Get the App
SLTechnology News&Howtos  ›  IT Information  › 

Microsoft announced that it will use GPT-4 in the medical field to help doctors respond to patients and analyze records.

Shulou Source: shulou.com Published: 2023-11-24 16:15:56 10月02日 Update

April 19, Monday, Microsoft and Epic Systems announced that they will introduce OpenAI's GPT-4 artificial intelligence language model to healthcare to help health care workers respond to patient information and analyze medical records.

Epic Systems is one of the largest medical software companies in the United States. Its electronic health record (EHR) software, such as MyChart, is used in more than 29% of emergency hospitals in the United States, and the electronic records of more than 305 million patients worldwide are kept in Epic. However, Epic's history of using predictive algorithms for health care in the past has attracted some criticism.

It is understood that GPT-4 can help doctors and health care workers automatically draft and respond to patient messages. Chero Goswami, CIO of UW Health, Wisconsin, said: "integrating generative AI into some of our daily workflows will increase the productivity of many of our providers and enable them to focus on clinical responsibilities that really need their attention."

GPT-4 also brings natural language query and "data analysis" to Epic's data discovery tool SlicerDicer, enabling medical institutions to search through large amounts of patient data and discover new trends. Microsoft says this will help "clinicians explore data in a conversational and intuitive way."

However, the collaboration between Microsoft and Epic has attracted the attention of large language model researchers, in part because GPT-4 can fabricate information that does not exist. According to the industry, natural language generation (NLG) has been studied in the field of health care for many years. Among them, the most important point is to provide non-misleading information.

Tags: Health care information patients data language Microsoft people health care healthcare domain analysis health care help doctors models electronics nature natural language software USA Apple Docker Huawei Linux macOS MariaDB Microsoft MySQL NVidia OPPO Reno Shulou Technology macOS Shulou Information Docker vpn