Optimizing Automatic Summarization of Long Clinical Records Using Dynamic Context Extension:Testing and Evaluation of the NBCE Method

TL;DR

This paper introduces a novel method for summarizing long clinical records using a 7B language model enhanced with a Native Bayes Context Extend and a new decoding mechanism, achieving high-quality summaries within limited context windows.

Contribution

The paper presents a new approach combining Native Bayes Context Extend and a redesigned decoding process to improve long input summarization with smaller models.

Findings

Achieved near-parity with Google's 175B Gemini on ROUGE-L metrics.

Enhanced summarization quality with a 7B model using the proposed methods.

Demonstrated resource-efficient performance in clinical record summarization.

Abstract

Summarizing patient clinical notes is vital for reducing documentation burdens. Current manual summarization makes medical staff struggle. We propose an automatic method using LLMs, but long inputs cause LLMs to lose context, reducing output quality especially in small size model. We used a 7B model, open-calm-7b, enhanced with Native Bayes Context Extend and a redesigned decoding mechanism to reference one sentence at a time, keeping inputs within context windows, 2048 tokens. Our improved model achieved near parity with Google's over 175B Gemini on ROUGE-L metrics with 200 samples, indicating strong performance using less resources, enhancing automated EMR summarization feasibility.