Silicon Valley tech giant Nvidia, best known for designing graphics processing units for the gaming and professional markets, is looking to use its experience to benefit the telehealth space.
Researchers at the company are working on developing an automated speech recognition and natural language processing technology, which would be able to transcribe and organize information from a telemedicine visit for both patient and clinicians. What separates the tool from other offerings in the market is that it is specifically trained to understand clinical and biomedical language.
Nvidia says the new tool will enable patients to leave telehealth visits with a lot more information and notes than they do currently.
While the Nvidia tool’s initial focus will be telehealth transcription, the company says its uses could extend to other medical applications.
Speaking about the tool, Hoo-Chang Shin, research scientist at NVIDIA, told MobiHealthNews: “This particular one was trained on large biomedical text and then a smaller set of clinical text ... but if we had a large amount of clinical notes like radiologist reports then the language processing trained on them would be kick-ass on recognizing radiologists reports.
“It would be so much better at transcribing radiologist reports and also we have even more recognition of named entities or disease names, or possibly planned treatments, and so on.”