This week, Epic hosted its annual Users Group Meeting, a multi-day gathering that brought together thousands of healthcare leaders at the EHR giant’s headquarters in Verona, Wisconsin.
During the meeting, Epic announced that it is developing hundreds of different AI bots to assist clinicians, payers and patients. Below are the three most notable projects that the company teased at its conference.
AI charting
Epic is building an AI charting tool in collaboration with its longtime partner Microsoft. The company is seeking to offer its own native documentation solution amongst a sea of third-party models — including Microsoft’s Dragon Ambient AI tool, as well as the tools sold by companies like Abridge, Ambience Healthcare, DeepScribe and Suki.
This new tool, which is expected to be available early next year, will listen to patient visits and automatically generate clinical notes within Epic’s workflow. It will use Epic’s Haiku and Canto technology to record patient conversations, and then Microsoft’s Dragon Ambient AI system to power transcription and note generation.
“In March, we introduced Microsoft Dragon Copilot — a comprehensive clinical AI assistant designed to streamline workflows and enhance the clinician-patient experience. We’re proud to be collaborating with Epic to explore how we can bring our core Dragon ambient AI technology to Epic’s new AI Charting capability to further improve care delivery,” Joe Petro, corporate vice president of Microsoft health and life sciences division, said in a statement.
Cosmos AI
Epic is creating a generative AI model based on its Cosmos dataset, which spans over 16 billion deidentified clinical encounters from 300 million people.
The company is developing “the Cosmos Medical Event Transformer,” or CoMET. This model is being trained on data from hundreds of millions of patients, which will allow it to spot patterns in how illnesses progress, as well as predict what might happen next during the course of a patient’s care, according to a new report from researchers at Epic, Microsoft and Yale School of Medicine.
Epic said this model is unique because it is based on real clinical data — not internet text — making it more useful for clinicians and health systems.
“To enable personalized medicine and [real world evidence] at scale for routine clinical decision-making, we need tools that can learn from the integrated patient record and can answer complex medical inquiries with flexibility, retrieving the right [real world evidence] to support clinical decision-making across a wide variety of contexts,” the report read.
Art, Penny & Emmie
Epic announced some new AI assistants across its platform, each with its own human name.
The clinician-facing tool, named Art, is built to suggest parts of documentation and give diagnostic insights during patient visits. The tool designed for revenue cycle management, called Penny, automates coding and denials appeals.
Epic’s new patient-forward AI assistant, named Emmie, helps users with scheduling, visit preparations, lab result explanations and general health advice.
Photo: DBenitostock, Getty Images
