DocToRead is an innovative app based on AI technology that translates medical documents into easy-to-understand language. The app uses advanced technologies to decode so-called “medical jargon” and complicated medical terminology and convert it into clear, understandable text.
Initial situation
Our client approached us with his idea for an app. The aim was to make it easier for non-medical professionals to understand medical documents such as doctor's letters. In addition to the need for the app to be able to automatically read the relevant documents (text and images) using OCR (optical character recognition), it also had to simplify the content. It was therefore necessary to connect the application to AI in order to achieve the desired results.
Implementation
In addition to extensive research into the necessary AI for the app's backend, our designers began designing a user-friendly and appealing frontend for DocToRead. We recommended implementing the application based on the Flutter framework, as this allows mobile apps for both iOS and Android to be implemented quickly and easily.
In addition to developing the app and connecting the AI, a major challenge was evaluating the optimal prompts, i.e., the specific inputs to the AI. It quickly became apparent that the app could not simply be built around the AI. We quickly decided to consult our software testing team.
Our idea was that our team of testers, who have experience in both manual and automated testing, would be best placed to formulate an expected result and figure out the best way to achieve it. As the first test data was evaluated, it quickly became apparent that prompts could be greatly optimized. Prompts are complex, and the results delivered by AI are highly dependent on how a prompt is formulated. There are a variety of functional settings, such as the type of language (technical or colloquial), the context (professional or casual), and cultural influences. For example, the same prompt in different language variants in the AI (German, English, Spanish, etc.) also led to different results. The biggest challenge was the multilingualism of the app. It was more complex than expected to find a prompt that would lead to the desired and, above all, reliable result in the languages used.
Another major challenge was compliance with data protection guidelines. Working closely with various specialist lawyers and organizations, we succeeded in implementing the app in a way that is both GDPR-compliant and secure.
Summary
Through continuous testing, translation, comparison, and optimization, an app was created that, in conjunction with AI, serves as a kind of medical interpreter. This offers enormous added value, especially in the medical field, where patients are mostly laypeople in this regard.
However, the project is far from complete. Depending on AI releases, the prompt will need to be adjusted again. In addition, there are plans to implement language-dependent prompts in the future – a truly exciting topic.