Scholarlink

<p>This study explored the technological evolution of artificial intelligence within the healthcare sector, with a particular focus on the thematic structures and semantic patterns embedded in patent texts. Based on the analysis of over 10,000 global healthcare AI patents retrieved from the Derwent Innovation Index, the study develops a comprehensive framework that integrates technology life cycle analysis, technological activity evaluation, and BERTopic topic-modeling. The results indicate that the healthcare AI sector is currently at the early stage of technological maturity, exhibiting strong growth momentum. Six major thematic areas are identified, highlighting trends of interdisciplinary convergence and multi-scenario applicability. The study offers multi-dimensional insights, providing both an analytical perspective for academic research and strategic references for industrial planning. Moreover, by introducing text mining methods, it proposes a scalable and transferable paradigm for future research in digital health innovation.</p>

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

Tracing thematic evolution in healthcare AI: evidence from patent analysis

  • 期刊论文

  • 发表日期：

    2025年12月7日

查看全文
  • Junrong Zhang,
  • Jianzhi Qiao

摘要

This study explored the technological evolution of artificial intelligence within the healthcare sector, with a particular focus on the thematic structures and semantic patterns embedded in patent texts. Based on the analysis of over 10,000 global healthcare AI patents retrieved from the Derwent Innovation Index, the study develops a comprehensive framework that integrates technology life cycle analysis, technological activity evaluation, and BERTopic topic-modeling. The results indicate that the healthcare AI sector is currently at the early stage of technological maturity, exhibiting strong growth momentum. Six major thematic areas are identified, highlighting trends of interdisciplinary convergence and multi-scenario applicability. The study offers multi-dimensional insights, providing both an analytical perspective for academic research and strategic references for industrial planning. Moreover, by introducing text mining methods, it proposes a scalable and transferable paradigm for future research in digital health innovation.