team photo

Figure 1
project photo

Figure 2
project photo

Team 10

Team Members

Faculty Advisor

Sebastiano Alderucci
Conrad Korzon
Zhaotian Li
Zhiyuan Liu
Andrew Placzek

Jake Scoggin



sponsored by
sponsor logo

The goal for this project, as presented by Cigna, was to create a digital solution to increase healthcare literacy and/or digital engagement, especially among underserved, low income populations. Our team developed the Prescription Interpreter, an Android mobile application which scans prescription labels utilizing the mobile camera, translates the image to text using a custom made machine learning algorithm, and displays visual medical adherence instructions. The Prescription Interpreter was designed to emphasize clarity, ease of use, accessibility, personalization, and diversity. Complex medical terminology is avoided in favor of visual icon-based directions. To promote personalization and inclusion, the visual directions feature an avatar which can be customized for skin tone, hair color, and hair style, so that users will feel represented regardless of their background. Lastly, our application’s most innovative feature separates it from other applications on the market with an ability to automatically interpret how and when a user should take their prescriptions via machine learning solely based on a picture of the prescription’s written directions, even when the directions contain some degree of spelling errors.