1
|
Zhang M, Kuo TT. Early prediction of long hospital stay for Intensive Care units readmission patients using medication information. Comput Biol Med 2024; 174:108451. [PMID: 38603899 DOI: 10.1016/j.compbiomed.2024.108451] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/08/2023] [Revised: 03/21/2024] [Accepted: 04/07/2024] [Indexed: 04/13/2024]
Abstract
OBJECTIVE Predicting Intensive Care Unit (ICU) Length of Stay (LOS) accurately can improve patient wellness, hospital operations, and the health system's financial status. This study focuses on predicting the prolonged ICU LOS (≥3 days) of the 2nd admission, utilizing short historical data (1st admission only) for early-stage prediction, as well as incorporating medication information. MATERIALS AND METHODS We selected 18,572 ICU patients' records from the MIMIC-IV database for this study. We applied five machine learning classifiers: Logistic regression (LR), Random Forest (RF), Support Vector Machine (SVM), AdaBoost (AB) and XGBoost (XGB). We computed both the sum dose and the average dose for the medication and included them in our model. RESULTS The performance of the RF model demonstrates the highest level of accuracy compared to other models, as indicated by an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.716 and an Expected Calibration Error (ECE) of 0.023. DISCUSSION The calibration improved all five classifiers (LR, RF, SVC, AB, XGB) in terms of ECE. The most important two features for RF are the length of 1st admission and the patient's age when they visited the hospital. The most important medication features are Phytonadione and Metoprolol Succinate XL. Also, both the sum and the average dose for the medication features contributed to the prediction task. CONCLUSION Our model showed the capability to predict the prolonged ICU LOS of the 2nd admission by utilizing the demographic, diagnosis, and medication information from the 1st admission. This method can potentially support the prevention of patient complications and enhance resource allocation in hospitals.
Collapse
Affiliation(s)
- Min Zhang
- Applied Statistics, University of Michigan, Ann Arbor, MI, 48109, USA
| | - Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, 92093, USA.
| |
Collapse
|
2
|
Kim H, Lee C, Pendyala D, Ng A, Kuo TT. A Comparative Study for Blockchain Applications in Nursing Informatics. medRxiv 2024:2024.02.24.24301619. [PMID: 38464022 PMCID: PMC10925357 DOI: 10.1101/2024.02.24.24301619] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/12/2024]
Abstract
We explored blockchain's applications in nursing informatics, highlighting its potential to improve patient care and data management. We compared and analyzed eight studies focusing on blockchain in Electronic Health Records (EHR) management, nursing optimization, and research facilitation. Although most of these studies are in the proposal stage, blockchain's technical features show promise in enhancing nursing practices and supporting nursing informatics researchers with the integration of technologies.
Collapse
|
3
|
Sharma A, Edelson M, Kuo TT. Profiling Clinical Researchers Effectively using Embeddings and Clustering. medRxiv 2024:2024.01.16.24300807. [PMID: 38293223 PMCID: PMC10827253 DOI: 10.1101/2024.01.16.24300807] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/01/2024]
Abstract
Effective researcher profiling is key to support rapid research team formation. We developed a profiling method using (1) widely accessible publication titles, (2) document embedding vector representations to consider background, and (3) both general and specific types of datasets. Our results showed that the most similar researchers have cosine similarities of 0.287/0.258. Our preliminary results can support biomedical informaticians to expedite collaborative clinical studies, enhance research quality, and eventually improve patient healthcare outcomes.
Collapse
|
4
|
Kuo TT, Pham A, Edelson ME, Kim J, Chan J, Gupta Y, Ohno-Machado L. Blockchain-enabled immutable, distributed, and highly available clinical research activity logging system for federated COVID-19 data analysis from multiple institutions. J Am Med Inform Assoc 2023; 30:1167-1178. [PMID: 36916740 PMCID: PMC10198529 DOI: 10.1093/jamia/ocad049] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2022] [Revised: 03/07/2023] [Accepted: 03/11/2023] [Indexed: 03/15/2023] Open
Abstract
OBJECTIVE We aimed to develop a distributed, immutable, and highly available cross-cloud blockchain system to facilitate federated data analysis activities among multiple institutions. MATERIALS AND METHODS We preprocessed 9166 COVID-19 Structured Query Language (SQL) code, summary statistics, and user activity logs, from the GitHub repository of the Reliable Response Data Discovery for COVID-19 (R2D2) Consortium. The repository collected local summary statistics from participating institutions and aggregated the global result to a COVID-19-related clinical query, previously posted by clinicians on a website. We developed both on-chain and off-chain components to store/query these activity logs and their associated queries/results on a blockchain for immutability, transparency, and high availability of research communication. We measured run-time efficiency of contract deployment, network transactions, and confirmed the accuracy of recorded logs compared to a centralized baseline solution. RESULTS The smart contract deployment took 4.5 s on an average. The time to record an activity log on blockchain was slightly over 2 s, versus 5-9 s for baseline. For querying, each query took on an average less than 0.4 s on blockchain, versus around 2.1 s for baseline. DISCUSSION The low deployment, recording, and querying times confirm the feasibility of our cross-cloud, blockchain-based federated data analysis system. We have yet to evaluate the system on a larger network with multiple nodes per cloud, to consider how to accommodate a surge in activities, and to investigate methods to lower querying time as the blockchain grows. CONCLUSION Blockchain technology can be used to support federated data analysis among multiple institutions.
Collapse
Affiliation(s)
- Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA
| | - Anh Pham
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA
| | - Maxim E Edelson
- Department of Computer Science and Engineering, University of California San Diego, La Jolla, California, USA
| | - Jihoon Kim
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA
| | - Jason Chan
- Poway High School, Poway, California, USA
| | - Yash Gupta
- Canyon Crest Academy, San Diego, California, USA
| | - Lucila Ohno-Machado
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA
- Division of Health Services Research & Development, VA San Diego Healthcare System, San Diego, California, USA
- Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, Connecticut, USA
| |
Collapse
|
5
|
Ohno-Machado L, Jiang X, Kuo TT, Tao S, Chen L, Ram PM, Zhang GQ, Xu H. A hierarchical strategy to minimize privacy risk when linking "De-identified" data in biomedical research consortia. J Biomed Inform 2023; 139:104322. [PMID: 36806328 DOI: 10.1016/j.jbi.2023.104322] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/27/2022] [Revised: 02/10/2023] [Accepted: 02/11/2023] [Indexed: 02/18/2023]
Abstract
Linking data across studies offers an opportunity to enrich data sets and provide a stronger basis for data-driven models for biomedical discovery and/or prognostication. Several techniques to link records have been proposed, and some have been implemented across data repositories holding molecular and clinical data. Not all these techniques guarantee appropriate privacy protection; there are trade-offs between (a) simple strategies that can be associated with data that will be linked and shared with any party and (b) more complex strategies that preserve the privacy of individuals across parties. We propose an intermediary, practical strategy to support linkage in studies that share de-identified data with Data Coordinating Centers. This technology can be extended to link data across multiple data hubs to support privacy preserving record linkage, considering data coordination centers and their awardees, which can be extended to a hierarchy of entities (e.g., awardees, data coordination centers, data hubs, etc.) b.
Collapse
Affiliation(s)
- Lucila Ohno-Machado
- UCSD Health Department of Biomedical Informatics, University of California San Diego Health, La Jolla, CA, USA; Biomedical Informatics & Data Science, Yale School of Medicine, New Haven, CT.
| | - Xiaoqian Jiang
- School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego Health, La Jolla, CA, USA
| | - Shiqiang Tao
- School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Luyao Chen
- School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Pritham M Ram
- School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Guo-Qiang Zhang
- School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA
| | - Hua Xu
- School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX, USA; Biomedical Informatics & Data Science, Yale School of Medicine, New Haven, CT
| |
Collapse
|
6
|
Kuo TT, Pham A. Quorum-based model learning on a blockchain hierarchical clinical research network using smart contracts. Int J Med Inform 2023; 169:104924. [PMID: 36402113 PMCID: PMC9984225 DOI: 10.1016/j.ijmedinf.2022.104924] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/23/2021] [Revised: 05/13/2022] [Accepted: 11/04/2022] [Indexed: 11/10/2022]
Abstract
BACKGROUND Collaborative privacy-preserving modeling across several healthcare institutions allows for the construction of more generalizable predictive models while protecting patient privacy. OBJECTIVE We aim at addressing the site availability issue on a hierarchical network by designing an immutable/transparent/source-verifiable quorum mechanism. METHODS We developed an approach to combine a hierarchical learning algorithm, a novel Proof-of-Quorum (PoQ) consensus protocol, and a design of blockchain smart contracts. We constructed QuorumChain as an example and evaluated the scenarios of site-unavailability during the initialization and/or iteration phases of the modeling process on three healthcare/genomic datasets. RESULTS When one or more sites would become unavailable, HierarchicalChain could not function, whereas QuorumChain improved predictive correctness significantly (the full Area Under the receiver operating characteristic Curve, or AUC, improved from 0.068 to 0.441, all with p-values < 0.001). CONCLUSION By constructing a quorum to continue the modeling process, QuorumChain possesses the capability to tackle the situation of sites being unavailable. It inherits the capability of learning on network-of-networks, improves learning continuity, and provides data/software immutability, transparency, and provenance, which can be important in expediting clinical research.
Collapse
Affiliation(s)
- Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, USA.
| | - Anh Pham
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, USA
| |
Collapse
|
7
|
Kuo TT, Jiang X, Tang H, Wang X, Harmanci A, Kim M, Post K, Bu D, Bath T, Kim J, Liu W, Chen H, Ohno-Machado L. The evolving privacy and security concerns for genomic data analysis and sharing as observed from the iDASH competition. J Am Med Inform Assoc 2022; 29:2182-2190. [PMID: 36164820 PMCID: PMC9667175 DOI: 10.1093/jamia/ocac165] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2022] [Revised: 08/25/2022] [Accepted: 09/13/2022] [Indexed: 01/11/2023] Open
Abstract
Concerns regarding inappropriate leakage of sensitive personal information as well as unauthorized data use are increasing with the growth of genomic data repositories. Therefore, privacy and security of genomic data have become increasingly important and need to be studied. With many proposed protection techniques, their applicability in support of biomedical research should be well understood. For this purpose, we have organized a community effort in the past 8 years through the integrating data for analysis, anonymization and sharing consortium to address this practical challenge. In this article, we summarize our experience from these competitions, report lessons learned from the events in 2020/2021 as examples, and discuss potential future research directions in this emerging field.
