Aokun Chen

Dr. Aokun Chen

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
26 March 2024 in Journal of Biomedical Informatics
Verified
Journal Article
Closed access
CPCheng Peng
Cheng Peng
XYXi Yang
Xi Yang
KSKaleb E Smith
Kaleb E Smith
ZYZehao Yu
Zehao Yu
ACAokun Chen
Aokun Chen
Yonghui WuYonghui Wu
Yonghui Wu

9 April 2025 in WIREs Data Mining and Knowledge Discovery
Verified
Journal Article
Open access
LBLeona Cilar Cilar Budler
Leona Cilar Cilar Budler
HCHongyu Chen
Hongyu Chen
ACAokun Chen
Aokun Chen
MTMaxim Topaz
Maxim Topaz
WTWilson Tam
Wilson Tam
GSGregor Stiglic
Gregor Stiglic
This paper reviews benchmarking methods for evaluating large language models (LLMs) in healthcare settings. It highlights the importance of rigorous benchmarking to ensure LLMs' safety, accuracy, and effectiveness in clinical applications. The review also discusses the challenges of developing standardized benchmarks and metrics tailored to healthcare‐specific tasks such as medical text generation, disease diagnosis, and patient management. Ethical considerations, including privacy, data security, and bias, are also addressed, underscoring the need for multidisciplinary collaboration to establish robust benchmarking frameworks that facilitate LLMs' reliable and ethical use in healthcare. Evaluation of LLMs remains challenging due to the lack of standardized healthcare‐specific benchmarks and comprehensive datasets. Key concerns include patient safety, data privacy, model bias, and better explainability, all of which impact the overall trustworthiness of LLMs in clinical settings.

1 June 2025 in JCO Clinical Cancer Informatics
Verified
Journal Article
Open access
HCHongyu Chen
Hongyu Chen
XLXiaohan Li
Xiaohan Li
XHXing He
Xing He
ACAokun Chen
Aokun Chen
JMJames McGill
James McGill
Jiang BianJiang Bian
Jiang Bian
PURPOSE: Patient recruitment remains a major bottleneck in clinical trial execution, with inefficient patient-trial matching often causing delays and failures. Recent advancements in large language models (LLMs) offer a promising avenue for automating and improving this process. This scoping review aims to provide a comprehensive synthesis of the emerging applications of LLMs in patient-trial matching. METHODS: A comprehensive search was conducted in PubMed, Web of Science, and OpenAlex for literature published between December 1, 2022, and December 31, 2024. Studies were included if they explicitly integrated LLMs into patient-trial matching systems. Data extraction focused on system architectures, patient data processing, eligibility criteria processing, matching techniques, evaluation metrics, and performance. RESULTS: Of the 2,357 studies initially identified, 24 met the inclusion criteria. The majority (21/24) were published in 2024, highlighting the rapid adoption of LLMs in this domain. Most systems used patient-centric matching (17/24), with OpenAI's generative pretrained transformer models being the most commonly used LLM. Core components of these systems included eligibility criteria processing, patient data processing, and matching, with some incorporating retrieval algorithms to enhance computational efficiency. LLM-integrated approaches demonstrated improved accuracy and scalability in patient-trial matching, although challenges such as performance variability, interpretability, and reliance on synthetic data sets remain significant. CONCLUSION: LLM-based patient-trial matching systems present a transformative opportunity to enhance the efficiency and accuracy of clinical trial recruitment. Despite current limitations related to model generalizability, explainability, and data constraints, future advancements in hybrid modeling strategies, domain-specific fine-tuning, and real-world data set integration could further optimize LLM-based trial matching. Addressing these challenges will be crucial to realizing the full potential of LLMs in streamlining patient recruitment and accelerating clinical trial execution.

1 January 2024
Verified
Conference Paper
Open access
PDF file
MLMengxian Lyu
Mengxian Lyu
CPCheng Peng
Cheng Peng
DPDaniel Paredes
Daniel Paredes
ZCZiyi Chen
Ziyi Chen
ACAokun Chen
Aokun Chen
Yonghui WuYonghui Wu
Yonghui Wu
Mengxian Lyu, Cheng Peng, Daniel Paredes, Ziyi Chen, Aokun Chen, Jiang Bian, Yonghui Wu. Proceedings of the 23rd Workshop on Biomedical Natural Language Processing. 2024.

