2026-04-17T15:01:36Z https://ipsj.ixsq.nii.ac.jp/oai

oai:ipsj.ixsq.nii.ac.jp:00241657 2025-01-19T07:35:21Z 1164:5159:11541:11870

Optimizing Automatic Summarization of Long Clinical Records Using Dynamic Context Extension Testing and Evaluation of the NBCE Method Optimizing Automatic Summarization of Long Clinical Records Using Dynamic Context Extension Testing and Evaluation of the NBCE Method Guoqing, Zhang Keita, Fukuyama Kazumasa, Kishimoto Tomohiro, Kuroda Guoqing, Zhang Keita, Fukuyama Kazumasa, Kishimoto Tomohiro, Kuroda 要約 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 nearparity with Google's over 175B Gemini on ROUGE-L metrics with 200 samples, indicating strong performance using less resources, enhancing automated EMR summarization feasibility. 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 nearparity with Google's over 175B Gemini on ROUGE-L metrics with 200 samples, indicating strong performance using less resources, enhancing automated EMR summarization feasibility. technical report 情報処理学会 2024-12-05 application/pdf 研究報告音声言語情報処理（SLP） 37 2024-SLP-154 1 6 2188-8663 AN10442647 https://ipsj.ixsq.nii.ac.jp/record/241657/files/IPSJ-SLP24154037.pdf eng