With publicly accessible source code and performance benchmarks, Hyperscribe sets the new standard for AI governance in healthcare
Canvas Medical, the EMR company accelerating everyday medicine, announced the launch of Hyperscribe, an open source artificial intelligent (AI) copilot that uses ambient audio to write clinical documentation and orders collaboratively with other AI agents. Built with the Canvas software development kit (SDK), Hyperscribe leverages instant access to complete patient medical data, continuous real-time event streams and agentic control of the Canvas EMR user interface, setting a new precedent for accessibility, transparency and effectiveness in clinical workflow automation.
AI governance in healthcare is becoming increasingly crucial as organizations both broaden and deepen their adoption of AI-powered products to streamline operations, enhance quality of care and improve financial outcomes. While entities such as the Coalition for Health AI and the Joint Commission have made efforts to define AI governance frameworks, practical examples of transparent evaluations and open benchmarks are virtually nonexistent. With the release of Hyperscribe, Canvas is setting a new governance standard by publishing reproducible evaluation code, the underlying evaluation data set and a growing set of benchmarks comparing different foundation models with Hyperscribe and other third-party AI scribes and copilots.
“Our customers long ago decided that an out-of-box EMR would fail them and now they are raising the bar again. We are seeing explosive demand for AI agents that can do work in Canvas, in collaboration with the care team,” said Adam Farren, CEO of Canvas Medical. “With Hyperscribe we are accelerating into that future, demonstrating a new level of compounding value from agents working together on the Canvas platform, made possible with our publicly-available developer tools.”
Also Read: Ansys & NVIDIA Showcase In-Silico Heart Research at GTC
Hyperscribe unlocks deeper functionality than competing scribe solutions. Key features include:
- Composable Chaining: different tasks performed in a Canvas EMR are automatically connected; outputs from one task can immediately trigger and provide information for the next task. This helps streamline processes like patient referrals, eligibility verification, preparing insurance claims and supporting clinical decisions.
- Complete Patient Context: leverages the patient’s full medical record and ongoing updates from prebuilt data integrations. This ensures that the information is always accurate, structured correctly and follows an organization’s safety guardrails and clinical guidelines.
- Order Execution with Guardrails: far beyond ambient speech recognition, Hyperscribe uses extensive clinical informatics guardrails to safely interpret conversations and accurately infer details about vocalized observations and care plans.
- Real-Time Experience: continuous updates to the patient record and note during an appointment give clinicians a live, up-to-date view of documentation and orders. Clinicians can edit anytime and Hyperscribe will continue running with the coalesced multi-author note.
- Open Source Development: the code and evaluation framework is available for anyone to use, meaning organizations can enhance it on their own, integrate their foundation model of choice or customize their own solutions for specific use cases.
“Hyperscribe would not be possible without the incredible power of the Canvas SDK, which has been such an important body of work at Canvas Medical,” said Andrew Hines, founder and chief technology officer at Canvas Medical. “Hyperscribe demonstrates how quickly customers and partners can innovate with the Canvas platform using tools that don’t exist in any other EMR platform. It is the gateway to a safe multi-agent future of care delivery we all know lies ahead.”
Source: PRNewswire