Collapse
Affiliation(s)
- Tsung-Ting Kuo
- Corresponding Author: Tsung-Ting Kuo, PhD, UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA 92093, USA;
| | | | | | | | - Arif Harmanci
- School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, Texas, USA
| | - Miran Kim
- Department of Mathematics, Hanyang University, Seoul, Republic of Korea,Department of Computer Science, Hanyang University, Seoul, Republic of Korea
| | - Kai Post
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA
| | - Diyue Bu
- Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington, Bloomington, Indiana, USA
| | - Tyler Bath
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA
| | - Jihoon Kim
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA
| | - Weijie Liu
- Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington, Bloomington, Indiana, USA
| | - Hongbo Chen
- Luddy School of Informatics, Computing, and Engineering, Indiana University Bloomington, Bloomington, Indiana, USA
| | - Lucila Ohno-Machado
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA,Division of Health Services Research & Development, Veteran Affairs San Diego Healthcare System, San Diego, California, USA
| |
Collapse
|
8
|
Li MM, Pham A, Kuo TT. Predicting COVID-19 county-level case number trend by combining demographic characteristics and social distancing policies. JAMIA Open 2022; 5:ooac056. [PMID: 35855422 PMCID: PMC9278037 DOI: 10.1093/jamiaopen/ooac056] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/20/2022] [Revised: 06/09/2022] [Accepted: 06/23/2022] [Indexed: 11/17/2022] Open
Abstract
Objective Predicting daily trends in the Coronavirus Disease 2019 (COVID-19) case number is important to support individual decisions in taking preventative measures. This study aims to use COVID-19 case number history, demographic characteristics, and social distancing policies both independently/interdependently to predict the daily trend in the rise or fall of county-level cases. Materials and Methods We extracted 2093 features (5 from the US COVID-19 case number history, 1824 from the demographic characteristics independently/interdependently, and 264 from the social distancing policies independently/interdependently) for 3142 US counties. Using the top selected 200 features, we built 4 machine learning models: Logistic Regression, Naïve Bayes, Multi-Layer Perceptron, and Random Forest, along with 4 Ensemble methods: Average, Product, Minimum, and Maximum, and compared their performances. Results The Ensemble Average method had the highest area-under the receiver operator characteristic curve (AUC) of 0.692. The top ranked features were all interdependent features. Conclusion The findings of this study suggest the predictive power of diverse features, especially when combined, in predicting county-level trends of COVID-19 cases and can be helpful to individuals in making their daily decisions. Our results may guide future studies to consider more features interdependently from conventionally distinct data sources in county-level predictive models. Our code is available at: https://doi.org/10.5281/zenodo.6332944.
Collapse
Affiliation(s)
- Megan Mun Li
- Department of Biology, University of California San Diego , La Jolla, California, USA
| | - Anh Pham
- UCSD Health Department of Biomedical Informatics, University of California San Diego , La Jolla, California, USA
| | - Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego , La Jolla, California, USA
| |
Collapse
|
9
|
Edelson M, Kuo TT. Generalizable prediction of COVID-19 mortality on worldwide patient data. JAMIA Open 2022; 5:ooac036. [PMID: 35663116 PMCID: PMC9129227 DOI: 10.1093/jamiaopen/ooac036] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2022] [Revised: 04/30/2022] [Accepted: 05/05/2022] [Indexed: 12/24/2022] Open
Abstract
Objective Predicting Coronavirus disease 2019 (COVID-19) mortality for patients is critical for early-stage care and intervention. Existing studies mainly built models on datasets with limited geographical range or size. In this study, we developed COVID-19 mortality prediction models on worldwide, large-scale "sparse" data and on a "dense" subset of the data. Materials and Methods We evaluated 6 classifiers, including logistic regression (LR), support vector machine (SVM), random forest (RF), multilayer perceptron (MLP), AdaBoost (AB), and Naive Bayes (NB). We also conducted temporal analysis and calibrated our models using Isotonic Regression. Results The results showed that AB outperformed the other classifiers for the sparse dataset, while LR provided the highest-performing results for the dense dataset (with area under the receiver operating characteristic curve, or AUC ≈ 0.7 for the sparse dataset and AUC = 0.963 for the dense one). We also identified impactful features such as symptoms, countries, age, and the date of death/discharge. All our models are well-calibrated (P > .1). Discussion Our results highlight the tradeoff of using sparse training data to increase generalizability versus training on denser data, which produces higher discrimination results. We found that covariates such as patient information on symptoms, countries (where the case was reported), age, and the date of discharge from the hospital or death were the most important for mortality prediction. Conclusion This study is a stepping-stone towards improving healthcare quality during the COVID-19 era and potentially other pandemics. Our code is publicly available at: https://doi.org/10.5281/zenodo.6336231.
Collapse
Affiliation(s)
- Maxim Edelson
- UCSD Department of Computer Science and Engineering, University of
California San Diego, La Jolla, California, USA
| | - Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California
San Diego, La Jolla, California, USA
| |
Collapse
|
10
|
Kuo TT, Ohno-Machado L. NLM’s sponsorship of research in biomedical informatics (1985–2016). ISU 2022; 42:61-70. [PMID: 35600120 PMCID: PMC9108565 DOI: 10.3233/isu-210137] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
The U.S. National Library of Medicine’s (NLM) funding for biomedical informatics research in the 1980s and 1990s focused on clinical decision support systems, which were also the focus of research for Donald A.B. Lindberg M.D. prior to becoming NLM’s director. The portfolio of projects expanded over the years. At NLM, Dr. Lindberg supported various large infrastructure programs that enabled biomedical informatics research, as well as investigator-initiated research projects that increasingly included biotechnology/bioinformatics and health services research. The authors review NLM’s sponsorship of research during Dr. Lindberg’s tenure as its Director. NLM’s funding significantly increased in the 2000’s and beyond. Authors report an analysis of R01 topics from 1985–2016 using data from NIH RePORTER. Dr. Lindberg’s legacy for biomedical informatics research is reflected by the research NLM supported under his leadership. The number of R01s remained steady over the years, but the funds provided within awards increased over time. A significant amount of NLM funds listed in RePORTER went into various types of infrastructure projects that laid a solid foundation for biomedical informatics research over multiple decades.
Collapse
|
11
|
Tellew J, Kuo TT. CertificateChain: decentralized healthcare training certificate management system using blockchain and smart contracts. JAMIA Open 2022; 5:ooac019. [PMID: 35571362 PMCID: PMC9097703 DOI: 10.1093/jamiaopen/ooac019] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2021] [Revised: 01/27/2022] [Accepted: 03/02/2022] [Indexed: 11/25/2022] Open
Abstract
Objective Managing training certificates is an important issue in research that can lead to
serious issues if not addressed properly. For institutions that currently do not have a
dedicated management system for these training certificates, a central database is the
most typical solution. However, such a system suffers from several risks, such as a
single-point-of-failure. Materials and Methods To address this issue, we developed and evaluated CertificateChain, a decentralized
training certificate management system by using peer-to-peer blockchain and automated
smart contracts. We developed an efficient certificate dividing-and-merging algorithm to
overcome the transaction size limit on blockchain. Results We performed experiments on the system to evaluate its performance, then created a web
app and tested the system in a real-world scenario. CertificateChain scaled linearly in
terms of time compared with the total number of certificates added and could be quickly
queried for existing data stored on-chain. Discussion CertificateChain was able to store and retrieve the training certificates on the
blockchain network, with limitations including a comparative analysis of other systems,
evaluation of different consensus protocols, examining certificates off-chain, a
thorough comparison with a centralized system, and the extension to the main public
Ethereum network. Conclusion We believe that these results indicate that blockchain technology could be a viable
decentralized alternative to traditional databases in this use case. Our software is
publicly available at: https://doi.org/10.5281/zenodo.6257094. In many research scenarios, certifications are required for data access requests.
Institutions must manage the relevant certificates to avoid potentially serious scenarios
that could impede research. Most existing systems suffer from risks such as
single-point-of-failure, a scenario in which an entire system can be rendered ineffective
with the failure of only one node in the network. To solve this problem, we developed
CertificateChain, a decentralized certificate management system that adopted blockchain
and smart contract (programs running on blockchain) technology and stores the certificates
on-chain. To evaluate the system’s performance, we performed experiments on it by storing
Collaborative Institutional Training Initiative (CITI) certificate files to test its
scalability and speed, as well as real-world testing using an accompanying web app. We
found that in terms of time, the system scaled linearly, and could quickly be searched for
any existing certificates. The limitations include the evaluation of other blockchain
consensus protocols, verification of certificate authenticity before and after uploading,
the scalability of upload file size, as well as an in-depth comparison to existing
centralized systems. After developing and evaluating the system, we believe that
CertificateChain shows potential to be a viable decentralized alternative for existing
centralized systems.
