Yihao Tan

Yihao Tan

Auto-generated profile, based on publicly available information

Yihao Tan

Department of Biostatistics, School of Public Health and Health Professions State University of New York at Buffalo Buffalo New York USA

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications

10 July 2025
Verified
Dataset
Closed access
YTYihao Tan
Yihao Tan
MMMarianthi Markatou
Marianthi Markatou
SCSaptarshi Chakraborty
Saptarshi Chakraborty
RMRaktim Mukhopadhyay
Raktim Mukhopadhyay
A suite of empirical Bayes methods to use in pharmacovigilance. Contains various model fitting and post-processing functions. For more details see Tan et al. (2025) , Koenker and Mizera (2014) and Efron (2016) .

7 October 2026 in Journal of Medical Internet Research
Verified
Journal Article
Open access
MMMarianthi Markatou
Marianthi Markatou
RMRaktim Mukhopadhyay
Raktim Mukhopadhyay
JGJeff Good
Jeff Good
YTYihao Tan
Yihao Tan
ADArpan Dharia
Arpan Dharia
ATAndrew Henry Talal
Andrew Henry Talal
Large language model (LLM)–based systems have tremendous potential to improve patient-centered health care, especially for medically underserved populations. However, realizing this potential requires careful consideration of the socio-technical contexts in which LLMs are used. The design of such systems should consider the vulnerabilities of any medically underserved group that the system intends to support, and provide trustworthy evidence for its use. This viewpoint reports the lessons learned from our experience and research with the CREATE (Culture, Respect, Education, Advancement, Trust, and Expertise) framework for engaging multiple stakeholders to guide the integration of LLM-based systems for improved health care delivery. We propose an extension of the traditional hierarchy of evidence model and identify key junction points in clinical workflows at which LLM-based systems can potentially be used to improve patient care. The key messages can be summarized as follows: (1) users of AI technologies, such as LLM-based tools, must be aware of the strengths, limitations, and impact of these technologies on health care delivery workflows and on the quality of generated evidence on which health care recommendations are based; (2) users must also be aware of the impact of data quality on AI outputs and on the evidence generated from the use of these systems; (3) the evidence pyramid provides a framework that facilitates the evaluation of the output generated by AI systems; (4) the CREATE framework facilitates the engagement of a variety of stakeholders. We propose concrete approaches for its validation and implementation; (5) any system designed to support people with opioid use disorder (OUD) needs to consider the overall lack of trust and stigmatizing experiences of this population with the health care system, and we discuss various aspects of the evaluation process necessary to build trust; (6) to discuss research directions that need to be addressed before LLM-based systems can be integrated usefully in patient health care.

3 April 2026 in JMIR Preprints
Verified
Preprint
Open access
MMMarianthi Markatou
Marianthi Markatou
RMRaktim Mukhopadhyay
Raktim Mukhopadhyay
JGJeff Good
Jeff Good
YTYihao Tan
Yihao Tan
ADArpan Dharia
Arpan Dharia
ATAndrew Henry Talal
Andrew Henry Talal
UNSTRUCTURED Large language model-based systems (LLMs) have tremendous potential to improve patient-centered healthcare, especially for medically underserved populations. However, realizing this potential requires careful consideration of the socio-technical contexts in which LLMs are used. The design of such systems should consider the vulnerabilities of any medically underserved group that the system intends to support and provide trustworthy evidence for its use. In this work, we study the adoption of LLM-based systems as socio-technical systems from the diffusion of innovations (DOI) theory perspective. We extend the CREATE (Culture, Respect, Education, Advancement, Trust and Expertise) framework to guide integration of LLM-based systems for improved healthcare delivery. We also propose an extension of the traditional hierarchy of evidence model appropriate for our context and discuss risks associated with the use of such systems. Furthermore, we identify key junction points in clinical workflows at which LLM-based systems can potentially be used to improve patient care. In addition to general considerations associated with the development of any patient-oriented LLM-based system, any system designed to support people with opioid use disorder (OUD) needs to consider the overall lack of trust and stigmatizing experiences of this population with the healthcare system. We therefore discuss various aspects of the evaluation process necessary to build trust.

14 October 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
YTYihao Tan
Yihao Tan
SCSaptarshi Chakraborty
Saptarshi Chakraborty
MMMarianthi Markatou
Marianthi Markatou
Background: Monitoring the safety of medical products is a core pharmacovigilance concern. To support drug safety assessment, Spontaneous Reporting Systems (SRS) collect reports of suspected adverse events of approved medical products, offering a critical resource for identifying potential safety concerns that may not emerge during clinical trials. Modern nonparametric empirical Bayes methods are flexible statistical approaches that can accurately identify and estimate the strength of the association between an adverse event and a drug from SRS data. However, there is currently no comprehensive and easily accessible implementation of these methods.Methods: We introduce an open-source R package pvEBayes, which implements a suite of nonparametric empirical Bayes methods (including general-gamma, K-gamma, Koenker-Mizera (KM) method, Efron's approach and Gamma-Poisson Shrinker (GPS)) for pharmacovigilance, along with post-processing tools and graphical summaries for streamlining the application of these methods. The package is openly available on the Comprehensive R Archive Network (CRAN), and has passed rOpenSci peer review with a gold badge. A simulation study is provided to examine the performance of the general-gamma method with different hyperparameter selection. In addition, detailed examples are provided to demonstrate the application of the package through analyses of two real-world SRS datasets, statin2025_44 and gbca2025_69, curated from the publicly available U.S. Food & Drug Administration's Adverse Event Reporting System (FAERS) database.Results: The simulation study confirms that the general-gamma method is robust to the choice of its hyperparameter α: Akaike information criterion- and Bayesian information criterion-based selection both perform well. The usage of the pvEBayes package is illustrated by analysis of statin2025_44 and gbca2025_69 datasets.