Tianchen Lyu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Interests
Tianchen Lyu has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Jiang Bian
Indiana University
4 shared publications - Zhaoyi Chen
University of Florida
3 shared publications - Cui Tao
Department of Artificial Intelligence and Informatics, Mayo Clinic, Jacksonville, FL 32224, USA
2 shared publications - Jiayi Tong
University of Pennsylvania
2 shared publications - William R. Hogan
Medical College of Wisconsin
2 shared publications - Xi Yang
Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Gainesville, USA
2 shared publications
Latest Publications
- Open Access
Exploring the Feasibility of Using Real-World Data from a Large Clinical Data Research Network to Simulate Clinical Trials of Alzheimer’s Disease
In this study, we explored the feasibility of using real-world data (RWD) from a large clinical research network to simulate real-world clinical trials of Alzheimer’s disease (AD). The target trial (i.e., NCT00478205 ) is a Phase III double-blind, parallel-group trial that compared the 23 mg donepezil sustained release with the 10 mg donepezil immediate release formulation in patients with moderate to severe AD. We followed the target trial’s study protocol to identify the study population, treatment regimen assignments, and outcome assessments, and to set up a number of different simulation scenarios and parameters. We considered two main scenarios: (1) a one-arm simulation: simulating a standard-of-care arm that can serve as an external control arm; and (2) a two-arm simulation: simulating both intervention and control arms with proper patient matching algorithms for comparative effectiveness analysis. In the two-arm simulation scenario, we used propensity score matching controlling for baseline characteristics to simulate the randomization process. In the two-arm simulation, higher SAE rates were observed in the simulated trials than the rates reported in original trial, and a higher SAE rate was observed in the 23mg arm than the 10 mg standard-of-care arm. In the one-arm simulation scenario, similar estimates of SAE rates were observed when proportional sampling was used to control demographic variables. In conclusion, trial simulation using RWD is feasible in this example of AD trial in terms of safety evaluation. Trial simulation using RWD could be a valuable tool for post-market comparative effectiveness studies and for informing future trials’ design. Nevertheless, such approach may be limited, for example, by the availability of RWD that matches the target trials of interest, and further investigations are warranted.
Open AccessExploring the Feasibility of Using Real-World Data from a Large Clinical Data Research Network to Simulate Clinical Trials of Alzheimer’s Disease
In this study, we explored the feasibility of using real-world data (RWD) from a large clinical research network to simulate real-world clinical trials of Alzheimer’s disease (AD). The target trial (i.e., NCT00478205 ) is a Phase III double-blind, parallel-group trial that compared the 23 mg donepezil sustained release with the 10 mg donepezil immediate release formulation in patients with moderate to severe AD. We followed the target trial’s study protocol to identify the study population, treatment regimen assignments, and outcome assessments, and to set up a number of different simulation scenarios and parameters. We considered two main scenarios: (1) a one-arm simulation: simulating a standard-of-care arm that can serve as an external control arm; and (2) a two-arm simulation: simulating both intervention and control arms with proper patient matching algorithms for comparative effectiveness analysis. In the two-arm simulation scenario, we used propensity score matching controlling for baseline characteristics to simulate the randomization process. In the two-arm simulation, higher SAE rates were observed in the simulated trials than the rates reported in original trial, and a higher SAE rate was observed in the 23mg arm than the 10 mg standard-of-care arm. In the one-arm simulation scenario, similar estimates of SAE rates were observed when proportional sampling was used to control demographic variables. In conclusion, trial simulation using RWD is feasible in this example of AD trial in terms of safety evaluation. Trial simulation using RWD could be a valuable tool for post-market comparative effectiveness studies and for informing future trials’ design. Nevertheless, such approach may be limited, for example, by the availability of RWD that matches the target trials of interest, and further investigations are warranted.
- Open Access
Developing and Validating a Computable Phenotype for the Identification of Transgender and Gender Nonconforming Individuals and Subgroups
Transgender and gender nonconforming (TGNC) individuals face significant marginalization, stigma, and discrimination. Under-reporting of TGNC individuals is common since they are often unwilling to self-identify. Meanwhile, the rapid adoption of electronic health record (EHR) systems has made large-scale, longitudinal real-world clinical data available to research and provided a unique opportunity to identify TGNC individuals using their EHRs, contributing to a promising routine health surveillance approach. Built upon existing work, we developed and validated a computable phenotype (CP) algorithm for identifying TGNC individuals and their natal sex (i.e., male-to-female or female-to-male) using both structured EHR data and unstructured clinical notes. Our CP algorithm achieved a 0.955 F1-score on the training data and a perfect F1-score on the independent testing data. Consistent with the literature, we observed an increasing percentage of TGNC individuals and a disproportionate burden of adverse health outcomes, especially sexually transmitted infections and mental health distress, in this population.
Open AccessDeveloping and Validating a Computable Phenotype for the Identification of Transgender and Gender Nonconforming Individuals and Subgroups
Transgender and gender nonconforming (TGNC) individuals face significant marginalization, stigma, and discrimination. Under-reporting of TGNC individuals is common since they are often unwilling to self-identify. Meanwhile, the rapid adoption of electronic health record (EHR) systems has made large-scale, longitudinal real-world clinical data available to research and provided a unique opportunity to identify TGNC individuals using their EHRs, contributing to a promising routine health surveillance approach. Built upon existing work, we developed and validated a computable phenotype (CP) algorithm for identifying TGNC individuals and their natal sex (i.e., male-to-female or female-to-male) using both structured EHR data and unstructured clinical notes. Our CP algorithm achieved a 0.955 F1-score on the training data and a perfect F1-score on the independent testing data. Consistent with the literature, we observed an increasing percentage of TGNC individuals and a disproportionate burden of adverse health outcomes, especially sexually transmitted infections and mental health distress, in this population.