Collapse
Affiliation(s)
- Jeffrey Tellew
- Department of Computer Science, University of California Santa Barbara, Santa Barbara, California, USA
| | - Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA
| |
Collapse
|
12
|
Kuo TT, Ohno-Machado L. NLM's Sponsorship of Research in Biomedical Informatics (1985-2016). Stud Health Technol Inform 2022; 288:64-73. [PMID: 35102829 DOI: 10.3233/shti210982] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
The U.S. National Library of Medicine's (NLM) funding for biomedical informatics research in the 1980s and 1990s focused on clinical decision support systems, which were also the focus of research for Donald A.B. Lindberg M.D. prior to becoming NLM's director. The portfolio of projects expanded over the years. At NLM, Dr. Lindberg supported various large infrastructure programs that enabled biomedical informatics research, as well as investigator-initiated research projects that increasingly included biotechnology/bioinformatics and health services research. The authors review NLM's sponsorship of research during Dr. Lindberg's tenure as its Director. NLM's funding significantly increased in the 2000's and beyond. Authors report an analysis of R01 topics from 1985-2016 using data from NIH RePORTER. Dr. Lindberg's legacy for biomedical informatics research is reflected by the research NLM supported under his leadership. The number of R01s remained steady over the years, but the funds provided within awards increased over time. A significant amount of NLM funds listed in RePORTER went into various types of infrastructure projects that laid a solid foundation for biomedical informatics research over multiple decades.
Collapse
Affiliation(s)
- Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, USA
| | - Lucila Ohno-Machado
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, USA.,Division of Health Services Research & Development, VA San Diego Healthcare System, San Diego, CA, USA
| |
Collapse
|
13
|
Kuo TT, Pham A. Detecting model misconducts in decentralized healthcare federated learning. Int J Med Inform 2021; 158:104658. [PMID: 34923447 PMCID: PMC10017272 DOI: 10.1016/j.ijmedinf.2021.104658] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2021] [Revised: 11/23/2021] [Accepted: 12/05/2021] [Indexed: 10/19/2022]
Abstract
BACKGROUND To accelerate healthcare/genomic medicine research and facilitate quality improvement, researchers have started cross-institutional collaborations to use artificial intelligence on clinical/genomic data. However, there are real-world risks of incorrect models being submitted to the learning process, due to either unforeseen accidents or malicious intent. This may reduce the incentives for institutions to participate in the federated modeling consortium. Existing methods to deal with this "model misconduct" issue mainly focus on modifying the learning methods, and therefore are more specifically tied with the algorithm. BASIC PROCEDURES In this paper, we aim at solving the problem in an algorithm-agnostic way by (1) designing a simulator to generate various types of model misconduct, (2) developing a framework to detect the model misconducts, and (3) providing a generalizable approach to identify model misconducts for federated learning. We considered the following three categories: Plagiarism, Fabrication, and Falsification, and then developed a detection framework with three components: Auditing, Coefficient, and Performance detectors, with greedy parameter tuning. MAIN FINDINGS We generated 10 types of misconducts from models learned on three datasets to evaluate our detection method. Our experiments showed high recall with low added computational cost. Our proposed detection method can best identify the misconduct on specific sites from any learning iteration, whereas it is more challenging to precisely detect misconducts for a specific site and at a specific iteration. PRINCIPAL CONCLUSIONS We anticipate our study can support the enhancement of the integrity and reliability of federated machine learning on genomic/healthcare data.
Collapse
Affiliation(s)
- Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, USA.
| | - Anh Pham
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, USA
| |
Collapse
|
14
|
Abstract
BACKGROUND An image sharing framework is important to support downstream data analysis especially for pandemics like Coronavirus Disease 2019 (COVID-19). Current centralized image sharing frameworks become dysfunctional if any part of the framework fails. Existing decentralized image sharing frameworks do not store the images on the blockchain, thus the data themselves are not highly available, immutable, and provable. Meanwhile, storing images on the blockchain provides availability/immutability/provenance to the images, yet produces challenges such as large-image handling, high viewing latency while viewing images, and software inconsistency while storing/loading images. OBJECTIVE This study aims to store chest x-ray images using a blockchain-based framework to handle large images, improve viewing latency, and enhance software consistency. BASIC PROCEDURES We developed a splitting and merging function to handle large images, a feature that allows previewing an image earlier to improve viewing latency, and a smart contract to enhance software consistency. We used 920 publicly available images to evaluate the storing and loading methods through time measurements. MAIN FINDINGS The blockchain network successfully shares large images up to 18 MB and supports smart contracts to provide code immutability, availability, and provenance. Applying the preview feature successfully shared images 93% faster than sharing images without the preview feature. PRINCIPAL CONCLUSIONS The findings of this study can guide future studies to generalize our framework to other forms of data to improve sharing and interoperability.
Collapse
Affiliation(s)
- Megan Mun Li
- University of California San Diego, La Jolla, CA, USA
| | | |
Collapse
|
15
|
Kuo TT, Bath T, Ma S, Pattengale N, Yang M, Cao Y, Hudson CM, Kim J, Post K, Xiong L, Ohno-Machado L. Benchmarking blockchain-based gene-drug interaction data sharing methods: A case study from the iDASH 2019 secure genome analysis competition blockchain track. Int J Med Inform 2021; 154:104559. [PMID: 34474309 PMCID: PMC9933142 DOI: 10.1016/j.ijmedinf.2021.104559] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2020] [Revised: 07/24/2021] [Accepted: 07/27/2021] [Indexed: 01/11/2023]
Abstract
BACKGROUND Blockchain distributed ledger technology is just starting to be adopted in genomics and healthcare applications. Despite its increased prevalence in biomedical research applications, skepticism regarding the practicality of blockchain technology for real-world problems is still strong and there are few implementations beyond proof-of-concept. We focus on benchmarking blockchain strategies applied to distributed methods for sharing records of gene-drug interactions. We expect this type of sharing will expedite personalized medicine. BASIC PROCEDURES We generated gene-drug interaction test datasets using the Clinical Pharmacogenetics Implementation Consortium (CPIC) resource. We developed three blockchain-based methods to share patient records on gene-drug interactions: Query Index, Index Everything, and Dual-Scenario Indexing. MAIN FINDINGS We achieved a runtime of about 60 s for importing 4,000 gene-drug interaction records from four sites, and about 0.5 s for a data retrieval query. Our results demonstrated that it is feasible to leverage blockchain as a new platform to share data among institutions. PRINCIPAL CONCLUSIONS We show the benchmarking results of novel blockchain-based methods for institutions to share patient outcomes related to gene-drug interactions. Our findings support blockchain utilization in healthcare, genomic and biomedical applications. The source code is publicly available at https://github.com/tsungtingkuo/genedrug.
Collapse
Affiliation(s)
- Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, USA.
| | - Tyler Bath
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, USA
| | - Shuaicheng Ma
- Department of Computer Science, Emory University, Atlanta, GA, USA
| | | | - Meng Yang
- BGI-Shenzhen, Shenzhen, Guangdong, China,Bioinformatics Centre, Department of Biology, University of Copenhagen, Copenhagen, Denmark
| | - Yao Cao
- Department of Social Informatics, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto, Japan
| | | | - Jihoon Kim
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, USA
| | - Kai Post
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, USA
| | - Li Xiong
- Department of Computer Science, Emory University, Atlanta, GA, USA
| | - Lucila Ohno-Machado
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, USA,Division of Health Services Research & Development, VA San Diego Healthcare System, San Diego, CA, USA
| |
Collapse
|
16
|
Baxter SL, Saseendrakumar BR, Paul P, Kim J, Bonomi L, Kuo TT, Loperena R, Ratsimbazafy F, Boerwinkle E, Cicek M, Clark CR, Cohn E, Gebo K, Mayo K, Mockrin S, Schully SD, Ramirez A, Ohno-Machado L. Predictive Analytics for Glaucoma Using Data From the All of Us Research Program. Am J Ophthalmol 2021; 227:74-86. [PMID: 33497675 PMCID: PMC8184631 DOI: 10.1016/j.ajo.2021.01.008] [Citation(s) in RCA: 21] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2020] [Revised: 01/02/2021] [Accepted: 01/06/2021] [Indexed: 12/21/2022]
Abstract
PURPOSE To (1) use All of Us (AoU) data to validate a previously published single-center model predicting the need for surgery among individuals with glaucoma, (2) train new models using AoU data, and (3) share insights regarding this novel data source for ophthalmic research. DESIGN Development and evaluation of machine learning models. METHODS Electronic health record data were extracted from AoU for 1,231 adults diagnosed with primary open-angle glaucoma. The single-center model was applied to AoU data for external validation. AoU data were then used to train new models for predicting the need for glaucoma surgery using multivariable logistic regression, artificial neural networks, and random forests. Five-fold cross-validation was performed. Model performance was evaluated based on area under the receiver operating characteristic curve (AUC), accuracy, precision, and recall. RESULTS The mean (standard deviation) age of the AoU cohort was 69.1 (10.5) years, with 57.3% women and 33.5% black, significantly exceeding representation in the single-center cohort (P = .04 and P < .001, respectively). Of 1,231 participants, 286 (23.2%) needed glaucoma surgery. When applying the single-center model to AoU data, accuracy was 0.69 and AUC was only 0.49. Using AoU data to train new models resulted in superior performance: AUCs ranged from 0.80 (logistic regression) to 0.99 (random forests). CONCLUSIONS Models trained with national AoU data achieved superior performance compared with using single-center data. Although AoU does not currently include ophthalmic imaging, it offers several strengths over similar big-data sources such as claims data. AoU is a promising new data source for ophthalmic research.
