An artificial intelligence virtual assistant named Dora Care is conducting telephone consultations with patients in the NHS in a two-year project to help clinicians monitor people suffering from long-term illnesses.
AI Calls Target Osteoporosis Care
Treating fractures costs the NHS roughly £4.5 billion annually, while osteoporosis affects 3.5 million people in the UK, particularly women and individuals over 50.
In its initial trial phase, the system focuses on osteoporosis. Fracture liaison services monitoring these patients face staffing shortages across many UK regions. Researchers at the University of York are assessing whether automated systems can reliably manage routine patient follow-ups.
The project uses generative AI to hold natural, spoken conversations with patients over the phone. Linguistics experts analysed empathetic behaviours by human clinicians to ensure the system sounds neither robotic nor unsympathetic.
We started with a question of ‘how might a patient experience being empathised with’? To do this, we explored how expert human clinicians display empathy, and we found it’s not only what they say, but how they say it, and also when in a clinical conversation they do this. We then looked at how the same linguistic behaviours could be designed into Dora’s conversations.
Dr Adam Brandt, senior lecturer in applied linguistics at Newcastle University
The trial runs under medical and ethical approval on a voluntary basis, serving as a supplement to regular NHS care rather than a replacement.
Safety Frameworks Built for Clinicians
To oversee the software’s performance across the study, safety experts at the University of York’s Centre for Assuring Autonomy are creating a dedicated safety framework.
Any development and deployment of AI within a healthcare setting must be backed by robust safety evidence and assurance. We know from other projects in healthcare settings, that safety and trust is key to clinicians feeling confident in deploying this technology, and having a clear understanding of how it can assist them in the decision making process. AI systems that have been tried and tested, and indeed do the job they have been tasked with, can still be underutilised if the safety assurance is not clear to those who are using them.
Professor Ibrahim Habli, Research Director at the University of York’s Centre for Assuring Autonomy
Dr Kate Preston, from the University of York’s Centre for Assuring Autonomy, pointed to the dual challenge of engineering empathy for vulnerable patients while maintaining high safety standards to assist trained clinicians in making optimal medical decisions.
Government agency Innovate UK is funding the project, which is spearheaded by technology company Ufonia alongside Newcastle University and the University of York. Dr Aisling Higham, the project’s chief investigator at Ufonia, said: We are pushing the boundaries of how empathetic and safe autonomous clinical AI assistants can be used to support patients and clinicians.
Phone Tracking Tested in Cancer Care
During a trial involving 100 individuals at the Uganda Cancer Institute (UCI), the tracking system flagged health concerns that prompted clinicians to recall 18 patients to the hospital prior to their booked appointments.
Similar mobile phone monitoring systems are being deployed internationally to bridge gaps in post-treatment care. Doctors at UCI are exploring whether a simple mobile phone call can help bridge this gap in cancer care.
Dr. Kabukye, who is involved in the pilot at UCI, explained that manual follow-ups are impractical for resource-constrained clinics.
It is not a solution to all the challenges in cancer care. Instead, its purpose is to help healthcare providers understand how patients are doing between visits and determine which symptoms require attention.
Dr. Kabukye
Can automated phone calls reliably replace human follow-ups without missing critical patient symptoms?