From virtual training to practical collaboration
In a simulated environment with millions of highly realistic AI patients, an AI doctor can conduct tens of thousands of simulated consultations daily.
This intensive virtual training results in a system consisting of 54 AI doctors and millions of AI patients, covering more than 20 clinical specialties and tens of thousands of diseases. The AI doctors have achieved an accuracy of over 96% using the MedQA dataset.
When a patient’s condition involves multiple specialties, the system dynamically activates relevant agents that work together simultaneously. Instead of operating in isolation, these agents present their clinical considerations and evidence on a unified user interface, highlighting any discrepancies for review by a human physician.
When an endocrinology agent suggested a beta-blocker for a patient with a history of palpitations and asthma, a pulmonology agent pointed out that non-selective beta-blockers could induce bronchoconstriction and suggested considering a selective beta-1 blocker.
Redesigning clinical workflows through AI collaboration
Specialized AI agents can provide recommendations simultaneously within the clinical interface, allowing physicians to consider interdisciplinary perspectives without having to wait for a separate meeting.
The system can also expand access to specialist medical expertise by enabling AI agents, modeled on specialist physicians, to support multiple departments and potentially reach primary care facilities, thereby making high-quality medical resources available to a wider audience.
In this model, AI is designed to increase efficiency and support clinical decision-making, rather than making critical decisions independently.
Data security is also integrated into the system design. Tairex’s underlying products comply with the EU General Data Protection Regulation (GDPR) and the South Korean Personal Data Protection Act (PIPA) and feature control mechanisms for handling and transferring sensitive data fields. The company has also received Level 3 certification under the Chinese Multi-Level Protection Scheme (MLPS).
By integrating AI-powered workflows into human-led clinical decision-making, Tairex’s multidisciplinary human-AI collaboration ecosystem aims to make high-quality medical resources available in more healthcare settings, including primary care settings, thereby bringing more equitable access to healthcare closer to reality.