18 March 2025 in JMIR Formative Research
Verified
Journal Article
Open access
DFDavid A Fedele
David A Fedele
JRJessica M. Ray
Jessica M. Ray
JMJaya L Mallela
Jaya L Mallela
Jiang BianJiang Bian
Jiang Bian
ACAokun Chen
Aokun Chen
JHJessica Hollenbach
Jessica Hollenbach
Background: There is a longstanding gap between national asthma guidelines and their implementation in primary care. Primary care providers (PCPs) endorse numerous provider and practice or clinic-related barriers to providing guidelines-based asthma care. To reduce asthma morbidity in primary care, PCPs need access to tools that facilitate adherence to national guidelines, which can be delivered at the point of care, are minimally burdensome, and fit within the clinic workflow. Clinical decision support (CDS) tools are health IT systems that can be housed in the electronic health record (EHR) system. Objective: This study aimed to follow user-centered design principles and describe the formative qualitative work with target stakeholders (ie, PCPs and IT professionals) to inform our design of an EHR-embedded CDS tool that adheres to recent, significant changes in asthma management guidelines. Methods: Purposive sampling was used to recruit three separate subgroups of professionals (n=15) between (1) PCPs with previous experience using a paper-based CDS tool for asthma management, (2) PCPs without previous experience using CDS tools for asthma management, and (3) health care IT professionals. The PCP interview guide focused on their practice, familiarity with national asthma guidelines, and how a CDS tool embedded in the EHR might help them provide guideline-based care. The health care IT professional guide included questions on the design and implementation processes of CDS tools into the EHR. Qualitative data were audio-recorded, transcribed, and then analyzed using an inductive approach to develop themes. Results: Themes were organized into 2 domains, current practice and CDS tool development. The themes that emerged from PCPs included descriptions of assessments conducted to make an asthma diagnosis, previous attempts or opportunities to implement updated national asthma guidelines, and how a CDS tool could be implemented using the EHR and fit into the current asthma management workflow. The themes that emerged from health care IT professionals included processes used to design CDS tools and strategies to collect evidence that indicated a tool’s value to a practice and the broader health system. Conclusions: In this study, user-centered design principles were used to guide a qualitative study on perceived barriers and facilitators to a primary care–based, EHR-integrated asthma CDS tool. PCPs expressed their interest in adopting an asthma CDS tool that was low burden and efficient but could help them adhere to national asthma guidelines and improve clinic workflow. Similarly, health care IT professionals perceived an asthma CDS tool to be useful, if it adhered to EHR design standards. Implementation of a CDS tool to improve adherence of PCPs to recently updated national asthma guidelines could be beneficial in reducing pediatric asthma morbidity.

28 September 2022 in Cancers
Verified
Journal Article
Open access
PDF file
ACAokun Chen
Aokun Chen
YLYongqiu Li
Yongqiu Li
JWJennifer N. Woodard
Jennifer N. Woodard
Jessica IslamJessica Islam
Jessica Islam
SYShuang Yang
Shuang Yang
Yi GuoYi Guo
Yi Guo
Breast cancer screening (BCS) with mammography is a crucial method for improving cancer survival. In this study, we examined the association of Alzheimer’s disease (AD) and AD-related dementias (ADRD) diagnosis and race–ethnicity with mammography use in BCS-eligible women. In the real-world data from the OneFlorida+ Clinical Research Network, we extracted a cohort of 21,715 BCS-eligible women with ADRD and a matching comparison cohort of 65,145 BCS-eligible women without ADRD. In multivariable regression analysis, BCS-eligible women with ADRD were more likely to undergo a mammography than the BCS-eligible women without ADRD (odds ratio [OR] = 1.19, 95% confidence interval [CI] = 1.13–1.26). Stratified by race–ethnicity, BCS-eligible Hispanic women with ADRD were more likely to undergo a mammography (OR = 1.56, 95% CI = 1.39–1.75), whereas BCS-eligible non-Hispanic black (OR = 0.72, 95% CI = 0.62–0.83) and non-Hispanic other (OR = 0.65, 95% CI = 0.45–0.93) women with ADRD were less likely to undergo a mammography. This study was the first to report the impact of ADRD diagnosis and race–ethnicity on mammography use in BCS-eligible women using real-world data. Our results suggest ADRD patients might be undergoing BCS without detailed guidelines to maximize benefits and avoid harms.