What Can Nuance’s Speech Recognition Technology Do?
Nuance released Dragon NaturallySpeaking in 1997, and it wasn’t long before the medical community took notice. Clinicians in particular stood to benefit from the use of front-end speech recognition and reduced need for transcription services. Over the years, the technology has evolved to include the ability to learn medical terminology, languages and accents.
In recent years, Nuance applied AI to its software for new use cases, including ambient clinical documentation. In this case, a smart speaker in an exam room picks up on key words during a patient visit and can translate the relevant speech into actions or activities within the EHR. For example, a physician could use a voice command to order medications or add a diagnosis to the chart.
Ambient clinical documentation and other new advances in technology inevitably raise questions of security and privacy. Nuance solutions maintain the highest levels of HIPAA compliance, as all protected health information and personally identifiable information is encrypted at use, in transit and at rest. Features such as ambient listening can be toggled off if more privacy is needed.
DIVE DEEPER: How can healthcare leverage natural language processing for medical records?
What’s Next for Speech Recognition in Healthcare?
Microsoft’s acquisition is certain to accelerate the use of AI and natural language processing within clinical workflows. For example, NLP allows providers to gather data from the point of care for comparison with large data sets within the EHR or Microsoft Cloud for Healthcare. This approach enables clinical decision support in real time, leading to better outcomes and patient satisfaction.
Demand for speech recognition continues to be high, and the combination of Nuance’s intellectual property and Microsoft’s cloud and analytics capabilities will result in more sophisticated offerings with increased interoperability. In addition, Microsoft can apply the technology to other industries and use cases, which could lead to more development within speech recognition and AI.
This article is part of HealthTech’s MonITor blog series. Please join the discussion on Twitter by using #WellnessIT.