From research to clinical practice: Expert consensus on Neuroimaging AI tools for the Memory clinic (Neuro-AIM)

Abstract Although AI tools for neuroimaging show considerable promise in the diagnosis, prognosis, and management of neurodegenerative disorders, their uptake in memory clinics has been limited. A key barrier is lack of consensus on their effective design and implementation. Here we establish expert consensus on the specific goals, usage and challenges of AI tools for neuroimaging in the memory clinic using a Delphi process. Sixteen experts from clinical, academic, and industry backgrounds participated in three rounds of questionnaires, coordinated by the Imaging Working Group of the Deep Dementia Phenotyping (DEMON) network, with support from a patient and public involvement representative. Consensus was reached on eight statements covering four themes: purpose, quality, interactions with clinicians and memory clinics, and privacy and ethics. Implementation of these recommendations will further the adoption of AI neuroimaging tools from research to clinical practice, improving diagnostic and care pathways for patient benefit.