AI to forecast health interventions based on nationwide NHS data
The generative AI model, called Foresight, is being trained on de-identified data from 57 million people in England as part of a pilot study conducted by University College London (UCL) and King's College London (KCL).
De-identified data is data in which personal information has been stripped away, meaning it is not possible to link back to an individual, ensuring privacy. Access to the data is within the NHS England Secure Data Environment (SDE), a secure data and research analysis platform.
The model is being trained on routinely collected NHS data such as hospital admissions and Covid-19 vaccination rates. The model could make predictions about health outcomes across all demographics and for rare conditions due to the size of the dataset and its coverage of England's population.
The researchers also aim to harness the model to address health inequalities, analysing risks and outcomes at the population level.
UCL Institute of Health Informatics' Dr Chris Tomlinson, who is serving as lead researcher of the study, said: 'AI models are only as good as the data on which they're trained. So, if we want a model that can benefit all patients, with all conditions, then the AI needs to have seen that during training.
"Using national-scale data allows us to represent the kaleidoscopic diversity of England's population, particularly for minority groups and rare diseases, which are often excluded from research.'
Foresight comes at a time of increased focus on digital technology to level up healthcare in the UK by the government. The Health Data Research Service, a tool that simplifies access to health data to accelerate research, was launched in April 2025. Partnered with the Wellcome Trust, the government has pledged up to £600m to enhance the use of NHS data on a national scale.
UK Health Secretary Wes Streeting has touted the importance of harnessing NHS data since entering office in July 2024. In November, he remarked at a conference that citizens should 'view their data in the same way they view their taxes'.
In a statement following Foresight's announcement, Streeting said: 'I'm determined that we use this kind of groundbreaking technology to cut down on unnecessary hospital trips, speed up diagnosis times, and free up staff time.
'AI will be central as we bring our analogue NHS into the digital age to deliver faster and smarter care across the country.'
"AI to forecast health interventions based on nationwide NHS data" was originally created and published by Medical Device Network, a GlobalData owned brand.
The information on this site has been included in good faith for general informational purposes only. It is not intended to amount to advice on which you should rely, and we give no representation, warranty or guarantee, whether express or implied as to its accuracy or completeness. You must obtain professional or specialist advice before taking, or refraining from, any action on the basis of the content on our site.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
CNBC
28 minutes ago
- CNBC
Yoga, Zumba or HIIT? The best way to exercise, based on your personality type
Curating your fitness routine to better match your personality could help you get the most out of your workouts, a new study shows. The paper, published last month in Frontiers in Psychology, shows that certain personality traits may indicate which type of exercises people enjoy and how likely they are to stick with them. "We found that our personality can influence how we engage with exercise, and particularly which forms of exercise we enjoy the most," Flaminia Ronca, one of the study's co-authors and an associate professor at University College London, said in a press release. "It's OK if we don't enjoy a particular session," Ronca said. "We can try something else." Ronca and her fellow researchers recruited 132 adults, and placed them into two groups. One group was told to follow at-home workouts of cycling and strength training, and the other group was asked to follow their usual routines. Participants were given a questionnaire to determine their personality type and stress levels. By the end of the study, a total of 86 participants completed their group's assignment and surveys which asked which workouts they enjoyed the most before and after the experiment began. The paper focused on the Big Five personality traits used in psychology: Here are the workouts that each personality type found the most exciting. People who scored high in extraversion seemed to enjoy high-intensity workouts (HIIT) and team sports. Some exercises that extroverts should try are: Those who got high scores for conscientiousness tended to like goal-oriented exercises. They really enjoyed activities like training for a marathon or joining a run club. Exercises that conscientious people should explore are: People that scored high in neuroticism, or those who often experienced mood swings and anxiety, preferred light, one-on-one workouts. "This group might appreciate being given space for independence and privacy during an exercise program," Ronca said. Anxious people may benefit from having private sessions with a personal trainer or a Pilates instructor, and would likely avoid group classes. People who fall into the group of openness and agreeableness liked fun workouts and looked for variety. Exercises for open-minded and agreeable people to consider are: It is not at all surprising that introverts preferred to work out on their own and in their homes. Some exercises that introverts would likely gravitate towards are:
The Hill
an hour ago
- The Hill
Flu, COVID can reawaken dormant breast cancer cells: Study
Respiratory infections like COVID-19 and the flu can activate dormant cancer cells in breast cancer patients who are in remission, new research finds. The study, published in Nature, found that common viruses can reawaken small numbers of dormant breast cancer cells in the lungs. Researchers began investigating the link after the team noticed that U.K. patients who were in remission from breast cancer and tested positive for COVID later showed a two-fold increase in cancer-related deaths. They also analyzed a U.S. database that included nearly 37,000 patients and found that COVID infection was associated with a more than 40 percent increased risk of metastatic breast cancer in the lungs. Studies on mice found that influenza and COVID infections triggered dormant breast cancer cells after just days of infection. Within two weeks, researchers observed 'massive expansion' of the cancer cells into metastatic lesions by more than 100 times. Scientists have suspected that common viruses like Epstein-Barr can trigger some cancers. Human papillomavirus (HPV) is already documented to trigger cervical cancer. When it comes to breast cancer, however, research on human cells was limited, and it's not entirely known how the virus triggers the disease to spread. The findings suggest the body's immune response plays a role. After breast cancer goes into remission, a tiny number of cells remain dormant in lung, bone and liver tissue. Sometimes, inflammation can wake up the cells. In the mouse experiments, both influenza A and coronavirus only reawakened dormant cells if they triggered an inflammatory cytokine response. More research is needed to see if vaccination makes a difference when it comes to the possibility of reawakening dormant cells.
