̽��ֱ�� of Cambridge - Health Data Research UK

£10 million programme to use AI and state-of-the-art analytics to fight cancer

cjb250 — Wed, 22 Jan 2025 00:05:20 +0000

̽��ֱ��Cancer Data-Driven Detection programme will be led by Antonis Antoniou, Professor of Cancer Risk Prediction at the ̽��ֱ�� of Cambridge. It is funded by Cancer Research UK, the National Institute for Health and Care Research, and the Engineering and Physical Sciences Research Council.

̽��ֱ��programme aims to access and link data from different sources - including health records, genomics, family history, demographics, and behavioural data - to develop statistical models that help scientists accurately predict who is most likely to get cancer. Alongside this, the programme will develop powerful new tools that use AI to analyse the data and calculate an individual’s risk of cancer throughout their lifetime.

Professor Antoniou said: “Finding people at the highest risk of developing cancer, including those with vague symptoms, is a major challenge. ̽��ֱ��UK’s strengths in population-scale data resources, combined with advanced analytical tools like AI, offer tremendous opportunities to link disparate datasets and uncover clues that could lead to earlier detection, diagnosis, and prevention of more cancers.”

Over the next five years, the funding will build the infrastructure required to access and link these datasets, train new data scientists, create the algorithms behind the risk models and evaluate the algorithms and AI tools to ensure that they are giving accurate and clinically useful information about cancer risk. ̽��ֱ��scientific programme will be guided by partnerships with cancer patients, the public, clinical experts and industry, while addressing ethical and legal considerations to ensure that the models and tools work well in practice.

Professor Antoniou added: “Ultimately, [the Cancer Data Driven Detection programme] could inform public health policy and empower individuals and their healthcare providers to make shared decisions. By understanding individual cancer risks, people can take proactive steps to stop cancer before it gets worse or even begins in the first place.”

̽��ֱ��models generated from this research could be used to help people at higher risk of cancer in different ways. For example, the NHS could offer more frequent cancer screening sessions or screening at a younger age to those at higher risk, whilst those at lower risk could be spared unnecessary tests. People identified as higher risk could also be sent for cancer testing faster when they go to their GP with possible cancer signs or symptoms. Individuals at higher risk could also access different ways to prevent cancer.

Earlier diagnosis of cancer saves lives, yet according to analysis of NHS figures by Cancer Research UK, only 54% of cancers in England are diagnosed at stages one and two, where treatment is more likely to be successful. NHS England has set a target to diagnose 75% of cancers at stages one and two by 2028, and this will only be achieved with research and embracing new technologies to catch cancer earlier.

Last week, the Prime Minister announced backing for the power of big data and AI, which has the potential to help even more patients, including those with cancer.

Science Minister Lord Vallance said: “There are huge opportunities in AI to improve UK healthcare, from scans detecting illnesses earlier to bringing NHS waiting lists down by planning appointments more efficiently, and these will continue to develop.

“This investment in harnessing the potential of data to spot those at risk of cancer represents the sort of innovation the Government’s new AI Opportunities Action Plan sets out to realise, so this technology improves lives, while transforming public services and boosting growth.”

Minister for Public Health and Prevention, Andrew Gwynne said: “Using the latest technology could revolutionise how the NHS diagnoses and treats patients. As part of this government’s Plan for Change, we will transform our health service from analogue to digital, and innovative projects like this show exactly how we will achieve it.”

̽��ֱ��Cancer Data Driven Detection programme is jointly supported by Cancer Research UK, the National Institute for Health & Care Research, the Engineering & Physical Sciences Research Council, Health Data Research UK, and Administrative Data Research UK.

Head of Prevention and Early Detection Research at Cancer Research UK, Dr David Crosby, said: “ ̽��ֱ��single most important thing we can do to beat cancer is to find it earlier, when treatment is more likely to be successful. With half a million cancer cases per year expected in the UK by 2040, we need a major shift towards more accurate diagnosis and detection of early cancer.”

Find out how Cambridge is Changing the Story of Cancer

Adapted from a press release from Cancer Research UK

Cambridge researchers are to lead a £10 million project that could result in doctors being able to predict your individual chances of getting cancer and offer personalised detection and prevention.

