China speeds up use of AI in healthcare
China’s West China Hospital of Stomatology uses an AI-powered 'smart brain' to diagnose over 30 dental diseases within seconds, generating visualized charts for patients, while a clinical-grade large model assists junior doctors with 80-90% accuracy. The country’s 2025 AI healthcare guidelines and the 15th Five-Year Plan (2026-30) aim to integrate AI into assisted diagnosis, precision medicine, and health management, though challenges like data gaps and misdiagnosis risks persist.
China is accelerating the adoption of artificial intelligence in healthcare, with the West China Hospital of Stomatology deploying an AI-powered system capable of diagnosing more than 30 common dental diseases in seconds. The system also produces visualized diagnostic charts to improve patient understanding of their conditions, reducing the time doctors previously spent explaining complex medical terms. At the hospital, a clinical-grade large model serves as a 'cloud mentor' for junior doctors, enabling early disease detection with an accuracy of 80 to 90 percent. This reflects a broader national push, as China issued guidelines in 2025 to promote AI tools in healthcare, aiming to enhance service quality. The 15th Five-Year Plan (2026-30) further emphasizes the orderly application of digital and intelligent technologies in assisted diagnosis, precision medicine, health management, and medical insurance services. As of May 1, 2025, China had released 300 medical large models, and county-level remote medical imaging services had handled over 68 million cases. These advancements are making AI a critical tool for grassroots healthcare, though challenges remain. Limited access to high-quality medical data and the risk of misdiagnosis are key concerns, prompting calls for stronger collaboration between the medical community and tech industry to build comprehensive datasets covering imaging, pathology, and biochemical tests.
This content was automatically generated and/or translated by AI. It may contain inaccuracies. Please refer to the original sources for verification.