Mengqian Wang

Mengqian Wang

Auto-generated profile, based on publicly available information

Mengqian Wang

University of North Carolina, Chapel Hill, Chapel Hill, NC, United States

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
2 August 2021 in Journal of the American Medical Informatics Association
Verified
Journal Article
Closed access
MWMengqian Wang
Mengqian Wang
MWManhua Wang
Manhua Wang
FYFei Yu
Fei Yu
YYYue Yang
Yue Yang
JWJennifer Walker
Jennifer Walker
JMJaved Mostafa
Javed Mostafa
Objective: Biomedical text summarization helps biomedical information seekers avoid information overload by reducing the length of a document while preserving the contents’ essence. Our systematic review investigates the most recent biomedical text summarization researches on biomedical literature and electronic health records by analyzing their techniques, areas of application, and evaluation methods. We identify gaps and propose potential directions for future research.Materials and Methods: This review followed the PRISMA methodology and replicated the approaches adopted by the previous systematic review published on the same topic. We searched 4 databases (PubMed, ACM Digital Library, Scopus, and Web of Science) from January 1, 2013 to April 8, 2021. Two reviewers independently screened title, abstract, and full-text for all retrieved articles. The conflicts were resolved by the third reviewer. The data extraction of the included articles was in 5 dimensions: input, purpose, output, method, and evaluation.Results: Fifty-eight out of 7235 retrieved articles met the inclusion criteria. Thirty-nine systems used single-document biomedical research literature as their input, 17 systems were explicitly designed for clinical support, 47 systems generated extractive summaries, and 53 systems adopted hybrid methods combining computational linguistics, machine learning, and statistical approaches. As for the assessment, 51 studies conducted an intrinsic evaluation using predefined metrics.Discussion and Conclusion: This study found that current biomedical text summarization systems have achieved good performance using hybrid methods. Studies on electronic health records summarization have been increasing compared to a previous survey. However, the majority of the works still focus on summarizing literature.

13 October 2021 in Proceedings of the Association for Information Science and Technology
Verified
Journal Article
Closed access
PDF file
MWManhua Wang
Manhua Wang
SSSelina Sharmin
Selina Sharmin
MWMengqian Wang
Mengqian Wang
FYFei Yu
Fei Yu

20 February 2026 in JMIR AI
Verified
Journal Article
Open access
SJSaubhagya Joshi
Saubhagya Joshi
MMMonjil Mehta
Monjil Mehta
SMSarjak Maniar
Sarjak Maniar
MWMengqian Wang
Mengqian Wang
VSVivek Kumar Singh
Vivek Kumar Singh
Background: Large language models (LLMs) are increasingly integrated into health care, where they contribute to patient care, administrative efficiency, and clinical decision-making. Despite their growing role, the ability of LLMs to handle imperfect inputs remains underexplored. These imperfections, which are common in clinical documentation and patient-generated data, may affect model reliability. Objective: This study investigates the impact of input perturbations on LLM performance across three dimensions: (1) overall effectiveness in different health-related applications, (2) comparative effects of different types and levels of perturbations, and (3) differential impact of perturbations on health-related terms versus non–health-related terms. Methods: We systematically evaluate 3 LLMs on 3 health-related tasks using a novel dataset containing 3 types of human-like variations (redaction, homophones, and typographical errors) at different perturbation levels. Results: Contrary to expectations, LLMs demonstrate notable robustness to common variations, and in more than half of the cases (151/270, 55.92%), the performance was stable or improved. In some cases (38/270, 14.07%), variations resulted in an increased performance, especially when dealing with lower perturbation levels. Redactions, often stemming from privacy concerns or cognitive lapses, are more detrimental than other variations. Conclusions: Our findings highlight the need for health care applications powered by LLMs to be designed with input variability in mind. Robustness to noisy or imperfect inputs is essential for maintaining reliability in real-world clinical settings, where data quality can vary widely. By identifying specific vulnerabilities and strengths, this study provides actionable insights for improving model resilience and guiding the development of safer, more effective artificial intelligence tools in health care. The accompanying dataset offers a valuable resource for further research into LLM performance under diverse conditions.

5 September 2025 in JMIR Preprints
Verified
Preprint
Open access
SJSaubhagya Joshi
Saubhagya Joshi
MMMonjil Mehta
Monjil Mehta
SMSarjak Maniar
Sarjak Maniar
MWMengqian Wang
Mengqian Wang
VSVivek Kumar Singh
Vivek Kumar Singh
BACKGROUND Large Language Models (LLMs) are increasingly integrated into healthcare, where they contribute to patient care, administrative efficiency, and clinical decision-making. Despite their growing role, the ability of LLMs to handle imperfect inputs remains underexplored. These imperfections, which are common in clinical documentation and patient-generated data, may affect model reliability. OBJECTIVE This study investigates the impact of input perturbations on LLM performance across three dimensions: (1) overall effectiveness in different health-related applications, (2) comparative effects of different types and levels of perturbations, and (3) differential impact of perturbations on health-related terms versus non-health-related terms. METHODS We systematically evaluate three LLMs on three health-related tasks using a novel dataset containing three types of human-like variations (redaction, homophones, and typographical errors) at different perturbation levels. RESULTS Contrary to expectations, LLMs demonstrate notable robustness to common variations, with some cases showing improved performance at lower perturbation levels. Redactions, often stemming from privacy concerns or cognitive lapses, are more detrimental than other variations. CONCLUSIONS Our findings highlight the need for healthcare applications powered by LLMs to be designed with input variability in mind. Robustness to noisy or imperfect inputs is essential for maintaining reliability in real-world clinical settings, where data quality can vary widely. By identifying specific vulnerabilities and strengths, this work provides actionable insights for improving model resilience and guiding the development of safer, more effective AI tools in healthcare. The accompanying dataset offers a valuable resource for further research into LLM performance under diverse conditions. CLINICALTRIAL (N/A)

16 October 2019 in bioRxiv
Verified
Preprint
Open access
PDF file
MOMichael Segundo Ortiz
Michael Segundo Ortiz
MWMengqian Wang
Mengqian Wang
KSKazuhiro Seki
Kazuhiro Seki
HKHeejun Kim
Heejun Kim
JMJaved Mostafa
Javed Mostafa
In this work we present Publication Access Through Tiered Interaction & Exploration (PATTIE) – an information foraging, sense-making, and exploratory spatial-semantic information retrieval (IR) system ( http://pattie.unc.edu/plos ). Non-spatial, spatial IR systems, and some recent studies focused on their principal functions are discussed and compared. To interactively work through a use-case from the biomedical domain, instructions are provided for readers to conduct exploratory searches directly on the PLOS archive based on the software embedded in the online version of this paper ( http://vzlib.unc.edu/software/ ). To carefully evaluate some of the critical parameters of the PATTIE algorithm, and the core functions of the implemented system, a set of experiments were conducted. Along with details on the experimental methods and their rationale, key findings from the experiments are analyzed and presented. Finally, with an eye toward the future of software-embedded scientific papers, their potential benefits for supporting direct engagement with scientific content, replication, and validation are discussed.