Qiang Pu

Qiang Pu

Auto-generated profile, based on publicly available information

Qiang Pu

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

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 March 2025 in Journal of Medical Internet Research
Verified
Journal Article
Open access
ZDZhang-Yi Dai
Zhang-Yi Dai
FWFu-Qiang Wang
Fu-Qiang Wang
CSCheng Shen
Cheng Shen
YJYan-Li Ji
Yan-Li Ji
ZLZhi-Yang Li
Zhi-Yang Li
QPQiang Pu
Qiang Pu
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.

13 October 2024 in JMIR Preprints
Verified
Preprint
Open access
ZDZhang-Yi Dai
Zhang-Yi Dai
FWFu-Qiang Wang
Fu-Qiang Wang
CSCheng Shen
Cheng Shen
YJYan-Li Ji
Yan-Li Ji
ZLZhi-Yang Li
Zhi-Yang Li
QPQiang Pu
Qiang Pu
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.

1 June 2026 in Journal of Thoracic Disease
Verified
Journal Article
Open access
PDF file
XJXiaohan Jin
Xiaohan Jin
JLJiaqi Li
Jiaqi Li
YLYaling Liu
Yaling Liu
ALAudrey Yaulap Li
Audrey Yaulap Li
JMJier Ma
Jier Ma
DTDong Tian
Dong Tian
Background and Objective: Lung transplantation (LTx) remains the only definitive treatment for end-stage lung disease. Throughout 2025, the global transplant community has made notable progress in addressing persistent challenges in the field, ranging from policy-level improvements in graft allocation to deeper biological insights into post-transplant complications. This review aims to synthesize the pivotal literature published in 2025 across four core areas: optimizing allocation, advancing perioperative care, defining the mechanisms of graft injury, and exploring translational frontiers. Methods: We conducted a structured literature search focused primarily on studies published in 2025 that highlight major advancements in LTx. In addition, the search was supplemented with key society guidelines, consensus statements, and relevant early 2026 publications. Selected articles were critically analyzed and categorized into clinical advancements, and basic/translational findings. Key Content and Findings: In clinical research, the refinement of allocation strategies and the expansion of donor criteria, have effectively broadened access. Perioperative management has evolved with the integration of artificial intelligence to predict complications such as primary graft dysfunction (PGD) and chronic lung allograft dysfunction (CLAD). In basic and translational research, studies have dissected the molecular basis of complications. Additionally, new insights into the evolution of drug-resistant pathogens and macrophage plasticity have deepened our understanding of infection and rejection. Conclusions: In 2025, significant progress has been achieved in the field of LTx research. Strategies for clinical donor allocation and perioperative management, along with the understanding of molecular mechanisms underlying complications, have also been greatly improved. These advancements are essential to further optimize outcomes and address the complex challenges in LTx.