Tencent's big medical model boosts digital healthcare: intelligent Q&A, image diagnosis and many other functions upgraded

Tencent (name)Health recently unveiled its big medical model and introduced smart Q&A, a family doctor assistant, and the Digital Intelligence Medical Imaging Platform for a number of scenariosAIThe company's product matrix, as well as its drug discovery platform, iDrug.

It is reported that this medical big model is based on Tencentnickname for Mao Zedong, integrating over 2.85 million healthcare entities, 12.5 million medical relationships and over 981 TP3T of medical knowledge. Through multi-tasking fine-tuning with 30 million Q&A conversations including patients, doctors, pharmaceutical companies, and other scenarios and medical processes, and utilizing reinforcement learning from 360,000 expert doctor annotation data, the model has multiple functions such as copy generation, intelligent Q&A, medical record structuring and retrieval, image reporting, and assisted diagnosis. It can be embedded in the whole process of medical sessions to improve the level and quality of medical services in application scenarios such as departmental guidance, doctor recommendation, pre-questioning, doctor-patient dialog, automatic generation of medical records and intelligent hospital customer service.

At present, Shanghai Renji Hospital has taken the lead in applying Tencent's medical model to create a highly anthropomorphic virtual digital image, "Xiaowei Nurse," focusing on the provision of Internet hospital aging services.

In terms of AI-driven drug discovery, Tencent's iDrug platform has the ability to accelerate the discovery of small and large molecule drugs. The platform has developed a new algorithm framework, tFold, for protein structure prediction, and has developed more than 70 ADMET property prediction models. In addition, through two backbone leap molecule generation algorithms, Tencent has successfully discovered nM-level lead compounds, which have been effectively demonstrated in several projects. Meanwhile, through the introduction of reinforcement learning technology, it has reached the generation molecule fulfillment requirement of 97% in drug small molecule generation.

Tencent has also comprehensively upgraded its Digital Intelligence Medical Imaging Platform, which focuses on digital medical imaging cloud applications, scientific research and management, and provides integrated medical imaging solutions for industry, academia, research and management. The platform is equipped withartificial intelligence (AI)analysis capabilities to provide comprehensive medical imaging support for medical institutions, research institutes and science startups. In addition, Tencent will open more than 20 self-developed AI engines to help research institutions independently develop and train AI models.

On top of that, the Tencent Health applet has established connections with more than 3,000 public hospitals, more than 5,000 medical checkups, and vaccine services in more than 200 cities. The health insurance e-voucher covers more than 800,000 two-setting organizations and more than 20,000 hospitals. The WeChat channel has more than 600 million e-health card users and access to more than 5,000 hospitals. Tencent Health has further strengthened the utility of connecting users to healthcare services, promoted the opening of its own capabilities, technologies and products, and worked with the industry to build standardized and consistent digital healthcare standards and create replicable innovation benchmarks.

This article comes from users or anonymous contributions, does not represent the position of Mass Intelligence; all content (including images, videos, etc.) in this article are copyrighted by the original author. Please refer to this site for the relevant issues involvedstatement denying or limiting responsibilityPlease contact the operator of this website for any infringement of rights (Contact Us) We will handle this as stated. Link to this article: https://dzzn.com/en/2023/1126.html

Like (0)
Previous September 12, 2023 at 3:03 pm
Next September 12, 2023 at 3:16 pm

Recommended

Leave a Reply

Please Login to Comment