"Chief-level AI Doctor" officially launched, medical AI enters a new phase

Against the backdrop of the rapid development of artificial intelligence technology, the medical industry is undergoing a profound transformation. Recently, the Quark Health Large Model successfully passed the written examination evaluation of 12 core disciplines by chief physicians, becoming the first AI model in China to complete this challenge, marking the formal entry of medical AI into the "chief-level" stage.

This breakthrough not only indicates that AI has achieved significant improvements in the depth and breadth of medical knowledge, but also suggests that AI will play a greater role in the future in areas such as auxiliary diagnosis and treatment, patient education, and psychological support.

In the test on July 23, the Quark Health Large Model achieved excellent results in exams covering multiple key areas, including general medicine, and performed outstandingly in high-difficulty questions such as multiple-choice questions and case analysis questions.

"We are not training AI to answer medical questions, but training it to learn medical thinking," said Xu Jian, head of the Quark Health algorithm team. The model has achieved deep integration and application of medical knowledge through the construction of a large-scale data resource library, systematically solving correctness issues, and improving reasoning capabilities.

In terms of data construction, the Quark Health Large Model uniformly processes professional data such as web data, books, guidelines, and drug instructions, combined with clinical cases and structured thinking of medical experts, to build a high-quality training dataset.

The accuracy of the model for diseases with diagnostic tests has reached 90.78%, approaching the level of specialists; for difficult diseases, it has also reached 85.51%, demonstrating strong medical reasoning capabilities.

"AI can assist doctors, providing doctors with more exploration space and suggestions," said Xu Jian. Currently, the Quark Health Large Model has been fully integrated into Quark AI Search, and users can invoke it when querying health issues by selecting deep search.

The combination of doctors and AI has become a major trend. Li Houmin, director of the Department of Dermatology and Venereology at the Peking University Health Science Center, said that AI has achieved significant results in dermatology applications and can help general practitioners and grassroots doctors improve their diagnostic capabilities.

Wang Huiling, director of the Center for Mental Health at Wuhan University People's Hospital, said that AI can play an important role in patients with mental illness, alleviate patients' psychological anxiety, and provide timely health advice.

The application scenarios of the Quark Health Large Model are continuously expanding. One of its core breakthroughs is the construction of "slow thinking capability," which integrates chain reasoning and multi-stage clinical deduction path modeling, enabling the model to derive final answers stage by stage and in-depth when facing complex medical issues.

With the continuous advancement of AI technology, the information gap between patients and doctors is narrowing, and more people can actively participate in the diagnostic and treatment process with the help of AI, thereby increasing the availability and accessibility of medical resources.

In the future, with the launch of more health large models, AI will play an increasingly important role in the medical field, providing patients and doctors with more efficient and accurate medical services.