- Open Access
Leverage Real-world Longitudinal Data in Large Clinical Research Networks for Alzheimer’s Disease and Related Dementia (ADRD)
With vast amounts of patients’ medical information, electronic health records (EHRs) are becoming one of the most important data sources in biomedical and health care research. Effectively integrating data from multiple clinical sites can help provide more generalized real-world evidence that is clinically meaningful. To analyze the clinical data from multiple sites, distributed algorithms are developed to protect patient privacy without sharing individual-level medical information. In this paper, we applied the One-shot Distributed Algorithm for Cox proportional hazard model (ODAC) to the longitudinal data from the OneFlorida Clinical Research Consortium to demonstrate the feasibility of implementing the distributed algorithms in large research networks. We studied the associations between the clinical risk factors and Alzheimer’s disease and related dementia (ADRD) onsets to advance clinical research on our understanding of the complex risk factors of ADRD and ultimately improve the care of ADRD patients.
Open AccessLeverage Real-world Longitudinal Data in Large Clinical Research Networks for Alzheimer’s Disease and Related Dementia (ADRD)
With vast amounts of patients’ medical information, electronic health records (EHRs) are becoming one of the most important data sources in biomedical and health care research. Effectively integrating data from multiple clinical sites can help provide more generalized real-world evidence that is clinically meaningful. To analyze the clinical data from multiple sites, distributed algorithms are developed to protect patient privacy without sharing individual-level medical information. In this paper, we applied the One-shot Distributed Algorithm for Cox proportional hazard model (ODAC) to the longitudinal data from the OneFlorida Clinical Research Consortium to demonstrate the feasibility of implementing the distributed algorithms in large research networks. We studied the associations between the clinical risk factors and Alzheimer’s disease and related dementia (ADRD) onsets to advance clinical research on our understanding of the complex risk factors of ADRD and ultimately improve the care of ADRD patients.
- Open Access
- 5 December 2019
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 19 (S5) , 1-9
A study of deep learning methods for de-identification of clinical notes in cross-institute settings
Background: De-identification is a critical technology to facilitate the use of unstructured clinical text while protecting patient privacy and confidentiality. The clinical natural language processing (NLP) community has invested great efforts in developing methods and corpora for de-identification of clinical notes. These annotated corpora are valuable resources for developing automated systems to de-identify clinical text at local hospitals. However, existing studies often utilized training and test data collected from the same institution. There are few studies to explore automated de-identification under cross-institute settings. The goal of this study is to examine deep learning-based de-identification methods at a cross-institute setting, identify the bottlenecks, and provide potential solutions. Methods: We created a de-identification corpus using a total 500 clinical notes from the University of Florida (UF) Health, developed deep learning-based de-identification models using 2014 i2b2/UTHealth corpus, and evaluated the performance using UF corpus. We compared five different word embeddings trained from the general English text, clinical text, and biomedical literature, explored lexical and linguistic features, and compared two strategies to customize the deep learning models using UF notes and resources. Results: Pre-trained word embeddings using a general English corpus achieved better performance than embeddings from de-identified clinical text and biomedical literature. The performance of deep learning models trained using only i2b2 corpus significantly dropped (strict and relax F1 scores dropped from 0.9547 and 0.9646 to 0.8568 and 0.8958) when applied to another corpus annotated at UF Health. Linguistic features could further improve the performance of de-identification in cross-institute settings. After customizing the models using UF notes and resource, the best model achieved the strict and relaxed F1 scores of 0.9288 and 0.9584, respectively. Conclusions: It is necessary to customize de-identification models using local clinical text and other resources when applied in cross-institute settings. Fine-tuning is a potential solution to re-use pre-trained parameters and reduce the training time to customize deep learning-based de-identification models trained using clinical corpus from a different institution.
- 5 December 2019
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 19 (S5) , 1-9
Open AccessA study of deep learning methods for de-identification of clinical notes in cross-institute settings
Background: De-identification is a critical technology to facilitate the use of unstructured clinical text while protecting patient privacy and confidentiality. The clinical natural language processing (NLP) community has invested great efforts in developing methods and corpora for de-identification of clinical notes. These annotated corpora are valuable resources for developing automated systems to de-identify clinical text at local hospitals. However, existing studies often utilized training and test data collected from the same institution. There are few studies to explore automated de-identification under cross-institute settings. The goal of this study is to examine deep learning-based de-identification methods at a cross-institute setting, identify the bottlenecks, and provide potential solutions. Methods: We created a de-identification corpus using a total 500 clinical notes from the University of Florida (UF) Health, developed deep learning-based de-identification models using 2014 i2b2/UTHealth corpus, and evaluated the performance using UF corpus. We compared five different word embeddings trained from the general English text, clinical text, and biomedical literature, explored lexical and linguistic features, and compared two strategies to customize the deep learning models using UF notes and resources. Results: Pre-trained word embeddings using a general English corpus achieved better performance than embeddings from de-identified clinical text and biomedical literature. The performance of deep learning models trained using only i2b2 corpus significantly dropped (strict and relax F1 scores dropped from 0.9547 and 0.9646 to 0.8568 and 0.8958) when applied to another corpus annotated at UF Health. Linguistic features could further improve the performance of de-identification in cross-institute settings. After customizing the models using UF notes and resource, the best model achieved the strict and relaxed F1 scores of 0.9288 and 0.9584, respectively. Conclusions: It is necessary to customize de-identification models using local clinical text and other resources when applied in cross-institute settings. Fine-tuning is a potential solution to re-use pre-trained parameters and reduce the training time to customize deep learning-based de-identification models trained using clinical corpus from a different institution.