Loading page. Please wait...
08 September 2022
Canada's most advanced healthcare cloud is now offering another ground-breaking product designed specifically for Canadian practitioners. The average healthcare provider spends 5 minutes documenting each encounter. During an eight-hour day, this adds up to over 2.5 hours! Current electronic medical record systems place an unfair burden upon practitioners; although EHR systems are widely regarded as beneficial to delivering health services to patients, the time spent documenting encounters is both inefficient and un-sustainable.
The Cybermedex v-MOA is a small hardware device with a high-definition audio recorder, designed to be placed in an exam room to record patient encounters. The recorded audio is sent in real-time to our PHIPA-compliant cloud servers for speech-to-text transcription. What makes our service unique is the ability to recognize and transcribe multiple speakers in a room. The underlying technology behind ambient conversational transcription has not been available until very recently, and enables highly accurate multi-speaker voice-to-text transcription.
Cybermedex has the necessary compliance infrastructure in place to store Canadian patient data, and already stores patient data for thousands of Canadians. We are currently integrated with the Microsoft ‘Cognitive Services’ API, and use their basic transcription service to convert the audio stream from telehealth video encounters (embedded within our medical records encounter screen) into editable text.
Once our cloud service processes the audio recorded during an encounter, a text file is available. This file can then be used as the primary documentation for any patient encounter, and optionally shared with the patient via SMS or email. The file can be copy/pasted into any EHR, or automatically added to the current encounter if paired with the Cybermedex EHR.
Recording a patient encounter (what was said, by whom, and at what time), converting it to text using ambient conversational transcription, and storing the output as an editable note in the patient encounter record reduces the documentation burden by as much as 95%.
Ambient transcription currently costs ~$3 per hour. It’s cost-effective and virtually eliminates the most tedious task a healthcare provider must perform (documentation). The average healthcare provider spends over 2 hours per day documenting encounters, time which could be better utilized treating patients or by spending time with family and friends.
The virtual-MOA can do more than just record and transcribe encounters. Other tasks such as billing or scheduling follow-up appointments can be accomplished as well (if paired with the Cybermedex EHR). Many of our cloud-based workflows can be controlled using voice commands.
Practitioner (9:31 am EST): |
Hi Angus, how are you feeling today? |
Angus (9:32 am EST): |
Hi Doctor, where should I begin? |
Practitioner (9:33 am EST): |
How about you start by telling me what hurts the most? |
Cloud-based ambient conversational transcription (backed by Microsoft's recent $7B acquisition of Dragon Naturally Speaking) has the potential to deliver the ‘holy grail’ of electronic health records. Hours spent hunched over a computer documenting encounters, scheduling patients, and billing will fade into the background and be replaced by a truly frictionless EHR experience. Focus your time on delivering the best healthcare to your patients, and allow your virtual assistant to handle the rest.
Ambient conversational transcription requires a high-quality 7-microphone input array. The Amazon Alexa ‘Dot’ device has such an array, however the Alexa API does not support audio recording. The Google Home/Nest device (which runs the Google Assistant) supports audio recording, however the device only has a 2-microphone input. Our unique hardware design features a high-definition, omnidirectional, 8-way digital audio recording device which sends a high-quality audio stream to our PHIPA-compliant servers for processing.
All transcribed text files are available by logging in to your Cybermedex portal. If patients have been scheduled using the Cybermedex EHR, the transcribed text is automatically added to the correct patient encounter as an editable note. Otherwise, all transcriptions are available to edit and download (as a PDF or text file) anytime, for use in your existing EHR system.
The v-MOA is now available on a first-come first-served basis. If you would like someone from Cybermedex to contact you to discuss the trial program in more detail, please make sure to express your interest (below).
Enter your contact details below to express your interest and stay updated with the latest news.
Device |
Notes |
Web Browser |
Supported |
Number of Audio Channels |
Best For |
Also Supported |
iPAD / iPhone |
iPadOS version 15.0 or higher |
|||||
Safari |
yes |
2 |
dictation |
conversational transcription* |
||
Chrome |
yes |
1 |
dictation |
conversational transcription* |
||
Firefox |
no |
no (webRTC not supported) |
dictation |
conversational transcription* |
||
Android |
||||||
Chrome |
yes |
1 |
dictation |
conversational transcription* |
||
Firefox |
yes |
1 |
dictation |
conversational transcription* |
||
Windows XP |
||||||
Chrome |
no (does not support SSL TLS 1.2) |
|||||
Firefox |
yes |
8 |
dictation / conversational transcription |
|||
Internet Explorer |
no (does not support SSL TLS 1.2) |
|||||
Windows 7 (or higher) |
||||||
Chrome |
yes |
2 |
dictation |
conversational transcription* |
||
Firefox |
yes |
8 |
dictation / conversational transcription |
|||
Internet Explorer |
no |
|||||
Edge |
yes |
2 |
dictation |
conversational transcription* |
||
Mac |
macOS Catalina (or higher) |
|||||
Safari |
yes |
8 |
dictation / conversational transcription |
|||
Chrome |
yes |
2 |
dictation |
conversational transcription* |
||
Firefox |
yes |
8 |
dictation / conversational transcription |
|||
Ubuntu 15 (or equivalent and higher) |
||||||
Chrome |
yes |
2 |
dictation |
conversational transcription* |
||
Firefox |
yes |
8 |
dictation / conversational transcription |
* may be used for conversational transcription, however you may experience lower transcription accurancy using less than 8 channels of source audio)