Tairex unveils multi-agent AI system for clinical collaboration
Tairex, an AI healthcare technology company incubated by Tsinghua University's Institute for AI Industry Research (AIR), has presented a multidisciplinary system in which specialized AI agents work alongside physicians on clinical cases. The Multidisciplinary Human-Agent Collaboration Ecosystem (MHAC) for Agent Hospital was shown on 21 October, according to the company.
- Tairex presented the MHAC ecosystem for Agent Hospital on 21 October.
- The system has 54 AI doctors across more than 20 clinical specialties.
- Tairex says its AI doctors exceed 96% accuracy on the MedQA dataset.
- Agents show reasoning and evidence in one interface, with discrepancies highlighted for the physician.
- The company cites GDPR and PIPA foundations and MLPS Level 3 certification.
From simulated training to real-world collaboration
According to Tairex, the system is trained in a simulated environment with millions of highly realistic AI patients. In that setting, a single AI doctor can carry out tens of thousands of simulated consultations every day. The result is a system of 54 AI doctors and millions of AI patients, covering more than 20 clinical specialties and tens of thousands of diseases.
The company says its AI doctors have reached an accuracy above 96% on the MedQA dataset.
How the agents work together on a case
When a patient's condition spans several specialties, the system dynamically activates the relevant agents so they work at the same time. Rather than operating in isolation, the agents present their clinical reasoning and supporting evidence in one unified interface. Discrepancies between them are highlighted so the physician can review them.
Tairex gave an example. An endocrinology agent proposed a beta-blocker for a patient with palpitations and a history of asthma. A pulmonology agent then flagged that non-selective beta-blockers could cause bronchoconstriction and suggested considering a selective beta-1 blocker.
Workflows, access and data protection
Tairex says the agents can give recommendations at the same time inside the clinical interface, so doctors can weigh interdisciplinary views without calling a separate meeting. Because the agents are modeled on specialists, they can support several departments and, potentially, reach primary care centers. The company argues this could make high-quality medical resources more accessible.
The company stresses that under this model the AI is meant to improve efficiency and support clinical decisions, not to make critical decisions independently.
On data security, Tairex states that its underlying products are built on the EU General Data Protection Regulation (GDPR) and South Korea's Personal Information Protection Act (PIPA), with controls governing the handling and transfer of sensitive data fields. It has also obtained China's Multi-Level Protection Scheme (MLPS) Level 3 certification.
What it means for healthcare institutions
By combining AI-assisted workflows with human-led clinical decision-making, Tairex says MHAC aims to help high-quality medical resources reach more healthcare institutions, including primary care facilities. The company frames this as a step toward more equitable access to care. The announcement gives no details on deployment, pricing or clinical trials, so the claims remain those of the company.
PR Newswire: Tairex lanza un sistema de IA multiagente
