Important progress has been made in the field of Chinese medicine. The "Concord Taichu" rare disease AI model jointly developed by Peking Union Medical College Hospital and the Institute of Automation of the Chinese Academy of Sciences has officially entered the clinical application stage recently. This move not only marks a breakthrough in my country's rare disease diagnosis technology, but also provides new tools for improving clinical medical efficiency.
The research and development of this AI model is due to the accumulation of rare disease knowledge bases in my country over the years and the support of genetic testing data for Chinese populations. As the first international rare disease model to adapt to the characteristics of the Chinese population, its purpose is to help doctors identify and diagnose rare diseases more quickly and accurately, significantly shortening the patient's diagnosis time. This is undoubtedly a major boon for patients with rare diseases.
In the development of traditional artificial intelligence models, massive data is often required for training, but due to the scattered cases of rare diseases and scarce data, traditional methods are difficult to apply effectively. In this regard, the R&D team adopted an innovative extremely small sample cold start technology, which requires only a small amount of data combined with medical knowledge to achieve the auxiliary decision-making function of the entire diagnosis and treatment process. This innovation makes the application of AI models more feasible in clinical settings.
In addition, the model has successfully introduced the deep reasoning ability of DeepSeek-R1, which has three core advantages: the decision logic is in line with clinical thinking patterns, can effectively suppress AI hallucinations, and support autonomous iteration of knowledge. Through these advantages, the model can better adapt to complex and changeable clinical needs and provide strong support for doctors' decision-making.
At present, the initial consultation and appointment function of this AI model has been opened to patients for testing. In the future, it will gradually connect to the rare disease joint outpatient online diagnosis and treatment services of Peking Union Medical College Hospital, and it is planned to be promoted nationwide to further promote the construction of my country's rare disease diagnosis and treatment collaboration network.
The successful application of this technology not only demonstrates China's cutting-edge technology level in the field of medical artificial intelligence, but also points out a new direction for the diagnosis and treatment of rare diseases in the future, greatly improving patients' medical experience and medical efficiency.