̽��ֱ��UK’s strengths in population-scale data resources, combined with advanced analytical tools like AI, offer tremendous opportunities to link disparate datasets and uncover clues that could lead to earlier detection, diagnosis, and prevention of more cancers

Antonis Antoniou

BrianPenny (Pixabay)

Image representing AI and Big Data

̽��ֱ��text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Licence type:

Public Domain

Incidence of heart attacks and strokes was lower after COVID-19 vaccination

cjb250 — Wed, 31 Jul 2024 09:00:37 +0000

̽��ֱ��study, published today in Nature Communications, showed that the incidence of arterial thromboses, such as heart attacks and strokes, was up to 10% lower in the 13 to 24 weeks after the first dose of a COVID-19 vaccine. Following a second dose, the incidence was up to 27% lower after receiving the AstraZeneca vaccine and up to 20% lower after the Pfizer/Biotech vaccine.

̽��ֱ��incidence of common venous thrombotic events – mainly pulmonary embolism and lower limb deep venous thrombosis – followed a similar pattern.

Research led by the Universities of Cambridge, Bristol and Edinburgh and enabled by the British Heart Foundation (BHF) Data Science Centre at Health Data Research UK analysed de-identified health records from 46 million adults in England between 8 December 2020 and 23 January 2022. Data scientists compared the incidence of cardiovascular diseases after vaccination with the incidence before or without vaccination, during the first two years of the vaccination programme.

Co-first author Dr Samantha Ip, Research Associate at the Department of Public Health and Primary Care, ̽��ֱ�� of Cambridge, said: “We studied COVID-19 vaccines and cardiovascular disease in nearly 46 million adults in England and found a similar or lower incidence of common cardiovascular diseases, such as heart attacks and strokes, following each vaccination than before or without vaccination. This research further supports the large body of evidence on the safety of the COVID-19 vaccination programme, which has been shown to provide protection against severe COVID-19 and saved millions of lives worldwide.”

Previous research found that the incidence of rare cardiovascular complications is higher after some COVID-19 vaccines. For example, incidence of myocarditis and pericarditis have been reported following mRNA-based vaccines such as the Pfizer/Biotech vaccine, and vaccine-induced thrombotic thrombocytopenia following adenovirus-based vaccines such as the AstraZeneca vaccine. This study supports these findings, but importantly it did not identify new adverse cardiovascular conditions associated with COVID-19 vaccination and offers further reassurance that the benefits of vaccination outweigh the risk.

Incidence of cardiovascular disease is higher after COVID-19, especially in severe cases. This may explain why incidence of heart attacks and strokes is lower in vaccinated people compared with unvaccinated people, but further explanations are beyond the scope of this study.

Professor William Whiteley, Associate Director at the BHF Data Science Centre and Professor of Neurology and Epidemiology at the ̽��ֱ�� of Edinburgh, said: “ ̽��ֱ��COVID-19 vaccination programme rollout began strongly in the UK, with over 90% of the population over the age of 12 vaccinated with at least one dose by January 2022.

“This England-wide study offers patients reassurance of the cardiovascular safety of first, second and booster doses of COVID-19 vaccines. It demonstrates that the benefits of second and booster doses, with fewer common cardiovascular events include heart attacks and strokes after vaccination, outweigh the very rare cardiovascular complications.”

̽��ֱ��research team used de-identified linked data from GP practices, hospital admissions and death records, analysed in a secure data environment provided by NHS England.

Co-last author Dr Venexia Walker, Research Fellow at the ̽��ֱ�� of Bristol, said: “Given the critical role of COVID-19 vaccines in protecting people from COVID-19, it is important we continue to study the benefits and risks associated with them. ̽��ֱ��availability of population-wide data has allowed us to study different combinations of COVID-19 vaccines and to consider rare cardiovascular complications. This would not have been possible without the very large data that we are privileged to access and our close cross-institution collaborations.”

