SBIR Phase I: AI-Powered Otoscope for Ear Infection Diagnosis

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is a novel automated diagnostic medical device technology for diagnosing ear infections, a common condition affecting up to 80% of all US children by age three resulting in nearly 9 million antibiotic prescriptions each year. The diagnostic tool aims to improve ear infection diagostics in multiple settings including pediatric, urgent care, and emergency exam room, with a novel otoscope that improves diagnostic accuracy from 50-60% to in excess of 92%.

The improved otoscope aims to reduce the long-term health consequences of poor or improper diagnosis including antibiotic overprescription and antibiotic resistance risks, and adverse drug reactions. The novel system will automate the otoscope access and navigation procedure, and utilize advanced adaptive algorithms to analyze digitally acquired images to improve the clinical diagnostic and prognostic measures for the nearly 500,000 physician and nurse practioners who examine ears in the United States on a routine basis. The device has an annual commercial potential of $240M.

This Small Business Innovation Research (SBIR) Phase I project addresses the critical technical challenges in diagnosing ear infections by developing a guided, image analysis enabled otoscope. The Phase 1 objectives advances the steerability and maneuverability of the system, and integrates a high-resolution camera onto an active otoscope enabled with advanced Machine Learning algorithms to guide users in obtaining the optimal eardrum view.

The research objectives include systems engineering and development of the prototype including hardware development and algorithm integration, followed by performance validation using a mechanical bench test model. The anticipated outcomes include demonstrating feasibility for the novel prototype otoscope and its navigational software algorithm, for enhancing clinicians and then parents ability to accurately move through the ear canal, avoid wax, and enabling eardrum access and clearer visualization.

The results will enable the company’s proprietary image based algorithm for clinicians to make more accurate diagnoses.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.