Tramscribe shipped to the NHS a privacy-by-design voice transcription and summarization system to help clinicians save time without exposing patient privacy with BlindBox. Tramscribe shipped to the NHS a privacy-by-design voice transcription and summarization system to help clinicians save time without exposing patient privacy with BlindBox.
Use Case: Speech-to-text and NLP with LLMs
Tramscribe is a recent startup aiming to save time for NHS clinicians by automating admin tasks. Clinicians within the NHS often have to take many notes and spend time doing administrative tasks that distance them from patients.
Tramscribe speeds up this process by using AI to transcribe medical voice notes and then turns the raw notes into well-formatted templates. However, ensuring data privacy when sending patient data to outside AI solutions is a real challenge. Tramscribe was looking for a solution to leverage the latest AI models with Large Language Models while respecting patient privacy.
Tramscribe wanted to provide a solution that would be as easy as possible to use by clinicians. Therefore, an on-prem solution would not meet those requirements. A fully SaaS solution in the Cloud would be the best choice for onboarding and infrastructure management.
In addition, because Tramscribe wants to provide AI-based transcription and summarization, getting the latest hardware and software from a Cloud provider is the natural way to go.
However, proposing a SaaS solution implies exposing data to Tramscribe Cloud platform. Then guaranteeing that patient data sent to Tramscribe would not be exposed is a real challenge. Indeed, Tramscribe would centralize patient data and can become a point of failure regarding this sensitive information.
Consequently, reconciling privacy and security, along with the imperative for a swift onboarding mechanism that accommodates an advanced AI infrastructure, presented a substantial technical challenge.
By using BlindBox, it was possible to deploy AI models on a Public Cloud while guaranteeing data privacy by leveraging Confidential Containers.
We deployed two open source models, Whisper from OpenAI, to perform speech-to-text, then used a ChatGPT-like model, Pythia from TogetherComputer, to conduct medical notes structuration. Both models were packaged inside a Docker container which was then hardened using BlindBox and deployed on Azure Confidential Containers.
Subsequently, we utilized the BlindBox client SDK to query these AI models, thereby maintaining end-to-end data protection. This approach ensured that patients' data remained secure, as key management and control verification were handled on the client side, preventing any unintended exposure of sensitive information.
The solution that Tramscribe implemented offers key benefits:
“Mithril Security appears to offer a solution to the privacy issues that come with creating AI-assisted tools for clinicians in areas such as the NHS.
Clinicians within the NHS often have to take many notes and spend time doing administrative tasks that distance them from patients.
We have been wanting to create an AI tool that can transcribe medical voice notes and turn the raw text into formatted medical notes in order to save clinicians valuable time.
However, ensuring data privacy when sending patient data to outside AI solutions is a real challenge.
By using BlindBox, we have been experimenting with getting the best of both worlds: leverage state-of-the-art AI solutions from third-party vendors to create value for clinicians, without risking the exposure of patient data.
We are excited to learn more about this technology and implement it into our products”
Director of Tramscribe Ltd
Contribute to our project, and mention open issues and PRs.
Join the community, share your ideas and talk with Mithril’s team.