The researchers have pioneered the first research-informed Chatbot-Assisted Self-Assessment (CASA) strategy that is designed specifically for ethnically diverse communities, the approach uses conversational AI to provide users with personalised health assessments and actionable recommendations.

Funded by the NHS AI Lab and The Health Foundation, the CASA protocol was co-developed with input from underrepresented groups, ensuring its design aligns with the needs of ethnically diverse communities. The study revealed that chatbots that provided explanations for medical inquiries used in self-assessment were deemed appropriate by participants for discussing sensitive health issues, including sexual health screening, and emphasised the importance of anonymity and trust in AI systems.

Conversational AI tools utilising the CASA protocol, developed using the above findings, can therefore help users who are reluctant to discuss sensitive health issues with healthcare professionals to access medical care.

Dr Tom Nadarzynski, who led the study at the University of Westminster, said: ‘The CASA protocol demonstrates how AI can be co-designed with diverse communities to enhance engagement, trust, and accessibility in healthcare. By ensuring that chatbots are inclusive, we can tackle longstanding health inequalities.'

The CASA protocol is also adaptable to other areas, including chronic disease management and mental health support, and holds potential for wider healthcare applications to address critical health disparities.

The research has been published in the journal PLOS Digital Health.