OMIKG FEATURED BY AWS AT AWS CLOUD AND AI DAY HANOI: AN AI SYSTEM THAT TRACES CHRONIC DISEASES TO THEIR MOLECULAR ROOTS
On September 29, 2026, in Hanoi, OmiKG, an evidence-based causal reasoning system for chronic diseases developed by OmiGroup on Amazon Web Services (AWS), was featured in the keynote session at AWS Cloud and AI Day. The keynote attracted more than 2,000 attendees, including 1,650 in-person and 350 online participants, with senior leaders from businesses among the audience.
30/09/2026
AWS Cloud and AI Day Hanoi is an annual technology event organized by AWS, bringing together developers, IT leaders, and business decision-makers to explore agentic AI, data analytics, cloud transformation, industry solutions, and modern application development. The OmiGroup team attended the event to learn from and connect with the broader technology community.
During the keynote session, Eric Yeo, Managing Director of AWS Vietnam, highlighted OmiKG as a notable example of applying AI to healthcare. He said: “OmiGroup’s work tackles one of healthcare AI’s most important challenges: making AI reasoning transparent, traceable, and explainable to clinicians. Their proof-of-concept demonstrates that a small, focused research team can use AWS to build something new and potentially impactful in healthcare, and we look forward to supporting them as they move from research validation to real-world application.”
OmiKG was developed to address the “black box” challenge in healthcare AI, where many existing systems cannot explain their reasoning process or trace conclusions back to their original sources of evidence. OmiKG maps patient clinical data onto a knowledge graph of disease mechanisms, with each causal relationship linked to a published source and level of medical evidence. This enables physicians to examine individual links, verify their sources, and trace diseases back to their underlying root causes rather than stopping at surface-level diagnoses. The system uses Amazon Bedrock to extract causal relationships from biomedical literature and analyze patient-specific causal chains, while Amazon EC2 provides the computing and storage infrastructure.
In a controlled evaluation, two independent clinical experts blindly assessed OmiKG’s results based on 20 clinical questions concerning the mechanisms of type 2 diabetes. OmiKG successfully identified 15 of 17 representative molecular mechanisms, while two other AI approaches identified only one and none, respectively.
Reflecting on OmiKG’s development journey, Nguyen Thi Trang Nhung, Head of AI Research at OmiGroup, said: “We started by building a nutrition advice system for diabetic patients and quickly discovered that the hardest problem was not accuracy, but verifiability. If clinicians cannot trace how an AI model reached its conclusions, they will not trust it. That realization drove us to pivot toward structured, evidence-grounded reasoning. Amazon Bedrock made it possible for a small research team to develop and validate this at the pace that would otherwise require significantly more resources.”
OmiKG’s presentation to thousands of attendees and business leaders at AWS Cloud and AI Day represents recognition of OmiGroup’s AI research capabilities, while also underscoring the collaboration between OmiGroup and AWS in developing transparent and trustworthy digital healthcare solutions.
Looking ahead, OmiKG will be presented at AMIA 2026, a leading global forum for biomedical and health informatics. In parallel, OmiGroup is exploring opportunities to pilot the integration of OmiKG with healthcare data platform partners and is in discussions with potential partners to commercialize the system, with Vietnam, Japan, and South Korea as priority markets.
.png)
