UF-HOBI at "Discharge Me!": A Hybrid Solution for Discharge Summary Generation Through Prompt-based Tuning of GatorTronGPT Models

TL;DR

This paper introduces a hybrid method combining extractive and abstractive techniques, including prompt-tuning of GatorTronGPT, to improve automated discharge summary generation in clinical settings, demonstrating competitive results in a shared task.

Contribution

The paper presents a novel two-stage approach using NER and prompt-tuned GatorTronGPT models for discharge summary section generation, advancing clinical NLP methods.

Findings

Achieved 5th place in the BioNLP 2024 Shared Task with a score of 0.284.

Demonstrated improved coherence and relevance in generated discharge sections.

Validated the effectiveness of hybrid extractive-abstractive techniques in clinical text generation.

Abstract

Automatic generation of discharge summaries presents significant challenges due to the length of clinical documentation, the dispersed nature of patient information, and the diverse terminology used in healthcare. This paper presents a hybrid solution for generating discharge summary sections as part of our participation in the "Discharge Me!" Challenge at the BioNLP 2024 Shared Task. We developed a two-stage generation method using both extractive and abstractive techniques, in which we first apply name entity recognition (NER) to extract key clinical concepts, which are then used as input for a prompt-tuning-based GatorTronGPT model to generate coherent text for two important sections including "Brief Hospital Course" and "Discharge Instructions". Our system was ranked 5th in this challenge, achieving an overall score of 0.284. The results demonstrate the effectiveness of our hybrid solution in improving the quality of automated discharge section generation.