Britain’s National Health Service (NHS) is famous for offering free medical treatment to all UK citizens. Despite this, uptake of some services remains low, particularly in certain ethnic demographics.
The British government has spent many years trying to reduce these inequalities – and now they are investigating how artificial intelligence (AI) can help bridge the gap. NHSx – the NHS’ AI lab and health foundation – has a mission “to ensure NHS patients are amongst the first in the world to benefit from leading AI,” and “a responsibility to ensure those technologies don’t exacerbate existing health inequalities.”
As part of these efforts, NHSx has recently identified four AI projects that will benefit from additional investment.
Encouraging HIV testing with chatbots
Minority ethnic communities within the UK are generally reluctant to be tested for sexually transmitted infections (STI) like AIDS. As a result, infections spread further and more quickly within these groups.
The University of Westminster is currently developing an AI-powered chatbot to connect with people who are at risk of catching an STI. The chatbot will provide advice and encourage people to get tested for infections. They will also collect data that allows the researchers to create new chatbots that are tailored to the specific needs of minority ethnic communities.
Improving maternity outcomes
Minority ethnic communities in the UK also tend to be disproportionately affected by maternity incidents that place the health of mother and baby in danger. Researchers at Loughborough University have been using artificial intelligence to automatically analyze vast amounts of data collected from pregnant women using the NHS.
This analysis is expected to help medical professionals understand how a range of causal factors combine, interact and lead to maternal harm. This will make it easier to design interventions that are targeted and more effective for these groups to reduce infant mortality rates and childhood illnesses.
Increasing accuracy of diabetes detection
The NHS already has a successful program for detecting diabetes using retinopathy – a scan of the patient’s eyeball that reveals damage caused by the condition. There are concerns however that the image analysis system may not be accurate for all patients.
Researchers from St George’s Hospital, the University of London and Moorfields Eye Hospital will refine and optimize the AI algorithms used to analyze retinopathy images. By making AI systems more accurate, treatment for diabetes will improve across all ethnicities.
Ensuring ethical data processing
Artificial Intelligence systems are only as good as the datasets they are built on. If those datasets do not contain enough information about ethnic minorities, the AI system will not work across demographic groups.
University Hospitals Birmingham NHS Foundation Trust has been tasked with helping to develop a set of standards that ensure AI datasets are ethical, inclusive and effective. Which means that all artificial intelligence systems built by the NHS will better serve the UK’s patients.
Many of the most exciting uses of artificial intelligence are in the healthcare sector. And it is clear from these new projects that the NHS is using technology to improve healthcare outcomes for the UK.