Research

The discovery AI platform is a production level, secure sandbox for building AI tools from huge multi-domain medical databases.

• Collaborative AI Development: Anonymously links multi-institution datasets yet share data securely and equitably between clinicians, researchers, and data scientists. By linking and aggregating multiple clinical and research databases, it facilitates the joint development of machine learning tools.
• Security and Governance: The platform is fortified by a proprietary blockchain technology coupled with enterprise-grade security. Access to this platform is unified through a cluster-wide governance policy.
• AI Integration with EMR: Multiple AI tools have been built on this platform and are integrated with the existing EMR system to alert clinicians directly. The computing architecture of the platform is able to host multiple modular machine learning systems, all using data from the same electronic record source. This juxtaposition of machine learning modules in one system allows machine learning tool designers to aggregate the outputs of various machine learning algorithms into fewer alerts, thus reducing alert fatigue for doctors.
• Continued Development: This platform and associated AI technologies are developed in-house with proprietary technology from the NUS School of Computing and partners in other institutes of higher learning.