image credit- freepik
Most AI foundation models used in healthcare today are trained on data from Western populations, which can limit the accuracy and relevance in Singapore’s clinical settings.
As a national R&D initiative, Singapore Medical Foundation AI Model (SIMFONI) has been launched to address this gap by adapting existing foundation models using local clinical data and guidelines, and contextualises AI foundation models for Singapore’s multi-ethnic population, local disease patterns, clinical guidelines and care pathways, to support clinicians and improve patient outcomes across the public healthcare system.
SIMFONI’s early-phase work focuses on two areas of clinical need: clinical decision support for cardiometabolic conditions in primary care and multimodal AI to improve the diagnosis and management of eye diseases such as cataract, retinal diseases and glaucoma, with plans to expand to other clinical areas over time.
The longer-term vision is for its AI tools to be seamlessly embedded within the Electronic Medical Records (EMR) system, serving as a trusted companion to clinicians across all care settings.
Prof Robert Morris, Executive Director of SIMFONI, said, “AI has the potential to advance healthcare outcomes, but its impact depends on how effectively it is embedded into real-world clinical practice. Our mission is to develop and deploy trustworthy, clinically grounded AI tools that can be scaled across Singapore’s public healthcare system. By bringing together healthcare clusters, research institutes and government agencies, we aim to integrate AI into care delivery in a way that improves patient outcomes and provides sustainable care for all Singaporeans.”