Reference
Ip, S et al. Cohort study of cardiovascular safety of different COVID-19 vaccination doses among 46 million adults in England. Nat Comms; 31 Jul 2024; DOI: 10.1038/s41467-024-49634-x

Adapted from a press release from Health Data Research UK

̽��ֱ��incidence of heart attacks and strokes was lower after COVID-19 vaccination than before or without vaccination, according to a new study involving nearly the whole adult population of England.

This research further supports the large body of evidence on the effectiveness of the COVID-19 vaccination programme, which has saved millions of lives worldwide

Samantha Ip

Paul_McManus

Vial of the AstraZeneca COVID-19 vaccine

Yes

Licence type:

Public Domain

Significant gaps in COVID-19 vaccine uptake may have led to over 7,000 hospitalisations and deaths

cjb250 — Mon, 15 Jan 2024 23:30:03 +0000

̽��ֱ��findings, published today in ̽��ֱ��Lancet, suggest that more than 7,000 hospitalisations and deaths might have been averted in summer 2022 if the UK had had better vaccine coverage.

With COVID-19 cases on the rise and a new variant strain recently identified, this research provides a timely insight into vaccine uptake and hesitancy and could inform policy-makers.

̽��ֱ��research relied on secure access to anonymised health data for everyone in all four nations of the UK, an advance which has only become possible during the pandemic.

Co-author Angela Wood, Professor of Health Data Science at the Victor Phillip Dahdaleh Heart & Lung Research Institute, ̽��ֱ�� of Cambridge and Associate Director of the British Heart Foundation Data Science Centre said: “This is the first epidemiological study to use individual-level anonymised health data covering the entire UK population. We have created a detailed, UK-wide picture of who is under-vaccinated against COVID-19 and the associated risks of under-vaccination.

“These results can be used to help create health policy and public health interventions to improve vaccine uptake. This approach could be extended to many other areas of medicine with great potential for new discoveries in the understanding and treatment of disease.”

Early COVID-19 vaccine rollout began strongly in the UK, with over 90% of the population over the age of 12 vaccinated with at least one dose by January 2022. However, rates of subsequent booster doses across the UK were not fully understood until now.

Scientists from England, Scotland, Northern Ireland and Wales – led by Health Data Research UK (HDR UK) and the ̽��ֱ�� of Edinburgh – studied securely-held, routinely collected NHS data from everyone over five years of age during 1 June to 30 September 2022. All data was de-identified and available only to approved researchers.

Data from across the four countries was then pooled and harmonised, a feat that was not possible until now. People were grouped by vaccine status, with under-vaccination defined as not having had all doses of a vaccine for which that a person was eligible.

̽��ֱ��findings reveal that the proportion of people who were under-vaccinated on 1 June 2022 ranged between one third and one half of the population – 45.7% for England, 49.8% for Northern Ireland, 34.2% for Scotland and 32.8% Wales.

Mathematical modelling indicated that 7,180 hospitalisations and deaths out of around 40,400 severe COVID-19 outcomes during four months in summer 2022 might have been averted, if the UK population was fully vaccinated.

Under-vaccination was related to significantly more hospitalisations and deaths across all age groups studied, with under-vaccinated people over 75 more than twice as likely to have a severe COVID-19 outcome than those who were fully protected.

̽��ֱ��highest rates of under-vaccination were found in younger people, men, people in areas of higher deprivation, and people of non-white ethnicity.

Researchers say the study – the largest ever study carried out in the UK – also ushers in a new era for UK science by overcoming challenges in uniting NHS data that is gathered and stored in different ways between devolved nations.

Professor Cathie Sudlow, Chief Scientist at Health Data Research UK and Director of the British Heart Foundation (BHF) Data Science Centre, said: “ ̽��ֱ��infrastructure now exists to make full use of the potential of routinely collected data in the NHS across the four nations of the UK. We believe that we could and should extend these approaches to many other areas of medicine, such as cancer, heart disease and diabetes to search for better understanding, prevention and treatment of disease."

