OrientaMed

Sistema conversazionale basato su LLMs e RAG per assistenza al triage

Explore the docs »

Report Bug· Request Feature

            

Table of Contents

1. About The Project
2. Installation
3. Publications
4. Contacts And Useful Links
5. Acknowledgements
6. License

About The Project

🇮🇹 Sistema conversazionale basato su Large Language Models (LLMs) affiancati da un sistema di Retrieval-Augmented Generation (RAG), per il supporto al triage per malattie reumatiche. Questa tecnologia è rivolta al medico di base nella fase di triage e di valutazione delle condizioni cliniche del paziente con possibile malattia reumatica, con l'intento di supportare il medico di base nell'identificare i criteri per l'invio a una visita specialistica reumatologica. Il software è realizzato nel contesto del progetto di ricerca DHEAL-COM (Digital Health Solutions in Community Medicine), finanziato dal Ministero della Salute. Consulta la sezione Acknowledgements per maggiori dettagli.

🇬🇧 Conversational system based on Large Language Models (LLMs) combined with a Retrieval-Augmented Generation (RAG) system, designed to support triage for rheumatic diseases. This technology is intended for general practitioners during the triage and assessment phase of patients with potential rheumatic diseases, helping them identify the criteria for referral to a rheumatology specialist. The software is developed as part of the DHEAL-COM (Digital Health Solutions in Community Medicine) research project, funded by the Ministry of Health. See the Acknowledgements section for more details.

Keywords: RAG, NLP, LLM, large language models, gradio, langchain, chatbot, generative AI, triage, decision support system.

↰ Back To Top

Installation

1. Make sure you have the latest version of pip installed

   pip install --upgrade pip

2. Install dependencies from requirements

   pip install -r --no-cache-dir requirements.txt

3. Run the Gradio app

   python3 app.py

↰ Back To Top

Publications

List of publications involving OrientaMed

• TM Buonocore, E Cardinale, G Sakellariou, R Bellazzi, and L Sacchi - Enhancing RAGs for Rheumatology Triage: Strategies for Optimized Knowledge Retrieval - Prepring (link)

Contacts and Useful Links

• Repository maintainer: Tommaso M. Buonocore

• Project Link: https://github.com/detsutut/dheal-com-rag-demo

↰ Back To Top

Acknowledgements

This work is funded by the "Hub Life Science – Digital Health (LSH-DH) PNC-E3-2022-23683267 - DHEAL-COM Project – CUP: F13C22002030001", funded by the Italian Ministry of Health as part of the National Complementary Plan Innovative Health Ecosystem - CUI: PNC-E.3.

This publication reflects only the authors’ view and the Italian Ministry of Health is not responsible for any use that may be made of the information it contains.

License

Distributed under MIT License. See LICENSE for more information.

↰ Back To Top