Advancements and Concerns in Healthcare Voice Recognition Technology
A major concern of the medical industry throughout its history has been the documentation of patient encounters in a timely fashion while maintaining patient privacy and confidentiality. Medical dictation and transcription technologies have traditionally been integral components in achieving documentation for medical reporting.
Now, with advancements in technology, continuous voice recognition (CVR) is used widely in the healthcare industry. Most voice recognition systems rely on three factors for successful operation: audio input from a microphone, a built-in vocabulary, and a statistical database that contains the speaker’s uniquely combined words (i.e., a word phrase the speaker frequently uses).
Rapid advancements in healthcare voice recognition
CVR technology has developed dramatically from its earliest healthcare applications to the point that it enables an automated documentation process with the use of wireless microphones, smartphones, integration with electronic health records, algorithms. and artificial intelligence. With the introduction of Google Voice Assistant, Amazon’s Alexa, Apple Siri and the like, growth in healthcare voice recognition systems appears inevitable.
Now CVR systems are trying to evolve beyond speech-to-text technology to an ambient listening system that, without need for a mouse and keyboard, can transcribe a conversation between a doctor and patient and upload key portions into a medical record or a voice assistant that can listen to the conversation and automatically add information from patient visits into the medical record. If successful, this could be a huge leap in the evolvement of this technology.
As Dr. John Halamka, chief information officer of Beth Israel Deaconess Medical Center in Boston, points out, “There are voice recognition products where I can simply dictate, and then a paragraph appears in the medical record. That’s fine, but it’s not sufficient. The dream is that the doctor and patient have dialogue, there is no keyboard in the room, and then at the end the clinician reviews the chart and makes any edits.”
Improving accuracy and security
With advancements in technology, vendors should also focus on the primary issues affecting the use of CVR: accuracy and security. “Seven in 100 words in unedited speech recognition-generated documents had an error, and one in 250 words contained ‘clinically significant errors,’” according to a study, “Analysis of Errors in Dictated Clinical Documents Assisted by Speech Recognition Software and Professional Transcriptions.” Nearly all the errors were caught by follow-up review and editing that emphasized the importance of careful supervision and review of documents generated by voice-recognized system.
As the CVR system is becoming more integrated with EHR, security of health data is assuming an important role in the development of CVR systems. It is noteworthy that Nuance was hit by the NotPetya cyberattack in 2017, disrupting many facilities’ transcription and imaging dictation operations for days and exposing thousands of patient records to an unauthorized party.
The cost of such sophisticated systems is also a concern for many providers and facilities. CVR systems are priced based on a subscription model that involves annual license fees and upfront hardware and installation costs. Integration to the EHR, ongoing upgrades, training, and annual license fees could result into higher ongoing cost for this system. With the decrease in reimbursement for office visits and reductions in overall healthcare operating budgets, not all facilities would be able to invest in ever-evolving new technologies.
Top 10 Negotiating Strategies
Skilled negotiators are like musical virtuosos. They have an extensive repertoire of tactics from which to draw, and they know when and how to make them a part of their performance. But negotiating healthcare contracts for capital, purchased services, and IT services can test the artistry of even the most masterful negotiator.