AI-Assisted Variant Review Across Asia: Country-Level Expert Panels, Regional Collaboration, and Global Knowledge Sharing
Year: 2026
Type: preprint
Abstract: Genome and exome sequencing have substantially advanced the diagnosis of rare and undiagnosed diseases, but moving from large variant sets to evidence-based interpretation still requires substantial expert work. Across Asia, population genomic resources and expertise in genomic medicine are expanding, yet variant prioritization, expert review, and the accumulation and sharing of reviewed knowledge remain fragmented across countries and institutions. During MedHackathon Asia 2026 in Singapore, participants from institutions in Japan, Singapore, the Philippines, and Thailand examined these shared challenges and developed a common platform concept and initial implementations that connect variant prioritization and evidence organization, structured expert review, and reviewed-knowledge sharing as a single workflow. Each country could operate its own expert panels on this common foundation, exchange reviewed evidence across Asia, and ultimately contribute appropriate information to global knowledge resources. Even within such a platform, however, expert review requires substantial manual effort to structure phenotype information, search the literature, extract and organize evidence, prioritize candidates, and retrieve previous reviews. We therefore argue that the principal value of artificial intelligence (AI) is not to replace expert interpretation, but to automate or semi-automate these information-gathering and organization tasks so that experts can concentrate on assessing evidence and making final decisions. This report discusses how AI can support this workflow, where expert governance must remain decisive, and how country-operated expert panels could develop into a regionally connected network linked to global variant knowledge sharing.
Language: English
Topic: Genomics and Rare Diseases
Subfield: Genetics
Domain: Life Sciences
Open Access status: green
OpenAlex ID: W7208754323