One of the key priorities is identifying early in pregnancy those mothers who need the extra support and care, thereby ensuring that women receive individualised care during pregnancy.

“With this new funding from the NIHR, we can evaluate how digital tools can help clinicians ensure that no mum falls ‘through the net’ in identifying risk, and ensure every family receives the right level of support.”

Partners involved in the NIHR Midlands Patient Safety Research Collaboration

  • University Hospitals Birmingham NHS Foundation Trust (BHP)
  • University of Birmingham (BHP)
  • Birmingham Women’s and Children’s NHS Foundation Trust (BHP)
  • Health Innovation West Midlands (BHP)
  • NHS Birmingham and Solihull Integrated Care Board
  • University of Warwick
  • University of Aberdeen
  • Clevermed Limited
  • West Midlands Ambulance Service University NHS Foundation Trust
  • Shrewsbury and Telford Hospital NHS Trust

Drugs to delay preterm birth are safe for global reduction in neonatal death

Written by Louise Stanley on . Posted in Health inequalities, Maternal health.

Women around the world should be able to access the best drug treatments that help to delay preterm births and improve outcomes for newborns, suggests new research.

Researchers from BHP founder-member the University of Birmingham worked with colleagues from the World Health Organization to review 122 randomised trials – published between 1966 and 2021, involving 13,697 women and conducted in 39 countries including high, middle and low-income states. The study, published in Cochrane Reviews, has allowed researchers to create a league table of drugs that delay birth, called tocolytics, based on their effectiveness and side effects.

Women benefitted from all preterm delay treatments included in the meta-analysis of studies, although the research team noted that the effectiveness of different drugs was less clear in some of the studies. The team also looked at the side effects of different drugs and combinations, including the likelihood of having to stop treatment.

The team have bought together the evidence on the benefits as well as the harms of these treatments (compared to no treatment or placebo), to arm clinicians and policy makers around with world with the information to decide upon the best treatment for the women in their care in their specific setting.

Dr Amie Wilson, Research Fellow Global Maternal Health at the University of Birmingham said: “The findings show that the benefits of these drugs outweigh any risks associated with unwanted side effects. These treatments are leading to a significant reduction in the number of deadly preterm births, and we now need to further understand the effectiveness of tocolytics for specific groups depending on pregnancy length.

“Our previous research has led to the improvement of guidelines for use of tocolysis drug use to delay preterm birth in the UK. Knowing that this paper helped to inform the forthcoming recommendations of the World Health Organization on the use of tocolytics, we hope that many more women around the globe will have access to these drugs, and have healthier births.”

Dr Victoria Hodgetts Morton, NIHR Clinical Lecturer in Obstetrics at the University of Birmingham and co-author of the paper said: “Preterm birth is the most common reason why a newborn baby may die, and the leading cause of death in children under five years of age.

“Tocolytics aim to delay preterm birth and allow time for the women to receive medicines that can help with baby’s breathing and feeding if born preterm, and medicines that lower the chance of cerebral palsy of the infant. Crucially, a short delay in preterm birth can enable women to reach specialist care.”

    3d rendering of red blood cells in vein

    New research collaboration will develop precision cell therapies for blood disorders

    Written by Louise Stanley on . Posted in Cancer outcomes, Experimental medicine, Health inequalities.

    The Universities of Birmingham and Oxford are to take part in one of five NHS Blood and Transplant (NHSBT) research units launched today.

    The £20m programme, co-funded by the National Institute for Health and Care Research (NIHR) and NHSBT – is aimed at providing new technologies, techniques or insights that will benefit donation, transfusion, and transplantation. The NIHR BTRUs are partnerships between universities and NHSBT.

    Many of the work strands in the new units could result in new technologies and practices that can then be delivered at scale by NHSBT, helping to save and improve even more lives. Much of the work will be aimed at reducing health disparities and improving access to new treatments.

    Researchers at the Universities of Birmingham (UoB) and Oxford are part of the NIHR BTRU in Precision Cellular Therapeutics – also working in collaboration with University Hospitals Birmingham (UHB) NHS Foundation Trust. UoB and UHB are both founding members of BHP, with a long history of collaborative research and development.  

    The aim is to develop new kinds of cell therapies for blood disorders and blood cancer, and improved systems for following up patients receiving treatment to better support their care.

