Speech Recognition

Stand alone or embedded, natural-language technology to drive productivity.

Whether seamlessly integrated to third-party systems or embedded in the eRAD platform, eRAD’s Speech Recognition enables radiologists to achieve faster turnaround times—a key measure for the health of your practice.

In imaging and radiology practices nationwide, productivity, patient satisfaction, and reimbursement are all closely tied to timely, accurate reports. Speech recognition technology drastically improves report generation workflow with faster turnaround and lower costs.

eRAD brings an industry-leading speech recognition engine—M*Modal—to your practice, so that radiologists can quickly create finalized reports. M*Modal combines eRAD’s speech and natural-language understanding technology to contextually understand the physician narrative. Radiologists can achieve unparalleled, out-of-the-gate accuracy and performance. You gain measurable improvements not only in report turnaround time and cost effectiveness, but also in quality and patient outcomes.

Under the Hood | Speech Recognition Technology

The M*Modal Speech Understanding advantage

Once the gold standard, conventional speech recognition is no longer sufficient for today’s clinical documentation challenges. That’s why we created a more intelligent alternative. eRAD’s Speech Recognition technology is based on M*Modal’s advanced speech technology, which transcends simple health speech recognition to achieve true medical Speech Understanding™.

Developed over a decade ago, and refined through steady technological advancement and the accumulated experience of 200,000 physicians, M*Modal Speech Understanding technology is much more than automating voice-to-text rendering. Unlike simple speech recognition, Speech Understanding recognizes the meaning and syntax of the dictation, not just the individual words or word strings.

With the benefit of contextual understanding of a document’s meaning, physicians can dictate in a normal, “conversational” mode—without needing to follow particular speech structures or provide verbal cues to the engine.

  • Available as a cloud-based solution.
  • Conversational speech with the highest accuracy.
  • No need for restrictive voice commands for punctuation or formatting.
  • Out-of-the-box effectiveness from day one.
  • Automatic and continuous learning system.
  • Creating structure from the narrative.
  • Information-driven workflows.
  • Unstructured data analytics.

Speech Recognition Technology Benefits

Users get fully integrated M*Modal voice recognition via both cloud and local VR engines. The cloud server enables roaming profiles, i.e., users access their profiles at login from anywhere.

eRAD’s Speech Recognition module is easy to install and access from its self-contained web-client for remote access from any workstation connected to the internet.

Users can report using full interactive mode or—for those not ready to make the leap to self-editing—in batch mode, where recognition is done in the background and sent to an editor for review. Report templates are provided, as well as macros for on-the-fly customizations. eRAD radiology speech recognition technology allows speech mic buttons and external keyboards to be mapped to user-defined commands.
eRAD radiology speech recognition technology integrates with third-party RIS (Radiology Information Systems) or PACS (Picture Archiving Communication System) using Web Services and HL7 (Health Level 7) platforms. It supports multi-site architecture with a modern user interface.
Core measurements are automatically reported for Meaningful Use, and eRAD radiology speech recognition technology solutions support HIPAA compliance even across distributed sites and high volumes.
“You need a lean, smart system. We had confidence in eRAD, knowing that they’ve helped many practices and physicians attest, so we knew we had a solution-oriented partner with access to the right resources to get the job done.”
Sandra Gonzales, Imaging Administrator
“We had quite a list of criteria for our next system, and in our evaluation eRAD stood out as one of the few able to satisfy our needs. One of the biggest factors was that eRAD had previous interface experience with Athena, and they had the dictation, transcription and speech recognition built right into the PACS viewing software—so we didn’t have to purchase a third-party system and go to the trouble of integrating and supporting it.”
Martha Mastroberti, Manager

Ready to see eRAD in action?

Schedule a demo and see how you can put Speech Recognition to work.