Yahoo
2 hours ago
- Yahoo
Millions on NHS waiting lists yet to have first appointment
Millions of people in England on NHS waiting lists are yet to have their first appointment, new data reveal. Figures from NHS England last month suggest nearly half of those waiting for hospital care have not had their first appointment with a specialist or a diagnostic test since their GP referral. An analysis by health data specialist MBI Health suggests nearly three million out of the 6.23 million patients (48 per cent) waiting for treatment are left in limbo. Experts referred to the issue as a 'frontlog' and warned the crisis 'has gone unchallenged for too long'. MBI's analysis also found that around 70 per cent of referral-to-treatment pathways fall into the category of being 'unseen' since the patient's GP referred them to a specialist. Delays in making a first assessment can lead to late diagnosis, worsening symptoms and pressure on emergency services. The analysis found that ear, nose and throat, trauma and orthopaedics, gastroenterology, ophthalmology and gynaecology and obstetrics departments were consistently the specialist departments with the greatest number of patients not seen for the first time. 'That's a breakdown' As part of the Government's 10-year health plan, the NHS is expected to meet its target of carrying out 92 per cent of routine operations and appointments within 18 weeks by March 2029 – a target that has not been achieved for almost a decade. The latest figures show how challenging that target will be given an estimated one million of the three million unseen patients have already gone more than 18 weeks without receiving any care. 'If accurate, three million people are trapped in an invisible waiting-list crisis, stuck without basic diagnostic tests of first appointments while their conditions worsen,' Rachel Power, the chief executive of the Patients Association, told the Guardian. 'The scale is staggering, as nearly half of all patients on a waiting list haven't been seen by anyone. That's not a healthcare service; that's a breakdown. 'These aren't just statistics. They're people checking their phones daily for hospital calls that never come, unable to plan their lives while their symptoms deteriorate.' Last month it was found people of working age are making up a growing proportion of those on the NHS waiting list for treatment in England. Data tables published for the first time by NHS England also show people in the most deprived parts of the country are more likely to wait more than a year to start hospital treatment than those in the least deprived. The figures, analysed by the PA news agency, showed 56.1 per cent of those on the list at the end of June this year were of working age (defined as age 19 to 64), up from 55.8 per cent a year ago and 55 per cent in June 2022. At the same time, the proportion of people on the waiting list under the age of 19 has fallen, standing at 10.8 per cent in June this year, down from 11.2 per cent a year earlier and 11.9 per cent in June 2022. The proportion who are over 65 has remained broadly unchanged at around 33.1 per cent. People of working age are also more likely to have to wait more than a year to start treatment (three per cent of patients in this age group at the end of June) than those over 65 (two and half per cent). However, the proportion is the same as those under 19 (also three per cent). An NHS spokesman said: 'NHS staff have made significant progress in reducing waiting lists in the last year, which are down by more than 260,000 since June 2024. 'All patients are assessed by clinicians as they are added to waiting lists, and we will continue with our plan to improve waiting times for patients throughout the year.' Broaden your horizons with award-winning British journalism. Try The Telegraph free for 1 month with unlimited access to our award-winning website, exclusive app, money-saving offers and more. Solve the daily Crossword
