AI Managed Emergency Documentation with a Pretrained Model

TL;DR

This paper explores using a pretrained large language model to generate emergency department discharge letters, aiming to improve efficiency and quality, with positive results from physician evaluations and significant time savings.

Contribution

It introduces a fine-tuned AI system for ED discharge letter generation from various inputs, demonstrating improved efficiency over manual writing.

Findings

Significant reduction in time required for discharge letter writing.

Physicians rated AI-generated summaries as comparable or better.

Positive attitudes towards AI integration in emergency documentation.

Abstract

This study investigates the use of a large language model system to improve efficiency and quality in emergency department (ED) discharge letter writing. Time constraints and infrastructural deficits make compliance with current discharge letter targets difficult. We explored potential efficiencies from an artificial intelligence software in the generation of ED discharge letters and the attitudes of doctors toward this technology. The evaluated system leverages advanced techniques to fine-tune a model to generate discharge summaries from short-hand inputs, including voice, text, and electronic health record data. Nineteen physicians with emergency medicine experience evaluated the system text and voice-to-text interfaces against manual typing. The results showed significant time savings with MedWrite LLM interfaces compared to manual methods.