Professor Sir Aziz Sheikh, Director of the Usher Institute at the ̽��ֱ�� of Edinburgh, HDR UK Research Director and study co-lead, said: “Large-scale data studies have been critical to pandemic management, allowing scientists to make policy-relevant findings at speed. COVID-19 vaccines save lives. As new variants emerge, this study will help to pinpoint groups of our society and areas of the country where public health campaigns should be focused and tailored for those communities.”

Reference
HDR UK COALESCE Consortium. Undervaccination and severe COVID-19 outcomes: meta-analysis of national cohort studies in England, Northern Ireland, Scotland, and Wales. Lancet; 16 Jan 2024; DOI: 10.1016/S0140-6736(23)02467-4

Adapted from a release from HDR-UK

Between a third and a half of the populations of the four UK nations had not had the recommended number of COVID vaccinations and boosters by summer 2022, according to the first research study to look at COVID-19 vaccine coverage of the entire UK population.

These results can be used to help create health policy and public health interventions to improve vaccine uptake

Angela Wood

KoldoyChris (Getty Images)

Girl being injected with COVID-19 vaccine

Yes

Type 2 diabetes diagnosis at age 30 can reduce life expectancy by up to 14 years

cjb250 — Tue, 03 Oct 2023 09:00:51 +0000

Even people who do not develop the condition until later in life – with a diagnosis at age 50 years – could see their life expectancy fall by up to six years, an analysis of data from 19 high-income countries found.

̽��ֱ��researchers say the findings, published in ̽��ֱ��Lancet Diabetes & Endocrinology, highlight the urgent need to develop and implement interventions that prevent or delay onset of diabetes, especially as the prevalence of diabetes among younger adults is rising globally.

Increasing levels of obesity, poor diet and increased sedentary behaviour are driving a rapid rise in the number of cases of type 2 diabetes worldwide. In 2021, 537 million adults were estimated to have diabetes worldwide, with an increasing number diagnosed at younger ages.

Type 2 diabetes increases an individual’s risk of a range of complications including heart attack and stroke, kidney problems, and cancer. Previous estimates have suggested that adults with type 2 diabetes die, on average, six years earlier than adults without diabetes. There is uncertainty, however, about how this average reduction in life expectancy varies according to age at diagnosis.

To answer this question, a team led by scientists at the ̽��ֱ�� of Cambridge and ̽��ֱ�� of Glasgow examined data from two major international studies – the Emerging Risk Factors Collaboration and UK Biobank – comprising a total of 1.5 million individuals.

̽��ֱ��earlier an individual was diagnosed with type 2 diabetes, the greater the reduction in their life expectancy. Overall, every decade of earlier diagnosis of diabetes was associated with about four years of reduced life expectancy.

Using data from US population it was estimated that, individuals with type 2 diabetes diagnosed at ages 30, 40, and 50 years died on average about 14, 10, and 6 years earlier, respectively, than individuals without the condition. These estimates were slightly higher in women (16, 11, and 7 years, respectively) than they were in men (14, 9, and 5 years, respectively).

̽��ֱ��findings were broadly similar in analyses using EU data, with corresponding estimates being about 13, 9, or 5 years earlier death on average.

Professor Emanuele Di Angelantonio from the Victor Phillip Dahdaleh Heart and Lung Research Institute (VPD-HLRI), ̽��ֱ�� of Cambridge, said: “Type 2 diabetes used to be seen as a disease that affected older adults, but we’re increasingly seeing people diagnosed earlier in life. As we’ve shown, this means they are at risk of a much shorter life expectancy than they would otherwise have.”

Dr Stephen Kaptoge, also from the VPD-HLRI, said: “Type 2 diabetes can be prevented if those at greatest risk can be identified and offered support – whether that’s to make changes to their behaviour or to provide medication to lower their risk. But there are also structural changes that we as a society should be pursuing, including relating to food manufacturing, changes to the built environment to encourage more physical activity, and so on.

“Given the impact type 2 diabetes will have on people’s lives, preventing – or at least delaying the onset – of the condition should be an urgent priority.”

̽��ֱ��researchers found that the majority of the reduction in life expectancy associated with diabetes was due to ‘vascular deaths’ – deaths related to conditions such as heart attack, stroke and aneurysms. Other complications such as cancer also contributed to lowering life expectancy.