Collapse
Affiliation(s)
- Sally L Baxter
- From the Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, (S.L.B., B.R.S.), La Jolla, California; UCSD Health Department of Biomedical Informatics, University of California San Diego, (S.L.B., B.R.S., P.P., J.K., L.B., T.-T.K., L.O.-M.), La Jolla, California.
| | - Bharanidharan Radha Saseendrakumar
- From the Viterbi Family Department of Ophthalmology and Shiley Eye Institute, University of California San Diego, (S.L.B., B.R.S.), La Jolla, California; UCSD Health Department of Biomedical Informatics, University of California San Diego, (S.L.B., B.R.S., P.P., J.K., L.B., T.-T.K., L.O.-M.), La Jolla, California
| | - Paulina Paul
- UCSD Health Department of Biomedical Informatics, University of California San Diego, (S.L.B., B.R.S., P.P., J.K., L.B., T.-T.K., L.O.-M.), La Jolla, California
| | - Jihoon Kim
- UCSD Health Department of Biomedical Informatics, University of California San Diego, (S.L.B., B.R.S., P.P., J.K., L.B., T.-T.K., L.O.-M.), La Jolla, California
| | - Luca Bonomi
- UCSD Health Department of Biomedical Informatics, University of California San Diego, (S.L.B., B.R.S., P.P., J.K., L.B., T.-T.K., L.O.-M.), La Jolla, California
| | - Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, (S.L.B., B.R.S., P.P., J.K., L.B., T.-T.K., L.O.-M.), La Jolla, California
| | - Roxana Loperena
- Vanderbilt Institute for Clinical and Translational Research, Vanderbilt University Medical Center, Nashville, Tennessee (R.L., F.R.)
| | - Francis Ratsimbazafy
- Vanderbilt Institute for Clinical and Translational Research, Vanderbilt University Medical Center, Nashville, Tennessee (R.L., F.R.)
| | - Eric Boerwinkle
- School of Public Health, The University of Texas Health Science Center at Houston, Houston, Texas (E.B.)
| | - Mine Cicek
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota (M.C.)
| | - Cheryl R Clark
- Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts (C.R.C.)
| | - Elizabeth Cohn
- Hunter-Bellevue School of Nursing, Hunter College City University of New York, New York, New York (E.C.)
| | - Kelly Gebo
- Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, Maryland
| | - Kelsey Mayo
- Vanderbilt Institute for Clinical and Translational Research, Vanderbilt University Medical Center, Nashville, Tennessee (R.L., F.R.)
| | - Stephen Mockrin
- Life Sciences Division, Leidos, Inc, Frederick, (S.M.), Maryland
| | - Sheri D Schully
- All of Us Research Program, National Institutes of Health, Bethesda (K.M., S.S.), Bethesda, Maryland
| | - Andrea Ramirez
- Department of Medicine, Vanderbilt University Medical Center, Nashville, Tennessee (A.R.)
| | - Lucila Ohno-Machado
- UCSD Health Department of Biomedical Informatics, University of California San Diego, (S.L.B., B.R.S., P.P., J.K., L.B., T.-T.K., L.O.-M.), La Jolla, California; Division of Health Services Research and Development, Veterans Affairs San Diego Healthcare System, La Jolla, California (L.O.-M.), USA
| |
Collapse
|
17
|
Kuo TT, Gabriel RA, Cidambi KR, Ohno-Machado L. EXpectation Propagation LOgistic REgRession on permissioned blockCHAIN (ExplorerChain): decentralized online healthcare/genomics predictive model learning. J Am Med Inform Assoc 2021; 27:747-756. [PMID: 32364235 PMCID: PMC7309256 DOI: 10.1093/jamia/ocaa023] [Citation(s) in RCA: 24] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2019] [Revised: 02/11/2020] [Accepted: 02/24/2020] [Indexed: 11/19/2022] Open
Abstract
Objective Predicting patient outcomes using healthcare/genomics data is an increasingly popular/important area. However, some diseases are rare and require data from multiple institutions to construct generalizable models. To address institutional data protection policies, many distributed methods keep the data locally but rely on a central server for coordination, which introduces risks such as a single point of failure. We focus on providing an alternative based on a decentralized approach. We introduce the idea using blockchain technology for this purpose, with a brief description of its own potential advantages/disadvantages. Materials and Methods We explain how our proposed EXpectation Propagation LOgistic REgRession on Permissioned blockCHAIN (ExplorerChain) can achieve the same results when compared to a distributed model that uses a central server on 3 healthcare/genomic datasets, and what trade-offs need to be considered when using centralized/decentralized methods. We explain how the use of blockchain technology can help decrease some of the problems encountered in decentralized methods. Results We showed that the discrimination power of ExplorerChain can be statistically similar to its counterpart central server-based algorithm. While ExplorerChain inherited some benefits of blockchain, it had a small increased running time. Discussion ExplorerChain has the same prerequisites as a distributed model with a centralized server for coordination. In a manner similar to secure multi-party computation strategies, it assumes that participating institutions are honest, but “curious.” Conclusion When evaluated on relatively small datasets, results suggest that ExplorerChain, which combines artificial intelligence and blockchain technologies, performs as well as a central server-based method, and may avoid some risks at the cost of efficiency.
Collapse
Affiliation(s)
- Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA
| | - Rodney A Gabriel
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA.,Department of Anesthesiology, University of California San Diego, San Diego, California, USA
| | - Krishna R Cidambi
- Department of Orthopaedic Surgery, University of California at San Diego, San Diego, California, USA
| | - Lucila Ohno-Machado
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA.,Division of Health Services Research & Development, VA San Diego Healthcare System, San Diego, California, USA
| |
Collapse
|
18
|
Kuo TT, Kim J, Gabriel RA. Privacy-preserving model learning on a blockchain network-of-networks. J Am Med Inform Assoc 2021; 27:343-354. [PMID: 31943009 PMCID: PMC7025358 DOI: 10.1093/jamia/ocz214] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/22/2019] [Revised: 11/04/2019] [Accepted: 12/02/2019] [Indexed: 01/07/2023] Open
Abstract
Objective To facilitate clinical/genomic/biomedical research, constructing generalizable predictive models using cross-institutional methods while protecting privacy is imperative. However, state-of-the-art methods assume a “flattened” topology, while real-world research networks may consist of “network-of-networks” which can imply practical issues including training on small data for rare diseases/conditions, prioritizing locally trained models, and maintaining models for each level of the hierarchy. In this study, we focus on developing a hierarchical approach to inherit the benefits of the privacy-preserving methods, retain the advantages of adopting blockchain, and address practical concerns on a research network-of-networks. Materials and Methods We propose a framework to combine level-wise model learning, blockchain-based model dissemination, and a novel hierarchical consensus algorithm for model ensemble. We developed an example implementation HierarchicalChain (hierarchical privacy-preserving modeling on blockchain), evaluated it on 3 healthcare/genomic datasets, as well as compared its predictive correctness, learning iteration, and execution time with a state-of-the-art method designed for flattened network topology. Results HierarchicalChain improves the predictive correctness for small training datasets and provides comparable correctness results with the competing method with higher learning iteration and similar per-iteration execution time, inherits the benefits of the privacy-preserving learning and advantages of blockchain technology, and immutable records models for each level. Discussion HierarchicalChain is independent of the core privacy-preserving learning method, as well as of the underlying blockchain platform. Further studies are warranted for various types of network topology, complex data, and privacy concerns. Conclusion We demonstrated the potential of utilizing the information from the hierarchical network-of-networks topology to improve prediction.
Collapse
Affiliation(s)
- Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA
| | - Jihoon Kim
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA
| | - Rodney A Gabriel
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA.,Department of Anesthesiology, University of California San Diego, San Diego, California, USA
| |
Collapse
|
19
|
Kuo TT, Jiang X, Tang H, Wang X, Bath T, Bu D, Wang L, Harmanci A, Zhang S, Zhi D, Sofia HJ, Ohno-Machado L. iDASH secure genome analysis competition 2018: blockchain genomic data access logging, homomorphic encryption on GWAS, and DNA segment searching. BMC Med Genomics 2020; 13:98. [PMID: 32693816 PMCID: PMC7372776 DOI: 10.1186/s12920-020-0715-0] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022] Open
Affiliation(s)
- Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, 92093, USA
| | - Xiaoqian Jiang
- School of Biomedical Informatics, The University of Texas Health Science Center, Houston, TX, 77030, USA
| | - Haixu Tang
- School of Informatics, Computing and Engineering, Indiana University Bloomington, Bloomington, IN, 47408, USA
| | - XiaoFeng Wang
- School of Informatics, Computing and Engineering, Indiana University Bloomington, Bloomington, IN, 47408, USA
| | - Tyler Bath
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, 92093, USA
| | - Diyue Bu
- School of Informatics, Computing and Engineering, Indiana University Bloomington, Bloomington, IN, 47408, USA
| | - Lei Wang
- School of Informatics, Computing and Engineering, Indiana University Bloomington, Bloomington, IN, 47408, USA
| | - Arif Harmanci
- School of Biomedical Informatics, The University of Texas Health Science Center, Houston, TX, 77030, USA
| | - Shaojie Zhang
- Department of Computer Science, University of Southern Florida, Orlando, FL, 32816, USA
| | - Degui Zhi
- School of Biomedical Informatics, The University of Texas Health Science Center, Houston, TX, 77030, USA
| | - Heidi J Sofia
- National Human Genome Research Institute, National Institutes of Health, Bethesda, MD, 20892, USA
| | - Lucila Ohno-Machado
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, 92093, USA.
- Division of Health Services Research & Development, VA San Diego Healthcare System, San Diego, CA, 92161, USA.
| |
Collapse
|
20
|
Kuo TT. The anatomy of a distributed predictive modeling framework: online learning, blockchain network, and consensus algorithm. JAMIA Open 2020; 3:201-208. [PMID: 32734160 PMCID: PMC7382618 DOI: 10.1093/jamiaopen/ooaa017] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2020] [Revised: 04/21/2020] [Accepted: 04/29/2020] [Indexed: 11/23/2022] Open
Abstract
Objective Cross-institutional distributed healthcare/genomic predictive modeling is an emerging technology that fulfills both the need of building a more generalizable model and of protecting patient data by only exchanging the models but not the patient data. In this article, the implementation details are presented for one specific blockchain-based approach, ExplorerChain, from a software development perspective. The healthcare/genomic use cases of myocardial infarction, cancer biomarker, and length of hospitalization after surgery are also described. Materials and Methods ExplorerChain’s 3 main technical components, including online machine learning, metadata of transaction, and the Proof-of-Information-Timed (PoINT) algorithm, are introduced in this study. Specifically, the 3 algorithms (ie, core, new network, and new site/data) are described in detail. Results ExplorerChain was implemented and the design details of it were illustrated, especially the development configurations in a practical setting. Also, the system architecture and programming languages are introduced. The code was also released in an open source repository available at https://github.com/tsungtingkuo/explorerchain. Discussion The designing considerations of semi-trust assumption, data format normalization, and non-determinism was discussed. The limitations of the implementation include fixed-number participating sites, limited join-or-leave capability during initialization, advanced privacy technology yet to be included, and further investigation in ethical, legal, and social implications. Conclusion This study can serve as a reference for the researchers who would like to implement and even deploy blockchain technology. Furthermore, the off-the-shelf software can also serve as a cornerstone to accelerate the development and investigation of future healthcare/genomic blockchain studies.
