EHR vendors, Epic and eClinicalWorks, have launched a generative artificial intelligence (GPT) features at the HIMSS23 conference. The tools enable provider organizations to search and summarize contextual information with natural language searches powered by cloud computing. eClinicalWorks’ GPT integrations allow operational queries, actions on patient telephone encounters, progress note creation, and revenue cycle management. Epic is developing a two-tool with Azure’s HIPAA-compliant GPT3 to support clinical efficiency and organizational effectiveness. Salesforce has also integrated GPT into its CRM, allowing care teams to discuss clinical and nonclinical data in a HIPAA-compliant environment.
The HIMSS23 conference saw the launch of new generative artificial intelligence (GPT) features from two leading electronic health record (EHR) vendors, Epic and eClinicalWorks. The tools use Microsoft’s Azure OpenAI Service, which was launched in March, to integrate GPT into their software and allow provider organizations to search and summarize contextual information with natural language searches powered by cloud computing.
EHR developers can now integrate custom large language model experiences directly into their applications using Azure, according to Microsoft. They can imbibe existing bots and other tools with the power to use conversational language “to make life simple for end-users,” as eClinicalWorks described it.
eClinicalWorks demonstrated a new AI-powered virtual assistant that is still in development. The GPT integration allows operational queries, actions on patient telephone encounters, and progress note creation. The tool provides recommendations based on what the patient is calling for, allowing nurses to quickly create a response based on the patient’s message.
Doctors will be able to use eClinicalWorks GPT to create progress note summaries and publish them to the patient record. They can also print results, such as exercise instructions, for the patient. Integrated AI can help providers with revenue cycle management by searching quickly in the EHR for reports and then exporting the data.
At HIMSS23, Epic also showcased fresh GPT integrations. In its Nebula cloud, the EHR company is creating a variety of automation using large language models (LLMs), neural nets, and predictive models. Epic is focused on accuracy, user experience, and ethics as there are a lot of unknowns with LLMs.
In production now is a new two-tool using Azure’s HIPAA-compliant GPT3 that supports clinical efficiency and organizational effectiveness. The “in-basket” integration to support answering medical questions from patients is being tested with some customers, including UC San Diego Health, UW Health in Madison, Wisconsin, and Stanford Health Care. The automation can identify which of the patient’s prescribed medications is for the thyroid and how many refills are left if the patient requests an update on their thyroid medication. It can also present options for the patient.
Salesforce, which announced its Einstein GPT for CRM in early March, is also integrating GPT into its software. Healthcare providers can pull data from the EHR into the CRM, and in Slack, care teams can discuss clinical and nonclinical data in a HIPAA-compliant environment. With the Einstein GPT integration, they can summarize chat information between multiple members of the care team and complete Salesforce CRM tasks.
Despite the benefits of generative AI, there are still some challenges that need to be worked out before scaling GPT in healthcare. For example, customers need to be able to rely on and trust the source of information. On the roadmap, customers will be able to use their data or bring their own LLM in, so they can trust the AI’s source, but there is a lot to work out for healthcare.
