Artificial intelligence for early palliative referral in adult oncology: opportunities, challenges and future directions

Globally, AI-powered referral systems have a great deal of promise to enable earlier integration of palliative care in oncology. Among the main drawbacks are algorithmic bias, problems with data quality and the requirement for ethical supervision and clinical workflow integration. Although preliminary data appear promising, further prospective validation is necessary to guarantee that more referrals result in significant patient benefits. With a focus on patient-centred care, AI systems should support clinical judgement rather than replace it.