Collapse
Affiliation(s)
- Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA
| |
Collapse
|
21
|
Yu H, Sun H, Wu D, Kuo TT. Comparison of Smart Contract Blockchains for Healthcare Applications. AMIA Annu Symp Proc 2020; 2019:1266-1275. [PMID: 32308924 PMCID: PMC7153130] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
Blockchain and smart contracts (i.e., computer code that can be run on blockchain) are increasingly popular for healthcare applications. However, only very few implementations exist because of the complexity of the technologies. Although there are tutorials and reviews to introduce blockchain and smart contracts, a pragmatic comparison of such platforms is needed. In this study, we addressed practical considerations while building a healthcare blockchain and smart contract system, by (1) comparing technical features of platforms, (2) selecting three platforms, (3) constructing blockchain networks, (4) testing the blockchains, and (5) summarizing the experience and time used for implementation by students. We evaluated Ethereum, Hyperledger Fabric, and MultiChain, and confirmed that the selection of a proper platform depends on the requirements of the application. The findings of our study can accelerate the process and reduce the risk of adopting blockchain technology in biomedical and healthcare domain.
Collapse
Affiliation(s)
- Hongru Yu
- University of California San Diego, La Jolla, CA, USA
- Contributed Equally
| | - Haiyang Sun
- Syracuse University, Syracuse, NY, USA
- Contributed Equally
| | - Danyi Wu
- University of California San Diego, La Jolla, CA, USA
- Contributed Equally
| | | |
Collapse
|
22
|
Kuo TT, Zavaleta Rojas H, Ohno-Machado L. Comparison of blockchain platforms: a systematic review and healthcare examples. J Am Med Inform Assoc 2020; 26:462-478. [PMID: 30907419 PMCID: PMC7787359 DOI: 10.1093/jamia/ocy185] [Citation(s) in RCA: 75] [Impact Index Per Article: 18.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2018] [Revised: 12/02/2018] [Accepted: 01/07/2019] [Indexed: 12/22/2022] Open
Abstract
Objectives To introduce healthcare or biomedical blockchain applications and their underlying blockchain platforms, compare popular blockchain platforms using a systematic review method, and provide a reference for selection of a suitable blockchain platform given requirements and technical features that are common in healthcare and biomedical research applications. Target audience Healthcare or clinical informatics researchers and software engineers who would like to learn about the important technical features of different blockchain platforms to design and implement blockchain-based health informatics applications. Scope Covered topics include (1) a brief introduction to healthcare or biomedical blockchain applications and the benefits to adopt blockchain; (2) a description of key features of underlying blockchain platforms in healthcare applications; (3) development of a method for systematic review of technology, based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) statement, to investigate blockchain platforms for healthcare and medicine applications; (4) a review of 21 healthcare-related technical features of 10 popular blockchain platforms; and (5) a discussion of findings and limitations of the review.
Collapse
Affiliation(s)
- Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA
| | - Hugo Zavaleta Rojas
- Department of Mathematics, East Los Angeles College, Monterey Park, California, USA
| | - Lucila Ohno-Machado
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, California, USA.,Division of Health Services Research & Development, VA San Diego Healthcare System, La Jolla, California, USA
| |
Collapse
|
23
|
Kuo TT, Gabriel RA, Ohno-Machado L. Fair compute loads enabled by blockchain: sharing models by alternating client and server roles. J Am Med Inform Assoc 2020; 26:392-403. [PMID: 30892656 PMCID: PMC7787356 DOI: 10.1093/jamia/ocy180] [Citation(s) in RCA: 29] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/16/2018] [Revised: 10/16/2018] [Accepted: 12/02/2018] [Indexed: 11/28/2022] Open
Abstract
Objective Decentralized privacy-preserving predictive modeling enables multiple institutions to learn a more generalizable model on healthcare or genomic data by sharing the partially trained models instead of patient-level data, while avoiding risks such as single point of control. State-of-the-art blockchain-based methods remove the “server” role but can be less accurate than models that rely on a server. Therefore, we aim at developing a general model sharing framework to preserve predictive correctness, mitigate the risks of a centralized architecture, and compute the models in a fair way Materials and Methods We propose a framework that includes both server and “client” roles to preserve correctness. We adopt a blockchain network to obtain the benefits of decentralization, by alternating the roles for each site to ensure computational fairness. Also, we developed GloreChain (Grid Binary LOgistic REgression on Permissioned BlockChain) as a concrete example, and compared it to a centralized algorithm on 3 healthcare or genomic datasets to evaluate predictive correctness, number of learning iterations and execution time Results GloreChain performs exactly the same as the centralized method in terms of correctness and number of iterations. It inherits the advantages of blockchain, at the cost of increased time to reach a consensus model Discussion Our framework is general or flexible and can also address intrinsic challenges of blockchain networks. Further investigations will focus on higher-dimensional datasets, additional use cases, privacy-preserving quality concerns, and ethical, legal, and social implications Conclusions Our framework provides a promising potential for institutions to learn a predictive model based on healthcare or genomic data in a privacy-preserving and decentralized way.
Collapse
Affiliation(s)
- Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California, San Diego, La Jolla, California, USA
| | - Rodney A Gabriel
- UCSD Health Department of Biomedical Informatics, University of California, San Diego, La Jolla, California, USA.,Department of Anesthesiology, University of California, San Diego, San Diego, California, USA
| | - Lucila Ohno-Machado
- UCSD Health Department of Biomedical Informatics, University of California, San Diego, La Jolla, California, USA.,Division of Health Services Research & Development, VA San Diego Healthcare System, La Jolla, California, USA
| |
Collapse
|
24
|
Baxter SL, Marks C, Kuo TT, Ohno-Machado L, Weinreb RN. Machine Learning-Based Predictive Modeling of Surgical Intervention in Glaucoma Using Systemic Data From Electronic Health Records. Am J Ophthalmol 2019; 208:30-40. [PMID: 31323204 PMCID: PMC6888922 DOI: 10.1016/j.ajo.2019.07.005] [Citation(s) in RCA: 29] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/08/2019] [Revised: 07/08/2019] [Accepted: 07/11/2019] [Indexed: 01/27/2023]
Abstract
PURPOSE To predict the need for surgical intervention in patients with primary open-angle glaucoma (POAG) using systemic data in electronic health records (EHRs). DESIGN Development and evaluation of machine learning models. METHODS Structured EHR data of 385 POAG patients from a single academic institution were incorporated into models using multivariable logistic regression, random forests, and artificial neural networks. Leave-one-out cross-validation was performed. Mean area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, and Youden index were calculated for each model to evaluate performance. Systemic variables driving predictions were identified and interpreted. RESULTS Multivariable logistic regression was most effective at discriminating patients with progressive disease requiring surgery, with an AUC of 0.67. Higher mean systolic blood pressure was associated with significantly increased odds of needing glaucoma surgery (odds ratio [OR] = 1.09, P < .001). Ophthalmic medications (OR = 0.28, P < .001), non-opioid analgesic medications (OR = 0.21, P = .002), anti-hyperlipidemic medications (OR = 0.39, P = .004), macrolide antibiotics (OR = 0.40, P = .03), and calcium blockers (OR = 0.43, P = .03) were associated with decreased odds of needing glaucoma surgery. CONCLUSIONS Existing systemic data in the EHR has some predictive value in identifying POAG patients at risk of progression to surgical intervention, even in the absence of eye-specific data. Blood pressure-related metrics and certain medication classes emerged as predictors of glaucoma progression. This approach provides an opportunity for future development of automated risk prediction within the EHR based on systemic data to assist with clinical decision-making.
Collapse
Affiliation(s)
- Sally L Baxter
- Viterbi Family Department of Ophthalmology, Hamilton Glaucoma Center and Shiley Eye Institute, University of California, San Diego, La Jolla, California, USA; UCSD Health Department of Biomedical Informatics, University of California, San Diego, La Jolla, California, USA
| | - Charles Marks
- UCSD Health Department of Biomedical Informatics, University of California, San Diego, La Jolla, California, USA; Interdisciplinary Research on Substance Use Joint Doctoral Program, University of California, San Diego and San Diego State University, San Diego, California, USA
| | - Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California, San Diego, La Jolla, California, USA
| | - Lucila Ohno-Machado
- UCSD Health Department of Biomedical Informatics, University of California, San Diego, La Jolla, California, USA; Division of Health Services Research and Development, Veterans Administration San Diego Healthcare System, La Jolla, California, USA
| | - Robert N Weinreb
- Viterbi Family Department of Ophthalmology, Hamilton Glaucoma Center and Shiley Eye Institute, University of California, San Diego, La Jolla, California, USA.
| |
Collapse
|
25
|
Mackey TK, Kuo TT, Gummadi B, Clauson KA, Church G, Grishin D, Obbad K, Barkovich R, Palombini M. 'Fit-for-purpose?' - challenges and opportunities for applications of blockchain technology in the future of healthcare. BMC Med 2019; 17:68. [PMID: 30914045 PMCID: PMC6436239 DOI: 10.1186/s12916-019-1296-7] [Citation(s) in RCA: 78] [Impact Index Per Article: 15.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/27/2019] [Accepted: 02/27/2019] [Indexed: 12/16/2022] Open
Abstract
Blockchain is a shared distributed digital ledger technology that can better facilitate data management, provenance and security, and has the potential to transform healthcare. Importantly, blockchain represents a data architecture, whose application goes far beyond Bitcoin - the cryptocurrency that relies on blockchain and has popularized the technology. In the health sector, blockchain is being aggressively explored by various stakeholders to optimize business processes, lower costs, improve patient outcomes, enhance compliance, and enable better use of healthcare-related data. However, critical in assessing whether blockchain can fulfill the hype of a technology characterized as 'revolutionary' and 'disruptive', is the need to ensure that blockchain design elements consider actual healthcare needs from the diverse perspectives of consumers, patients, providers, and regulators. In addition, answering the real needs of healthcare stakeholders, blockchain approaches must also be responsive to the unique challenges faced in healthcare compared to other sectors of the economy. In this sense, ensuring that a health blockchain is 'fit-for-purpose' is pivotal. This concept forms the basis for this article, where we share views from a multidisciplinary group of practitioners at the forefront of blockchain conceptualization, development, and deployment.
