Scholarlink

Background <p>Exhaled breathomics is a promising non-invasive avenue for cancer detection via volatile organic compounds (VOCs).</p> Methods <p>This study presents an AI‑enhanced evidence‑mapping framework that integrates. three large language models (LLMs): Tongyi Qianwen, Hunyuan, and Yi to semantically score relevance (0–10) for studies (2005-early 2025) retrieved by a broad initial query. Deterministic decoding (temperature = 0.0; top_p = 0.1), a unified scoring rubric, and threshold-sensitivity analyses (cutoffs 5–7) were adopted. A stratified random sample (<i>n</i> = 100) underwent double expert labeling with adjudication to validate AI screening.</p> Results <p>After exclusions, the corpus comprised 2,625 records (2,083 ART; 542 REV). ART were de-duplicated 2,083 to 2,007, then combined with REV (total 2,549) for LLM screening, retaining 808 core publications (31.7%). Against expert labels, the multi-LLM consensus yielded Accuracy 0.92, Precision 0.91, Recall 0.89, F1 0.90, Cohen’s κ 0.82. Bibliometric mapping shows sustained growth, with ~ 40% of top-cited studies centered on lung-cancer VOCs and limited mechanistic interrogation of biomarker origins or stage correlations.</p> Conclusions <p>The proposed multi‑LLM consensus framework reliably scale relevance assessment for breathomics literature while maintaining transparency and reproducibility. Findings highlight methodological maturation and collaboration expansion, alongside translational gaps in biological plausibility and cross-platform reproducibility.</p> Graphical Abstract <p></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

An AI-enhanced evidence-mapping framework for exhaled breathomics in cancer diagnostics: integrating multiple large language models (2005–early 2025)

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月10日

查看全文
  • Yilan Sun,
  • Guozhen Cheng,
  • Yiyi Liu,
  • Jing Han,
  • Yujue Wang,
  • Jingnan Zhou,
  • Yixiang Duan,
  • Jiannan Liu

摘要

Background

Exhaled breathomics is a promising non-invasive avenue for cancer detection via volatile organic compounds (VOCs).

Methods

This study presents an AI‑enhanced evidence‑mapping framework that integrates. three large language models (LLMs): Tongyi Qianwen, Hunyuan, and Yi to semantically score relevance (0–10) for studies (2005-early 2025) retrieved by a broad initial query. Deterministic decoding (temperature = 0.0; top_p = 0.1), a unified scoring rubric, and threshold-sensitivity analyses (cutoffs 5–7) were adopted. A stratified random sample (n = 100) underwent double expert labeling with adjudication to validate AI screening.

Results

After exclusions, the corpus comprised 2,625 records (2,083 ART; 542 REV). ART were de-duplicated 2,083 to 2,007, then combined with REV (total 2,549) for LLM screening, retaining 808 core publications (31.7%). Against expert labels, the multi-LLM consensus yielded Accuracy 0.92, Precision 0.91, Recall 0.89, F1 0.90, Cohen’s κ 0.82. Bibliometric mapping shows sustained growth, with ~ 40% of top-cited studies centered on lung-cancer VOCs and limited mechanistic interrogation of biomarker origins or stage correlations.

Conclusions

The proposed multi‑LLM consensus framework reliably scale relevance assessment for breathomics literature while maintaining transparency and reproducibility. Findings highlight methodological maturation and collaboration expansion, alongside translational gaps in biological plausibility and cross-platform reproducibility.

Graphical Abstract