NVIDIA supports telemedicine through its Automated speech recognition and natural language processing technology that captures conversations in the medical record. The novel coronavirus pandemic significantly changed the way patients interact with their doctors worldwide. Telemedicine has been widely adopted as an alternative for the usual doctor-patient face to face visits. Some governments are encouraging patients with mild symptoms and those with increased vulnerability to use telemedicine services. This initiative is for preventing them from visiting hospitals so as to protect themselves.
Telemedicine includes having constant video or audio calls with our doctors or service providers using our mobile devices. The most important part of the call is the conversation between the patient and the doctor. It is important that the main points of discussion be stored safely in some form of medical records system in a structured manner. NVIDIA’s research is using automated speech recognition and natural language processing technology to automatically capture conversations in the medical record.
Automated speech recognition and natural language processing technology capture, recognize, understand, and summarize key concepts and structures using conversational AI models. In addition, clinical ontologies like SNOMED-CT or ICD-10 are also used as the patient talks about their symptoms. Examples of such concepts include disease conditions, symptoms, and treatments. The captured audio can come in the form of a telemedicine visit, or even captured during in-person physician visits. This creates the ability to recap conversations for both patients and their caregivers, as well as for the patient care team, as an important benefit so that they can be informed and have the reassurance of being able to review what was discussed.
