Scholarlink

With the proliferation of digital healthcare data, there is a substantial challenge in summarizing the volumes effectively and making such summaries available to non-specialist audiences. This work proposes a hybrid approach for medical text summarization that integrates rule-based systems with transformer-based generative models. Evaluations on real-world clinical texts demonstrate improved readability (65.23) and factual accuracy (0.83) compared to standalone rule-based and transformer models. The framework successfully bridges medical accuracy with patient accessibility, establishing new benchmarks for responsible AI in health care.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Human-Centric Medical Summarization with Hybrid Generative AI: A New Era for Accessible Healthcare Insights

  • 章节

  • 发表日期：

    2026年

查看全文
  • M. Pavithra,
  • B. Varunkrishna,
  • J. Umamageswaran,
  • S. Nithish Kannaa

摘要

With the proliferation of digital healthcare data, there is a substantial challenge in summarizing the volumes effectively and making such summaries available to non-specialist audiences. This work proposes a hybrid approach for medical text summarization that integrates rule-based systems with transformer-based generative models. Evaluations on real-world clinical texts demonstrate improved readability (65.23) and factual accuracy (0.83) compared to standalone rule-based and transformer models. The framework successfully bridges medical accuracy with patient accessibility, establishing new benchmarks for responsible AI in health care.