Work

eHealth Assistant AI Chatbot Using a Large Language Model to Provide Personalized Answers through Secure Decentralized Communication

Year: 2024

Type: article

Abstract: In this paper, we present the implementation of an artificial intelligence health assistant designed to complement a previously built eHealth data acquisition system for helping both patients and medical staff. The assistant allows users to query medical information in a smarter, more natural way, respecting patient privacy and using secure communications through a chat style interface based on the Matrix decentralized open protocol. Assistant responses are constructed locally by an interchangeable large language model (LLM) that can form rich and complete answers like most human medical staff would. Restricted access to patient information and other related resources is provided to the LLM through various methods for it to be able to respond correctly based on specific patient data. The Matrix protocol allows deployments to be run in an open federation; hence, the system can be easily scaled.

Source: Sensors

DOI: 10.3390/s24186140

Authors: Iuliu Alexandru Pap, Stefan Oniga

Institutions: Technical University of Cluj-Napoca, University of Debrecen

Language: English

Topic: Artificial Intelligence in Healthcare and Education

Subfield: Health Informatics

Field: Medicine

Domain: Health Sciences

SDG: Good health and well-being

Open Access status: gold

Estimated APC paid: $2,955