Video to Screen for Strep Throat

Three Johns Hopkins Professors plus a JHU School of Medicine Professor received grants for their research through the Bisciotti Foundation Translational Fund established from a gift from the Bisciotti Foundation.

The fund provides $300,000 annually in seed money to advance JHU’s discoveries on a commercial path. Recipients are awarded between $25,000 and $100,000 to conduct their research in up to nine months. This year’s funding round received 14 applications Five finalists presented their work in late January to an outside panel of researchers, scientists, and investors.

One specific research project is titledTransforming Acute Care Telehealth with a Novel AI-Driven Strep Throat Screening System Using Smartphone Video”. While  telehealth medicine continues to revolutionize patient care, diagnostic tests for strep throat remain unavailable in the home settings.

Today telehealth doctors caring for sole throats account for up to 10% of all pediatric visits. They either send patients out for a throat swab or prescribe antibiotics if they suspect strep throat. In-person visits can take several hours, and prescribing antibiotics without a throat swab may be unnecessary. According to Dr. Canares, children with strep throat are commonly taken to the pediatric ER although many cases are not severe enough to justify visiting the ER  

To reduce the flow of children to the ER, researchers Therese Canares M.D,, Assistant Professor of Pediatrics at JHU’s School of Medicine, and Mathias Unberath Ph.D, Assistant Professor in the Department of Computer Science at the Whiting School of Engineering  at JHU, are developing a machine-learning algorithm to screen for strep throat based on throat images that are captured and uploaded with their cellphone.

They believe that their technology will let patients get tested for strep throat without going to the ER. They will use the dataset to train the model employed by the algorithm to distinguish strep throat from an ordinary sore throat while also accounting for race, sex, ethnicity, and age to minimize bias.  

Dr. Canares and Dr. Unberath plan to use the funding  from the Bisciotti Fund to develop the app that will house the algorithm and obtain pictures for training the algorithm. The goal is to  help move the project to the point where the researchers will be able to obtain more funding to enhance the accuracy of their machine learning algorithm and develop a prototype of the patient user interface.

Dr. Canares eventually would like to form a startup to provide a platform for mobile, artificial intelligence driven medical diagnoses for common childhood illnesses. Right now the planning for the project involves identifying potential customers and talking to experts in the telehealth industry. Dr Canares is encouraging anyone who has had tonsillitis or strep throat and is interested in assisting with their technology to contact her at therese@jhmi.edu

Go to https://hub.jhu.edu/2022/03/10/bisciotti-foundation-grants for more information and https://ventures.jhu.edu/news/?category+funding for more details on how Johns Hopkins Technology Ventures is working with inventors to patent technologies.