Professor Naveed Sattar from the Institute of Cardiovascular & Medical Sciences, ̽��ֱ�� of Glasgow, added: “Our findings support the idea that the younger an individual is when they develop type 2 diabetes, the more damage their body accumulates from its impaired metabolism. But the findings also suggest that early detection of diabetes by screening followed by intensive glucose management could help prevent long-term complications from the condition.”

̽��ֱ��Cambridge team was supported by the Medical Research Council, British Heart Foundation, Health Data Research UK and NIHR Cambridge Biomedical Research Centre.

Reference
Emerging Risk Factors Collaboration. Life expectancy associated with different ages at diagnosis of diabetes: 23 million person-years of observation. Lancet Diabetes & Endocrinology; 11 Sept 2023; DOI: 10.1016/S2213-8587(23)00223-1

An individual diagnosed with type 2 diabetes at age 30 years could see their life expectancy fall by as much as 14 years, an international team of researchers has warned.

Given the impact type 2 diabetes will have on people’s lives, preventing – or at least delaying the onset – of the condition should be an urgent priority

Stephen Kaptoge

Elva Etienne (Getty Images)

Man using blood sugar measurement device to monitor diabetes - stock photo

̽��ֱ��text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Act now to prevent uncontrolled rise in carbon footprint of computational science

cjb250 — Mon, 26 Jun 2023 09:04:03 +0000

Writing in Nature Computational Science, researchers from the Department of Public Health and Primary Care at the ̽��ֱ�� of Cambridge argue that the scientific community needs to act now if it is to prevent a potentially uncontrolled rise in the carbon footprint of computational science as data science and algorithms increase in usage.

Dr Loïc Lannelongue, who is a research associate in biomedical data science and a postdoctoral associate at Jesus College, Cambridge, said: “Science has transformed our understanding of the world around us and has led to great benefits to society. But this has come with a not-insignificant – and not always well understood – impact on the environment. As scientists – as with people working in every sector – it’s important that we do what we can to reduce the carbon footprint of our work to ensure that the benefits of our discoveries are not outweighed by their environmental costs.”

Recent studies have begun to explore the environmental impacts of scientific research, with an initial focus on scientific conferences and experimental laboratories. For example, the 2019 Fall Meeting of the American Geophysical Union was estimated to emit 80,000 tons of CO2e* (tCO2e), equivalent to the average weekly emissions of the city of Edinburgh, UK. ̽��ֱ��annual carbon footprint of a typical life science laboratory has been estimated to be around 20 tCO2e.

But there is one aspect of research that often gets overlooked – and which can have a substantial environmental impact: high performance and cloud computing.

In 2020, the Information and Communication Technologies sector was estimated to have made up between 1.8% and 2.8% of global greenhouse gas emissions – more than aviation (1.9%). In addition to the environmental effects of electricity usage, manufacturing and disposal of hardware, there are also concerns around data centres’ water usage and land footprint.

Professor Michael Inouye said: “While the environmental impact of experimental ‘wet’ labs is more immediately obvious, the impact of algorithms is less clear and often underestimated. While new hardware, lower-energy data centres and more efficient high performance computing systems can help reduce their impact, the increasing ubiquity of artificial intelligence and data science more generally means their carbon footprint could grow exponentially in coming years if we don’t act now.”

To help address this issue, the team has developed GREENER (Governance, Responsibility, Estimation, Energy and embodied impacts, New collaborations, Education and Research), a set of principles to allow the computational science community to lead the way in sustainable research practices, maximising computational science’s benefit to both humanity and the environment.

Governance and Responsibility

Everyone involved in computational science has a role to play in making the field more sustainable: individual and institutional responsibility is a necessary step to ensure transparency and reduction of greenhouse gas emission.

For example, institutions themselves can be key to managing and expanding centralised data infrastructures, and in ensuring that procurement decisions take into account both the manufacturing and operational footprint of hardware purchases. IT teams in high performance computing (HPC) centres can play a key role, both in terms of training and helping scientists monitor the carbon footprint of their work. Principal Investigators can encourage their teams to think about this issue and give access to suitable training. Funding bodies can influence researchers by requiring estimates of carbon footprints to be included in funding applications.

