Engineering FAIR Privacy-preserving Applications that Learn Histories of Disease

TL;DR

This paper demonstrates a privacy-preserving, client-side deployment of a generative AI model for healthcare, ensuring data privacy while maintaining high performance using FAIR principles and custom architecture.

Contribution

It introduces a novel in-browser deployment architecture for privacy-sensitive generative AI applications in medicine, leveraging ONNX and JavaScript SDKs.

Findings

Successful client-side deployment of a generative model in healthcare

Achieved secure, high-performance inference without data sharing

Established a blueprint for private AI applications in medicine

Abstract

A recent report on "Learning the natural history of human disease with generative transformers" created an opportunity to assess the engineering challenge of delivering user-facing Generative AI applications in privacy-sensitive domains. The application of these models, particularly for personalized healthcare tasks like predicting individual morbidity risk, is typically constrained by data privacy concerns. This project was accordingly designed as an in-browser model deployment exercise (an "App") testing the architectural boundaries of client-side inference generation (no downloads or installations). We relied exclusively on the documentation provided in the reference report to develop the model, specifically testing the "R" component of the FAIR data principles: Findability, Accessibility, Interoperability, and Reusability. The successful model deployment, leveraging ONNX and a custom JavaScript SDK, establishes a secure, high-performance architectural blueprint for the future of private generative AI in medicine.