    There is a wide range of work in the package but examples include:

      • Transplants work in blood cancer patients because some of the donor immune cells attack and eliminate the cancer, but these cells can also attack the donors own cells and cause a complication called graft versus host disease (GvHD).  The team will seek to identify and clone the receptors that enable the T cells to target the cancer cells while reducing the toxicity due to GvHD seen in patients. The ultimate aim of this research is develop a novel clinical trial, with NHSBT, via its cell therapy manufacturing infrastructure, expanding these cancer specific T cell receptors for use in patients.
      • There is a shortage of suitable cell donors for minority communities.  Cord blood units from babies may be a match but not have enough cells to be successful in adults. The team will seek to expand and gene edit the stem cells in cord blood, so they could be used with increased safely in a wider range of adults.  NHSBT will support the translation of this research through to early phase clinical trials, providing process development, manufacturing and quality control expertise.  This initiative will drive wider access to cord blood transplant.
      • It is important that patients from all communities benefit from cell therapies.  The team will seek to better understand how patients access the newer cell therapies and how they perceive the benefits of treatment.  The team will develop new digital technologies that improve care by enhancing interactions between the patients and their doctors and nurses.

    The BRTUs are funded by £16m from the NIHR and £4m from NHSBT, with research goals set to meet NHSBT’s requirements, to be delivered between 2022 and 2027.

    The products could be manufactured at the latest NHSBT sites including major new centres such as the new cellular therapies laboratories in Barnsley and the forthcoming Clinical Biotechnology Centre in Bristol.

    Dr Gail Miflin, Chief Medical Officer for NHSBT, said: “By collaborating with academia, these five new Blood and Transplant Research Units will help us to deliver on our mission to ‘save and improve even more lives’ and drive innovation to inform future clinical practice and improve patient outcomes.

    “For example, the supply-demand gap for solid organs continues to grow. We will explore the use of organ perfusion technologies to maintain and enhance the quality of organs, improve organ preservation and increase organ utilisation. This will enable more patients to receive the transplant they need.

    “And by building and analysing new data sets to track and demonstrate the impact of our interventions will lead to better understanding and improved outcomes. We already do this well for solid organs, but do not currently understand the outcomes for people who receive blood or stem cells. We will work with partners to build integrated data sets for these patients, focusing on the multi-transfused, especially those with sickle cell disease where a clear health inequity exists.

    “To maximise the value and impact from our research, we will accelerate the translation of innovation into practice. The NIHR BTRUs will be an important vehicle for this in the longer term.”

    Improving access to quality post-injury care can save lives

    Written by Louise Stanley on . Posted in Health inequalities.

    A major study led by BHP founder-member the University of Birmingham will help reduce unnecessary deaths in developing countries from injuries caused by accidents or violence.

    Every year five million people die due to injuries like road traffic accidents, burns, falls, or violence – with 90% of these deaths in Low- or Middle-income Countries (LMICs).

    Backed by £2.9 million of NIHR funding, University of Birmingham (UK) and University of Stellenbosch (South Africa) researchers will build on partnerships with experts in Ghana, South Africa, Rwanda, and Pakistan to explore how to overcome barriers to accessing quality care after injury and reduce the likelihood of death or disability.

    Experts will use a ‘four delays framework’, which looks at where delays occur in people seeking, reaching, receiving, and remaining in good quality care after injuries, to collect information on delays and their effects on patient outcomes. They will develop visualisations for policy makers to see where to intervene to reduce delays suffered after injury and produce maximum health benefits.

    The project builds on a recent study funded by the NIHR led by University of Birmingham and experts in Rwanda which identified 121 barriers to access to quality injury care in three countries across sub-Saharan Africa: Ghana, South Africa and Rwanda.

    Researchers discovered that whilst there were a large number of barriers in total, only 31 (25.6%) of these were shared across all three countries, suggesting that solutions to improve access to quality care after injuries may be highly contextually dependent.

    Also, only just over half of these common factors (18/31, 58%) were related to delays in receiving quality care at the healthcare facility, suggesting that investment needs to be made in overcoming delays in seeking or reaching care.

    Justine Davies, Professor of Global Health Research at the University of Birmingham, explained: “Injuries in LMICs are common and their number is expected to increase, but death and disability after injury can be substantially reduced if people reach healthcare facilities in a timely manner. Understanding access to quality injury care is critical to improving patient outcomes. By partnering with organisations in Ghana, South Africa, Rwanda, and Pakistan, we will develop solutions for future study in these, and similar countries. Our research has already identified many barriers to quality care in Rwanda, Ghana and South Africa. However, as few of these are shared across countries, solutions to reduce the risk of post-injury death and disability will need to reflect circumstances in each country.”

    The diversity of cultures, economies, and injuries in partner countries will allow researchers to identify delays and solutions that can be applied across different settings and others that are transferable outside of the four countries of this study.

    Study leaders will also train four PhD students and 14 junior researchers in countries with low resources. Training will be done through the development of research hubs in partner countries – these hubs will continue and train future LMIC researchers beyond the project’s end.

    Researchers will also work closely with patients, community members and leaders, healthcare providers, and policy makers to understand how to translate the findings of the study into real world solutions.