EUVIMEDEUVIMED entdecken
Open Access

Accuracy of Large Language Models for Literature Screening in Thoracic Surgery: Diagnostic Study

Zhang-Yi Dai iD, Fu-Qiang Wang iD, Cheng Shen iD, Yan-Li Ji iD, Zhi-Yang Li iD, Yun Wang iD, Qiang Pu iD

Journal of Medical Internet Research · 11.03.2025 · 27 · e67488

DOI: 10.2196/67488 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Medical Internet Research, online erschienen am 11.03.2025. Verfasst von Zhang-Yi Dai und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Thoracic Surgery, West China Hospital of Sichuan University, Chengdu, China. Hauptthemen laut MEDLINE: Thoracic Surgery. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Systematic reviews and meta-analyses rely on labor-intensive literature screening. While machine learning offers potential automation, its accuracy remains suboptimal. This raises the question of whether emerging large language models (LLMs) can provide a more accurate and efficient approach.

Objective

This paper evaluates the sensitivity, specificity, and summary receiver operating characteristic (SROC) curve of LLM-assisted literature screening.

Methods

We conducted a diagnostic study comparing the accuracy of LLM-assisted screening versus manual literature screening across 6 thoracic surgery meta-analyses. Manual screening by 2 investigators served as the reference standard. LLM-assisted screening was performed using ChatGPT-4o (OpenAI) and Claude-3.5 (Anthropic) sonnet, with discrepancies resolved by Gemini-1.5 pro (Google). In addition, 2 open-source, machine learning–based screening tools, ASReview (Utrecht University) and Abstrackr (Center for Evidence Synthesis in Health, Brown University School of Public Health), were also evaluated. We calculated sensitivity, specificity, and 95% CIs for the title and abstract, as well as full-text screening, generating pooled estimates and SROC curves. LLM prompts were revised based on a post hoc error analysis.

Results

LLM-assisted full-text screening demonstrated high pooled sensitivity (0.87, 95% CI 0.77-0.99) and specificity (0.96, 95% CI 0.91-0.98), with the area under the curve (AUC) of 0.96 (95% CI 0.94-0.97). Title and abstract screening achieved a pooled sensitivity of 0.73 (95% CI 0.57-0.85) and specificity of 0.99 (95% CI 0.97-0.99), with an AUC of 0.97 (95% CI 0.96-0.99). Post hoc revisions improved sensitivity to 0.98 (95% CI 0.74-1.00) while maintaining high specificity (0.98, 95% CI 0.94-0.99). In comparison, the pooled sensitivity and specificity of ASReview tool-assisted screening were 0.58 (95% CI 0.53-0.64) and 0.97 (95% CI 0.91-0.99), respectively, with an AUC of 0.66 (95% CI 0.62-0.70). The pooled sensitivity and specificity of Abstrackr tool-assisted screening were 0.48 (95% CI 0.35-0.62) and 0.96 (95% CI 0.88-0.99), respectively, with an AUC of 0.78 (95% CI 0.74-0.82). A post hoc meta-analysis revealed comparable effect sizes between LLM-assisted and conventional screening.

Conclusions

LLMs hold significant potential for streamlining literature screening in systematic reviews, reducing workload without sacrificing quality. Importantly, LLMs outperformed traditional machine learning-based tools (ASReview and Abstrackr) in both sensitivity and AUC values, suggesting that LLMs offer a more accurate and efficient approach to literature screening.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Thoracic SurgeryHumansROC CurveMachine LearningSensitivity and SpecificityLarge Language Models

Stichwörter der Autor:innen

accuracylarge language modelsliterature screeningmeta-analysisthoracic surgery

Autor:innen und Institutionen

  • Department of Thoracic Surgery, West China Hospital of Sichuan University, Chengdu, China.

ORCID-Profile: Zhang-Yi Dai, Fu-Qiang Wang, Cheng Shen, Yan-Li Ji, Zhi-Yang Li, Yun Wang, Qiang Pu

Zitieren

APA

Dai, Z. Y., Wang, F. Q., Shen, C., Ji, Y. L., Li, Z. Y., Wang, Y., & Pu, Q. (2025). Accuracy of Large Language Models for Literature Screening in Thoracic Surgery: Diagnostic Study. Journal of Medical Internet Research, 27, e67488. https://doi.org/10.2196/67488

Vancouver

Dai ZY, Wang FQ, Shen C, Ji YL, Li ZY, Wang Y, et al. Accuracy of Large Language Models for Literature Screening in Thoracic Surgery: Diagnostic Study. Journal of Medical Internet Research. 2025;27:e67488. doi:10.2196/67488

BibTeX
@article{Dai2025,
  author = {Dai, Zhang-Yi and Wang, Fu-Qiang and Shen, Cheng and Ji, Yan-Li and Li, Zhi-Yang and Wang, Yun and Pu, Qiang},
  title = {Accuracy of Large Language Models for Literature Screening in Thoracic Surgery: Diagnostic Study},
  journal = {Journal of Medical Internet Research},
  year = {2025},
  volume = {27},
  pages = {e67488},
  doi = {10.2196/67488}
}
Kostenlos starten →