Collapse
Affiliation(s)
- Tim K. Mackey
- Department of Anesthesiology and Division of Infectious Disease and Global Public Health, University of California, San Diego School of Medicine, San Diego, CA USA
- Department of Healthcare Policy, Technology and Research, University of California, San Diego – Extension, San Diego, CA USA
- Global Health Policy Institute, San Diego, CA USA
- BlockLAB, San Diego Supercomputer Center, La Jolla, CA USA
| | - Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA USA
| | - Basker Gummadi
- Bayer Corporation, 100 Bayer Boulevard, Whippany, NJ 07981 USA
| | - Kevin A. Clauson
- Department of Pharmacy Practice, Lipscomb University College of Pharmacy & Health Sciences, Nashville, TN USA
| | - George Church
- Department of Genetics, Harvard Medical School, Boston, MA USA
- Nebula Genomics, Inc., San Francisco, CA USA
| | - Dennis Grishin
- Department of Genetics, Harvard Medical School, Boston, MA USA
- Nebula Genomics, Inc., San Francisco, CA USA
| | - Kamal Obbad
- Nebula Genomics, Inc., San Francisco, CA USA
| | - Robert Barkovich
- Productive Consulting, Mountain View, CA USA
- Health Linkages Inc., Mountain View, CA USA
| | - Maria Palombini
- IEEE Standards Association, 445 Hoes Lane, Piscataway, NJ 08854 USA
| |
Collapse
|
26
|
Wu MY, Wang CH, Ng CY, Kuo TT, Chang YC, Yang CH, Lin JY, Ho HC, Chung WH, Chen CB. Periorbital erythema and swelling as a presenting sign of lupus erythematosus in tertiary referral centers and literature review. Lupus 2018; 27:1828-1837. [PMID: 30134759 DOI: 10.1177/0961203318792358] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Background Cutaneous lupus erythematosus (CLE) includes a broad range of dermatologic manifestations. Periorbital involvement, however, is a relatively rare clinical presentation of CLE. Objectives This clinical study aimed to investigate the characteristics of this unique presentation of CLE in tertiary medical centers. Methods We enrolled patients with periorbital erythema and swelling as the presenting sign of lupus erythematosus, from January 2003 to November 2017, using the data of 553 pathologically proven CLE cases from the registration database of the Chang Gung Memorial Hospitals in Taiwan. Results We enrolled a total of 25 patients. The mean age was 46.7 years and 68% of the patients were female. Most of the patients (84.0%) presented with unilateral involvement, with the left orbit involved in 15 patients (60%); the upper eyelid was the most frequently involved (72%). Mean duration between the onset of clinical manifestations and the diagnosis of CLE was approximately 59 weeks. Nineteen patients had been previously misdiagnosed. All patients had features compatible with CLE on histopathological examination. In contrast, laboratory analysis of the autoimmune profile often revealed negative results, including those for antinuclear antibodies (25%). Notably, anti-SSA/SSB (45.5%) showed the highest positive rate. During follow-up, six patients developed systemic lupus erythematosus (SLE) and two patients developed Sjögren syndrome. Conclusions The diagnosis of CLE presenting as periorbital erythema and swelling is often delayed because of clinical mimicry and the high proportion of negative results on autoantibody tests. Increased clinical suspicion and prompt histopathological examination are crucial for early diagnosis. Moreover, one-fourth of the patients ultimately developed SLE, which highlights the importance of clinical awareness.
Collapse
Affiliation(s)
- M Y Wu
- 1 Department of Dermatology, Chang Gung Memorial Hospital, Taipei, Linkou, and Keelung, Taiwan.,2 College of Medicine, Chang Gung University, Kwei-Shan, Taoyuan, Taiwan
| | - C H Wang
- 1 Department of Dermatology, Chang Gung Memorial Hospital, Taipei, Linkou, and Keelung, Taiwan.,2 College of Medicine, Chang Gung University, Kwei-Shan, Taoyuan, Taiwan
| | - C Y Ng
- 1 Department of Dermatology, Chang Gung Memorial Hospital, Taipei, Linkou, and Keelung, Taiwan.,2 College of Medicine, Chang Gung University, Kwei-Shan, Taoyuan, Taiwan.,7 Department of Pathology, Chang Gung Memorial Hospital, Linkou, Taiwan
| | - T T Kuo
- 2 College of Medicine, Chang Gung University, Kwei-Shan, Taoyuan, Taiwan.,7 Department of Pathology, Chang Gung Memorial Hospital, Linkou, Taiwan
| | - Y C Chang
- 1 Department of Dermatology, Chang Gung Memorial Hospital, Taipei, Linkou, and Keelung, Taiwan.,2 College of Medicine, Chang Gung University, Kwei-Shan, Taoyuan, Taiwan
| | - C H Yang
- 1 Department of Dermatology, Chang Gung Memorial Hospital, Taipei, Linkou, and Keelung, Taiwan.,2 College of Medicine, Chang Gung University, Kwei-Shan, Taoyuan, Taiwan
| | - J Y Lin
- 1 Department of Dermatology, Chang Gung Memorial Hospital, Taipei, Linkou, and Keelung, Taiwan.,2 College of Medicine, Chang Gung University, Kwei-Shan, Taoyuan, Taiwan
| | - H C Ho
- 1 Department of Dermatology, Chang Gung Memorial Hospital, Taipei, Linkou, and Keelung, Taiwan.,2 College of Medicine, Chang Gung University, Kwei-Shan, Taoyuan, Taiwan
| | - W H Chung
- 1 Department of Dermatology, Chang Gung Memorial Hospital, Taipei, Linkou, and Keelung, Taiwan.,2 College of Medicine, Chang Gung University, Kwei-Shan, Taoyuan, Taiwan.,4 Whole-Genome Research Core Laboratory of Human Diseases, Chang Gung Memorial Hospital, Keelung, Taiwan.,5 Chang Gung Immunology Consortium, Chang Gung Memorial Hospital and Chang Gung University, Taoyuan, Taiwan.,6 Department of Dermatology, Chang Gung Memorial Hospital, Xiamen, China
| | - C B Chen
- 1 Department of Dermatology, Chang Gung Memorial Hospital, Taipei, Linkou, and Keelung, Taiwan.,2 College of Medicine, Chang Gung University, Kwei-Shan, Taoyuan, Taiwan.,3 Graduate Institute of Clinical Medical Sciences, College of Medicine, Chang Gung University, Taoyuan, Taiwan.,4 Whole-Genome Research Core Laboratory of Human Diseases, Chang Gung Memorial Hospital, Keelung, Taiwan.,5 Chang Gung Immunology Consortium, Chang Gung Memorial Hospital and Chang Gung University, Taoyuan, Taiwan.,6 Department of Dermatology, Chang Gung Memorial Hospital, Xiamen, China
| |
Collapse
|
27
|
Gabriel RA, Kuo TT, McAuley J, Hsu CN. Identifying and characterizing highly similar notes in big clinical note datasets. J Biomed Inform 2018; 82:63-69. [PMID: 29679685 DOI: 10.1016/j.jbi.2018.04.009] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2018] [Revised: 04/16/2018] [Accepted: 04/17/2018] [Indexed: 11/19/2022]
Abstract
BACKGROUND Big clinical note datasets found in electronic health records (EHR) present substantial opportunities to train accurate statistical models that identify patterns in patient diagnosis and outcomes. However, near-to-exact duplication in note texts is a common issue in many clinical note datasets. We aimed to use a scalable algorithm to de-duplicate notes and further characterize the sources of duplication. METHODS We use an approximation algorithm to minimize pairwise comparisons consisting of three phases: (1) Minhashing with Locality Sensitive Hashing; (2) a clustering method using tree-structured disjoint sets; and (3) classification of near-duplicates (exact copies, common machine output notes, or similar notes) via pairwise comparison of notes in each cluster. We use the Jaccard Similarity (JS) to measure similarity between two documents. We analyzed two big clinical note datasets: our institutional dataset and MIMIC-III. RESULTS There were 1,528,940 notes analyzed from our institution. The de-duplication algorithm completed in 36.3 h. When the JS threshold was set at 0.7, the total number of clusters was 82,371 (total notes = 304,418). Among all JS thresholds, no clusters contained pairs of notes that were incorrectly clustered. When the JS threshold was set at 0.9 or 1.0, the de-duplication algorithm captured 100% of all random pairs with their JS at least as high as the set thresholds from the validation set. Similar performance was noted when analyzing the MIMIC-III dataset. CONCLUSIONS We showed that among the EHR from our institution and from the publicly-available MIMIC-III dataset, there were a significant number of near-to-exact duplicated notes.
