Researchers are using artificial intelligence (AI) to “digitally simulate” families struggling under the effects of the cost of living crisis to simulate the most effective ways to help.
It is one of more than a dozen projects covering data analytics and machine learning launched to help cope with the winter pressures facing the NHS.
The health service is struggling with high numbers of flu and COVID cases, a massive backlog exacerbated by the pandemic, and growing wait times for ambulance, first aid, and routine care.
The 16 projects, launched by the UK’s Health Data Research (HDR), hope to have results by the end of March.
Health Secretary Steve Barclay said the aim was to channel the “spirit of innovation” that led to the rapid rollout of a coronavirus vaccine, with the government providing £800,000 in funding.
If you are an NHS worker and would like to share your story anonymously with us, please email NHSstories@sky.uk
While many projects seek to use technology to reduce stress on hospital staff, others seek to address some of the root causes of problems facing the NHS.
One such initiative is to use existing data and artificial intelligence to “digitally model” the home environment and simulate interventions to improve people’s health at home – especially children.
Dr Martin Chapman, from King’s College London, explained: “Living in cold, damp and musty homes can lead to chest problems in children and mental health problems in teenagers, while rising energy costs mean more than ever More people are living in thermal poverty.
“We are investigating the effectiveness of interventions such as the Support Energy Act on young people’s health by using artificial intelligence to digitally simulate their home environment and assessing the impact of simulated interventions.
“This will help guide future policy changes to improve health outcomes, reduce inequalities and, in turn, reduce pressure on NHS services.”
Ambulance response times worst on record
How many free beds are there in your local hospital?
What are the projects?
Using the same infrastructure as Siren, It collates and publishes regular public data on COVID at the height of the pandemicthe winter stress substudy will be expanded to include influenza and a common childhood illness called Respiratory syncytial virus (RSV).
Another project aims to use artificial intelligence to help clinicians more easily identify high-risk patients.
By analyzing patient data, the AI model can suggest the most appropriate ward for the patient, the ward with the greatest immediate risk of deterioration, and when the patient should or should not be discharged.
Also focusing on time to discharge is a project called DS4SmartDischarge.
This uses machine learning (the process of teaching a computer to do something on its own) to help the computer classify patients according to their risk for different discharge outcomes.
Another team of paramedics, hospital leaders and the Acute Medicine Society is also using machine learning to help build a model that can identify patients who need same-day emergency care.
Patients will be graded based on data such as blood pressure, medications and bedside tests, helping staff make decisions within four hours of a patient’s admission.
Project leader Professor Elizabeth Sapey said the work would help “reduce inequalities in care and relieve pressure on emergency services”.
“Respond quickly to changing pressures”
While these projects come too late for the current crisis gripping health services, it is hoped that they will produce results that will contribute to better coping in the long term.
HDR chief scientist Professor Cathie Sudlow said they would delve into “key pain points” in the NHS.
“By using existing data, research teams and infrastructure, these projects are able to respond quickly to changing pressures on the NHS,” she added.
Each project works with analysts from the Department of Health, which sponsors the programmes; the Office for National Statistics; and the UK Health Security Agency.
Once the findings are delivered in March, they are expected to be published later this year.