Mar 25 2019
Smart speakers that are typically used in one’s living room can be set to serve as an aid to physicians in hospital operating rooms, according to new study presented at the Society of Interventional Radiology’s 2019 Annual Scientific Meeting. Smart speakers, such as the Google Home and Amazon Echo, offer a conversational voice interface that enables interventional radiology (IR) physicians to ask questions and obtain information required for their patient treatments without breaking sterilized scrub.
During treatment, IRs rely on nuanced medical information delivered in a timely manner. When you’re in the middle of a procedure, you need to remain sterile, so you lose the ability to use a computer. This smart speaker technology helps us to quickly and intelligently make decisions relevant to a patient’s specific needs.
Kevin Seals, M.D., Study Lead Author and Fellow in Interventional Radiology, University of California, San Francisco (UCSF).
The scientists at UCSF created a device-sizing application for the Google Home smart speaker. The application processes queries from a human voice and offers suggestions on the precise sizing of medical devices. For instance, if an IR wants to know what sheath size to use to implant a stent in a patient’s blood vessel, the smart speaker can rapidly and accurately state the correct size based on the precise circumstances, which helps the physician in coming up with a final decision.
There are hundreds of devices, with more being introduced every day, making it difficult to determine the correct sizing or materials needed in every circumstance. This technology allows physicians to concentrate more closely on the care of their patients, devoting less time and mental energy to device technicalities.
Kevin Seals, M.D., Study Lead Author and Fellow in Interventional Radiology, University of California, San Francisco (UCSF).
In designing the application, size specifications were obtained using literature reviews for 475 IR devices, such as vascular plugs, catheters, stents, sheaths, and others. Natural language processing was executed using Dialogflow, which extracted the data of interest from an input query. Logic operations and other data processing were carried out using a Python script installed in the cloud.
The team plans to continue to develop on this technology and increase its scope to include information on material costs and inventory databases. With this information freely available, treatments will become more efficient, economical, and helpful to patients. More research will aim to yield information for physicians in other spheres and deliver information from electronic health records and patient clinical data, such as prior surgeries or allergies.