AI-Assisted Variant Review Across Asia: Country-Level Expert Panels, Regional Collaboration, and Global Knowledge Sharing
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.
Related
- SARS-CoV-2 neutralising antibody profiles reveal variant specific antibody dynamics and regional differences in infection histories in Malawi
- AI-Assisted WES Variant Interpretation in Neurodevelopmental Disorders: A Narrative Review of Existing Tools.
- Limited knowledge exchange across biological subfields in agent-based modelling: an LLM-assisted bibliometric analysis
- Immersion 360, a european patient-partnered research project aimed at developing communication skills in paediatrics and raising awareness of interprofessional collaboration practice in partnership.
- Collaboration between advanced practice nurses and general practitioners in rural France
BibTeX
@misc{fujiwara2026aiassisted,
title = {{AI-Assisted Variant Review Across Asia: Country-Level Expert Panels, Regional Collaboration, and Global Knowledge Sharing}},
author = {Toyofumi Fujiwara and George Devasia and Rutharra Ghayadthri Manisekaran and Vasanthan Jayakumar and Yosuke Kawai and Shuichi Kawashima and Yuko Kitano and Francis A. Tablizo and Shoichiro Takahashi and Piyakrit Wongboonchai},
howpublished = {BioHackrXiv},
year = {2026},
month = sep,
doi = {10.37044/osf.io/e5g6s_v1},
url = {https://osf.io/preprints/biohackrxiv/e5g6s_v1/},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - AI-Assisted Variant Review Across Asia: Country-Level Expert Panels, Regional Collaboration, and Global Knowledge Sharing
AU - Toyofumi Fujiwara
AU - George Devasia
AU - Rutharra Ghayadthri Manisekaran
AU - Vasanthan Jayakumar
AU - Yosuke Kawai
AU - Shuichi Kawashima
AU - Yuko Kitano
AU - Francis A. Tablizo
AU - Shoichiro Takahashi
AU - Piyakrit Wongboonchai
PY - 2026
DA - 2026/09/04
PB - BioHackrXiv
DO - 10.37044/osf.io/e5g6s_v1
UR - https://osf.io/preprints/biohackrxiv/e5g6s_v1/
AB - 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.
ER -