Home

Awesome

<!-- This source file is part of the Stanford LLM on FHIR project SPDX-FileCopyrightText: 2023 Stanford University SPDX-License-Identifier: MIT -->

LLM on FHIR - Demystifying Health Records

Beta Deployment codecov DOI

"Demystifying Health Records - A Conversational Interface to Your Health Data"

<p float="left"> <img alt="AllHealthRecords" src="Figures/LLMonFHIR_Screenshots_Main.png"> </p>

This repository contains the LLM on FHIR Application to demonstrate the power of LLMs to explain and provide helpful context around patient data provided in the FHIR format. It demonstrates using the Spezi framework and builds on top of the Stanford Spezi Template Application. The application connects to the OpenAI GPT API to interpret FHIR resources using the GPT suite of large language models.

<p float="left"> <img alt="AllHealthRecords" src="Figures/LLMonFHIR_Screenshots_Translation.png"> </p>

LLMonFHIR supports multiple languages. The LLM is prompt-engineered to converse with users based on their system language. The application is currently translated into English, Spanish, Chinese, German, and French.

[!NOTE] Do you want to try out the LLM on FHIR Application? You can download it to your iOS device using TestFlight!

Overview

Disclaimer

LLM on FHIR is an experimental iOS app. It is designed for general informational purposes, providing users a platform to interact with health records stored in Apple Health using OpenAI models.

Remember that your health data will be sent to OpenAI for processing. Please inspect and carefully read the OpenAI API data usage policies and settings accordingly.

HealthKit Access

LLM on FHIR requires access to the FHIR health records stored in the Apple Health app. You have the control to select the different types of health records you wish to inspect in LLM on FHIR.

In case no health records are available, please follow the instructions to connect and retrieve your health records from your provider. If your health records are visible in the Apple Health app, please ensure that LLM on FHIR has access to your health records in the Apple Health App. You can find these settings in the privacy section of your profile in Apple Health.

Application Structure

The Spezi Template Application uses a modularized structure using the Spezi modules enabled by the Swift Package Manager.

The application uses the FHIR standard to provide a shared repository for data exchanged between different modules. You can learn more about the Spezi standards-based software architecture in the Spezi documentation.

Build and Run the Application

You can build and run the application using Xcode by opening up the LLMonFHIR.xcodeproj.

Contributors & License

This project is based on Spezi framework and builds on top of the Stanford Spezi Template Application provided using the MIT license. You can find a list of contributors in the CONTRIBUTORS.md file.

The LLM on FHIR project, Spezi Template Application, and the Spezi framework are licensed under the MIT license.