Collapse
Affiliation(s)
- Rodney A Gabriel
- UCSD Health Department of Biomedical Informatics, University of California, San Diego, 9500 Gilman Dr, La Jolla, CA 92093, USA; Department of Anesthesiology, University of California, San Diego, 200 West Arbor Dr, San Diego, CA 92103, USA.
| | - Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California, San Diego, 9500 Gilman Dr, La Jolla, CA 92093, USA
| | - Julian McAuley
- Department of Computer Science and Engineering, University of California, San Diego, 9500 Gilman Dr, La Jolla, CA 92093, USA
| | - Chun-Nan Hsu
- UCSD Health Department of Biomedical Informatics, University of California, San Diego, 9500 Gilman Dr, La Jolla, CA 92093, USA
| |
Collapse
|
28
|
Kuo TT, Kim HE, Ohno-Machado L. Blockchain distributed ledger technologies for biomedical and health care applications. J Am Med Inform Assoc 2018; 24:1211-1220. [PMID: 29016974 PMCID: PMC6080687 DOI: 10.1093/jamia/ocx068] [Citation(s) in RCA: 260] [Impact Index Per Article: 43.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2017] [Accepted: 06/30/2017] [Indexed: 11/16/2022] Open
Abstract
Objectives To introduce blockchain technologies, including their benefits, pitfalls, and the latest applications, to the biomedical and health care domains. Target Audience Biomedical and health care informatics researchers who would like to learn about blockchain technologies and their applications in the biomedical/health care domains. Scope The covered topics include: (1) introduction to the famous Bitcoin crypto-currency and the underlying blockchain technology; (2) features of blockchain; (3) review of alternative blockchain technologies; (4) emerging nonfinancial distributed ledger technologies and applications; (5) benefits of blockchain for biomedical/health care applications when compared to traditional distributed databases; (6) overview of the latest biomedical/health care applications of blockchain technologies; and (7) discussion of the potential challenges and proposed solutions of adopting blockchain technologies in biomedical/health care domains.
Collapse
Affiliation(s)
- Tsung-Ting Kuo
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, USA
| | - Hyeon-Eui Kim
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, USA
| | - Lucila Ohno-Machado
- UCSD Health Department of Biomedical Informatics, University of California San Diego, La Jolla, CA, USA.,Division of Health Services Research and Development, Veterans Administration San Diego Healthcare System, La Jolla, CA, USA
| |
Collapse
|
29
|
Kuo TT, Rao P, Maehara C, Doan S, Chaparro JD, Day ME, Farcas C, Ohno-Machado L, Hsu CN. Ensembles of NLP Tools for Data Element Extraction from Clinical Notes. AMIA Annu Symp Proc 2017; 2016:1880-1889. [PMID: 28269947 PMCID: PMC5333200] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Subscribe] [Scholar Register] [Indexed: 06/06/2023]
Abstract
Natural Language Processing (NLP) is essential for concept extraction from narrative text in electronic health records (EHR). To extract numerous and diverse concepts, such as data elements (i.e., important concepts related to a certain medical condition), a plausible solution is to combine various NLP tools into an ensemble to improve extraction performance. However, it is unclear to what extent ensembles of popular NLP tools improve the extraction of numerous and diverse concepts. Therefore, we built an NLP ensemble pipeline to synergize the strength of popular NLP tools using seven ensemble methods, and to quantify the improvement in performance achieved by ensembles in the extraction of data elements for three very different cohorts. Evaluation results show that the pipeline can improve the performance of NLP tools, but there is high variability depending on the cohort.
Collapse
Affiliation(s)
| | | | | | - Son Doan
- University of California San Diego, La Jolla, CA
| | | | | | | | | | - Chun-Nan Hsu
- University of California San Diego, La Jolla, CA
| |
Collapse
|
30
|
Wei W, Marmor R, Singh S, Wang S, Demner-Fushman D, Kuo TT, Hsu CN, Ohno-Machado L. Finding Related Publications: Extending the Set of Terms Used to Assess Article Similarity. AMIA Jt Summits Transl Sci Proc 2016; 2016:225-34. [PMID: 27570676 PMCID: PMC5001748] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 11/15/2022]
Abstract
Recommendation of related articles is an important feature of the PubMed. The PubMed Related Citations (PRC) algorithm is the engine that enables this feature, and it leverages information on 22 million citations. We analyzed the performance of the PRC algorithm on 4584 annotated articles from the 2005 Text REtrieval Conference (TREC) Genomics Track data. Our analysis indicated that the PRC highest weighted term was not always consistent with the critical term that was most directly related to the topic of the article. We implemented term expansion and found that it was a promising and easy-to-implement approach to improve the performance of the PRC algorithm for the TREC 2005 Genomics data and for the TREC 2014 Clinical Decision Support Track data. For term expansion, we trained a Skip-gram model using the Word2Vec package. This extended PRC algorithm resulted in higher average precision for a large subset of articles. A combination of both algorithms may lead to improved performance in related article recommendations.
Collapse
Affiliation(s)
- Wei Wei
- Health System Department of Biomedical Informatics, UC San Diego, San Diego, CA
| | - Rebecca Marmor
- Health System Department of Biomedical Informatics, UC San Diego, San Diego, CA
| | - Siddharth Singh
- Health System Department of Biomedical Informatics, UC San Diego, San Diego, CA
| | - Shuang Wang
- Health System Department of Biomedical Informatics, UC San Diego, San Diego, CA
| | | | - Tsung-Ting Kuo
- Health System Department of Biomedical Informatics, UC San Diego, San Diego, CA
| | - Chun-Nan Hsu
- Health System Department of Biomedical Informatics, UC San Diego, San Diego, CA
| | - Lucila Ohno-Machado
- Health System Department of Biomedical Informatics, UC San Diego, San Diego, CA
| |
Collapse
|
31
|
Jain S, Tumkur KR, Kuo TT, Bhargava S, Lin G, Hsu CN. Erratum to: Weakly supervised learning of biomedical information extraction from curated data. BMC Bioinformatics 2016; 17:84. [PMID: 26868016 PMCID: PMC4751676 DOI: 10.1186/s12859-016-0925-9] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/23/2022] Open
Affiliation(s)
- Suvir Jain
- Department of Computer Science and Engineering, Jacobs School of Engineering, University of California, 9500 Gilman Drive, La Jolla, San Diego, 92093, USA
| | - Kashyap R Tumkur
- Department of Computer Science and Engineering, Jacobs School of Engineering, University of California, 9500 Gilman Drive, La Jolla, San Diego, 92093, USA
| | - Tsung-Ting Kuo
- Department of Biomedical Informatics, School of Medicine, University of California, 9500 Gilman Drive, La Jolla, San Diego, 92093, USA
| | - Shitij Bhargava
- Department of Computer Science and Engineering, Jacobs School of Engineering, University of California, 9500 Gilman Drive, La Jolla, San Diego, 92093, USA
| | - Gordon Lin
- Department of Computer Science and Engineering, Jacobs School of Engineering, University of California, 9500 Gilman Drive, La Jolla, San Diego, 92093, USA
| | - Chun-Nan Hsu
- Department of Biomedical Informatics, School of Medicine, University of California, 9500 Gilman Drive, La Jolla, San Diego, 92093, USA.
| |
Collapse
|
32
|
Abstract
Background Numerous publicly available biomedical databases derive data by curating from literatures. The curated data can be useful as training examples for information extraction, but curated data usually lack the exact mentions and their locations in the text required for supervised machine learning. This paper describes a general approach to information extraction using curated data as training examples. The idea is to formulate the problem as cost-sensitive learning from noisy labels, where the cost is estimated by a committee of weak classifiers that consider both curated data and the text. Results We test the idea on two information extraction tasks of Genome-Wide Association Studies (GWAS). The first task is to extract target phenotypes (diseases or traits) of a study and the second is to extract ethnicity backgrounds of study subjects for different stages (initial or replication). Experimental results show that our approach can achieve 87 % of Precision-at-2 (P@2) for disease/trait extraction, and 0.83 of F1-Score for stage-ethnicity extraction, both outperforming their cost-insensitive baseline counterparts. Conclusions The results show that curated biomedical databases can potentially be reused as training examples to train information extractors without expert annotation or refinement, opening an unprecedented opportunity of using “big data” in biomedical text mining. Electronic supplementary material The online version of this article (doi:10.1186/s12859-015-0844-1) contains supplementary material, which is available to authorized users.
Collapse
Affiliation(s)
- Suvir Jain
- Department of Computer Science and Engineering, Jacobs School of Engineering, University of California, San Diego, 9500 Gilman Drive, La Jolla, 92093, USA.
| | - Kashyap R Tumkur
- Department of Computer Science and Engineering, Jacobs School of Engineering, University of California, San Diego, 9500 Gilman Drive, La Jolla, 92093, USA.
| | - Tsung-Ting Kuo
- Department of Biomedical Informatics, School of Medicine, University of California, San Diego, 9500 Gilman Drive, La Jolla, 92093, USA.
| | - Shitij Bhargava
- Department of Computer Science and Engineering, Jacobs School of Engineering, University of California, San Diego, 9500 Gilman Drive, La Jolla, 92093, USA.
| | - Gordon Lin
- Department of Computer Science and Engineering, Jacobs School of Engineering, University of California, San Diego, 9500 Gilman Drive, La Jolla, 92093, USA.
| | - Chun-Nan Hsu
- Department of Biomedical Informatics, School of Medicine, University of California, San Diego, 9500 Gilman Drive, La Jolla, 92093, USA.
| |
Collapse
|
33
|
|
34
|
Lo HY, Chang CM, Chiang TH, Hsiao CY, Huang A, Kuo TT, Lai WC, Yang MH, Yeh JJ, Yen CC, Lin SD. Learning to improve area-under-FROC for imbalanced medical data classification using an ensemble method. ACTA ACUST UNITED AC 2008. [DOI: 10.1145/1540276.1540290] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
Abstract
This paper presents our solution for KDD Cup 2008 competition that aims at optimizing the area under ROC for breast cancer detection. We exploited weighted-based classification mechanism to improve the accuracy of patient classification (each patient is represented by a collection of data points). Final predictions for challenge 1 are generated by combining outputs from weighted SVM and AdaBoost; whereas we integrate SVM, AdaBoost, and GA to produce the results for challenge 2. We have also tried location-based classification and model adaptation to add the testing data into training. Our results outperform other participants given the same set of features, and was selected as the joint winner in KDD Cup 2008.