Estimate and report the energy consumption of algorithms

Estimating and monitoring the carbon footprint of computations identifies inefficiencies and opportunities for improvement.

User-level metrics are crucial to understanding environmental impacts and promoting personal responsibility. ̽��ֱ��financial cost of running computations is often negligible, particularly in academia, and scientists may have the impression of unlimited and inconsequential computing capacity. Quantifying the carbon footprint of individual projects helps raise awareness of the true costs of research.

Tackling Energy and embodied impacts through New collaborations

Minimising carbon intensity – that is, the carbon footprint of producing electricity – is one of the most immediately impactful ways to reduce greenhouse gas emissions. This could involve relocating computations to low-carbon settings and countries, but this needs to be done with equity in mind. Carbon intensities can differ by as much as three orders of magnitude between the top and bottom performing high-income countries (from 0.10 gCO2e/kWh in Iceland to 770 gCO2e/kWh in Australia).

̽��ֱ��footprint of user devices is also a factor: one estimate found that almost three-quarters (72%) of the energy footprint of streaming a video to a laptop is from the laptop, with 23% used in transmission and a mere 5% at the data centre.

Another key consideration is data storage. ̽��ֱ��carbon footprint of storing data depends on numerous factors, but the life cycle footprint of storing one terabyte of data for a year is of the order of 10 kg CO2e. This issue is exacerbated by the duplication of such datasets in order for each institution, and sometimes each research group, to have a copy. Large (hyperscale) data centres are expected to be more energy efficient, but they may also encourage unnecessary increases in the scale of computing (the ‘rebound effect’).

Education and Research

Education is essential to raise awareness of the issues with different stakeholders. Integrating sustainability into computational training courses is a tangible first step toward reducing carbon footprints. Investing in research that will catalyse innovation in the field of environmentally sustainable computational science is a crucial role for funders and institutions to play.

Recent studies found that the most widely-used programming languages in research, such as R and Python, tend to be the least energy efficient ones, highlighting the importance of having trained Research Software Engineers within research groups to ensure that the algorithms used are efficiently implemented. There is also scope to use current tools more efficiently by better understanding and monitoring how coding choices impact carbon footprints.

Dr Lannelongue said: “Computational scientists have a real opportunity to lead the way in sustainability, but this is going to involve a change in our culture and the ways we work. There will need to more transparency, more awareness, better training and resources, and improved policies.

“Cooperation, open science, and equitable access to low-carbon computing facilities will also be crucial. We need to make sure that sustainable solutions work for everyone, as they frequently have the least benefit for populations, often in low- and middle-income countries, who suffer the most from climate change.”

Professor Inouye added: “Everyone in the field – from funders to journals to institutions down to individuals – plays an important role and can, themselves, make a positive impact. We have an immense opportunity to make a change, but the clock is ticking.”

̽��ֱ��research was a collaboration with major stakeholders including Health Data Research UK, EMBL-EBI, Wellcome and UK Research and Innovation (UKRI).

*CO2e, or CO2-equivalent, summarises the global warming impacts of a range of greenhouse gases and is the standard metric for carbon footprints, although its accuracy is sometimes debated.

Reference
Lannelongue, L et al. GREENER principles for environmentally sustainable computational science. Nat Comp Sci; 26 June; DOI: 10.1038/s43588-023-00461-y

For more information on energy-related research in Cambridge, please visit Energy IRC, which brings together Cambridge’s research knowledge and expertise, in collaboration with global partners, to create solutions for a sustainable and resilient energy landscape for generations to come.

Cambridge scientists have set out principles for how computational science – which powers discoveries from unveiling the mysteries of the universe to developing treatments to fight cancer to improving our understanding of the human genome, but can have a substantial carbon footprint – can be made more environmentally sustainable.

Science has transformed our understanding of the world around us and has led to great benefits to society. But this has come with a not-insignificant – and not always well understood – impact on the environment

Loic Lannelongue

geralt

Binary world

̽��ֱ��text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Licence type:

Public Domain