Collapse
Affiliation(s)
- Hung-Yi Lo
- National Taiwan University, Taipei, Taiwan
| | | | | | | | - Anta Huang
- National Taiwan University, Taipei, Taiwan
| | | | | | | | | | | | | |
Collapse
|
35
|
Dai H, Tsay SH, Kuo TT, Lin YH, Wu WC. Neolysogenization of Xanthomonas campestris pv. citri infected with filamentous phage Cf16. Virology 2008; 156:313-20. [PMID: 18644554 DOI: 10.1016/0042-6822(87)90411-9] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/1986] [Accepted: 10/13/1986] [Indexed: 10/26/2022]
Abstract
All previously described filamentous bacteriophages are capable of persistent infection while their DNA replicates as an episome in the host cell. Filamentous phage Cf16 undergoes an infectious cycle different from other filamentous phages reported heretofore. Upon initial infection with Cf16, infective centers are formed, each of which produces a large number of phage particles. As the infectious cycle progresses, the phage particles released and infective centers formed per carrier cell decrease with time. Finally, the Cf16 enters a "prophage" state, in which the carrier cell becomes lysogenic containing only one complete phage genome in an integrated form. One out of 10(3)-10(6) lysogenic cells can develop spontaneously into an infective center, which releases only one to two phage particles per cell in stationary phase culture. After infection, the Cf16 genome integrates into the host chromosome and replicates as a part of it. Free RF (replicative form) coexists with the integrated form and replicates independently from host chromosome. Upon further division, carrier cells eliminate the free RF at each succeeding generation. When Cf16 reaches the "prophage" state, only the integrated phage genome remains in the carrier cell with no detectable free RF.
Collapse
Affiliation(s)
- H Dai
- Institute of Botany, Academia Sinica, Nankang, Taipei, Taiwan, Republic of China
| | | | | | | | | |
Collapse
|
36
|
Kuo TT, Lin YH, Huang CM, Chang SF, Dai H, Feng TY. The lysogenic cycle of the filamentous phage Cflt from Xanthomonas campestris pv. citri. Virology 2008; 156:305-12. [PMID: 18644553 DOI: 10.1016/0042-6822(87)90410-7] [Citation(s) in RCA: 19] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/21/1986] [Accepted: 10/13/1986] [Indexed: 10/26/2022]
Abstract
A phage, Cflt, forming turbid plaques, was isolated from Xanthomonas campestris pv. citri. After infection, infected sensitive cells become immune to Cflt and produce very few phages. These properties were genetically rather stable. The phage was purified and shown to be filamentous with a size of 1157 +/- 73 nm. The genome size is about 7.62 kb. The phage does not affect the growth of host bacteria. Under natural cultivation conditions Cflt-lysogenized cells could be induced spontaneously to give high phage yields, or cured to give phage-free cells. The integration of Cflt DNA into host DNA was proved by Southern blot hybridization. The lysogenic phage was genetically stable in log phase cells and persisted in stationary phase cells through many cell generations in the absence of extracellular phage reinfection.
Collapse
Affiliation(s)
- T T Kuo
- Institute of Botany, Academia Sinica, Taipei, Republic of China
| | | | | | | | | | | |
Collapse
|
37
|
Chen TC, Nakanuma Y, Zen Y, Chen MF, Jan YY, Yeh TS, Chiu CT, Kuo TT, Kamiya J, Oda K, Hamaguchi M, Ohno Y, Hsieh LL, Nimura Y. Intraductal papillary neoplasia of the liver associated with hepatolithiasis. Hepatology 2001; 34:651-8. [PMID: 11584359 DOI: 10.1053/jhep.2001.28199] [Citation(s) in RCA: 213] [Impact Index Per Article: 9.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/21/2022]
Abstract
Intraductal papillary growth of neoplastic biliary epithelia with a fine fibrovascular stalk (intraductal papillary neoplasia of liver [IPN-L]) resembling intraductal papillary mucinous neoplasm of pancreas is occasionally associated with hepatolithiasis. In this study, 136 cases of hepatolithiasis in Taiwan, between January 1998 and March 2000, and an additional 21 cases of IPN-L before December 1998, were examined histologically. IPN-L was found in 41 of 136 hepatolithiasis cases (30.1%). Sixty-two IPN-L cases (42 women and 20 men; age range, 59.8 +/- 10 years) were divided into 4 types (type 1, IPN-L with low-grade dysplasia, 23 cases; type 2, IPN-L with high grade dysplasia, 11 cases; type 3, IPN-L with in situ and microinvasive carcinoma, 13 cases; and type 4, IPN-L of types 2 and 3 with distinct invasive carcinoma, 15 cases). Intraductal spreading and glandular involvement were commonly observed in all types. About half of types 3 and 4 cases had mucobilia, and mucinous carcinoma was variably found in two thirds of group 4 patients. IPN-L frequently showed variable gastroenteric differentiation such as goblet cells and foveolar and colon-like metaplasia. IPN-L with goblet cells and colon-like metaplasia was frequently associated with overproduction of mucin and mucobilia (P <.01). In Japan, IPN-L was not frequent in hepatolithiasis (12 of 135 cases). In conclusion, IPN-L forms a spectrum of biliary neoplasm in hepatolithiasis. It often displays variable gastroenteric metaplasia and significant intraductal spread. IPN-L tends to progress to mucinous carcinoma. Formerly reported "mucin-producing intrahepatic cholangiocarcinoma" with a favorable prognosis is included in IPN-L.
Collapse
Affiliation(s)
- T C Chen
- Department of Pathology, Chang Gung Memorial Hospital, Chang Gung University School of Medicine, Tao Yuan, Taipei, Taiwan
| | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
38
|
Abstract
The classification of thymic epithelial neoplasms has been one of the most controversial issues in tumor pathology. There are two opposing schools of pathologists holding different views regarding the classification of thymic epithelial neoplasms. One school of pathologists believe that histological classification of thymomas is not possible or useful. Another school of pathologists believe that thymomas can be histologically subclassified despite their complex histomorphology and that these histological subtypes correlate with their aggressiveness and clinical behavior. A compromised histological classification has been established by World Health Organization (WHO) to designate thymic epithelial neoplasms with letters and numbers. This classification should be adopted internationally to facilitate the communication among concerned pathologists and oncologists. A simple histological classification of thymomas based on cytomorphology and supported by cytokeratin expressions is proposed and compared to the WHO and Müller-Hermelink's histogenetic classifications.
Collapse
Affiliation(s)
- T T Kuo
- Department of Pathology, Chang Gung Memorial Hospital, 199 Tun Hwa North Road, Taipei 105, Taiwan.
| |
Collapse
|
39
|
Abstract
Toxoplasmosis is a common cause of lymphadenopathy, but toxoplasmic cysts are not usually found in histological sections used for establishing diagnosis, except on extremely rare occasions. The histopathological triad of florid reactive follicular hyperplasia, clusters of epithelioid histiocytes, and focal sinusoidal distention by monocytoid B cells has been considered to be diagnostic of toxoplasmic lymphadenitis, but the validity of the histopathological triad is based indirectly on serological correlation only. The demonstration of Toxoplasma gondii DNA in lymph nodes displaying the histopathological triad will indicate the validity of the histopathological triad as the criterion for the histopathological diagnosis of toxoplasmic lymphadenitis. We used frozen tissues of 12 lymph nodes with the histopathological triad and tissues of 27 lymph nodes from patients with various other conditions (including 13 cases of follicular lymphoid hyperplasia, FLH; three cases of dermatopathic lymphadenopathy, DPL; two cases of plasmacytosis; two cases of Castleman's disease; two cases of metastatic adenocarcinoma; and five cases of lymphoma) to detect T. gondii DNA by polymerase chain reaction. Ten out of 12 lymph nodes with the triad and six out of 27 lymph nodes without the triad were positive for T. gondii DNA. Thus, the sensitivity of the triad was 62.5% (10/16) and the specificity was 91.3% (21/23). The predictive value of positive tests was 83.3% (10/12) and the predictive value of negative tests was 77.7% (21/27). The six cases positive for T. gondii DNA without the triad were four cases of FLH, one case of DPL, and one case of plasmacytosis. None of the neoplastic diseases was positive. The false positive and negative cases could be due to sampling problems or past T. gondii infection. The results confirm that the histopathological triad is highly specific for the diagnosis of toxoplasmic lymphadenitis and can be used confidently.
Collapse
Affiliation(s)
- M H Lin
- Chang Gung University School of Medical Technology, Chang Gung Memorial Hospital, 199 Tun Hwa North Road, Taipei 105, Taiwan, ROC
| | | |
Collapse
|
40
|
Wang BD, Kuo TT. Induction of a mitosis delay and cell lysis by high-level secretion of mouse alpha-amylase from Saccharomyces cerevisiae. Appl Environ Microbiol 2001; 67:3693-701. [PMID: 11472949 PMCID: PMC93073 DOI: 10.1128/aem.67.8.3693-3701.2001] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
Abstract
Some foreign proteins are produced in yeast in a cell cycle-dependent manner, but the cause of the cell cycle dependency is unknown. In this study, we found that Saccharomyces cerevisiae cells secreting high levels of mouse alpha-amylase have elongated buds and are delayed in cell cycle completion in mitosis. The delayed cell mitosis suggests that critical events during exit from mitosis might be disturbed. We found that the activities of PP2A (protein phosphatase 2A) and MPF (maturation-promoting factor) were reduced in alpha-amylase-oversecreting cells and that these cells showed a reduced level of assembly checkpoint protein Cdc55, compared to the accumulation in wild-type cells. MPF inactivation is due to inhibitory phosphorylation on Cdc28, as a cdc28 mutant which lacks an inhibitory phosphorylation site on Cdc28 prevents MPF inactivation and prevents the defective bud morphology induced by overproduction of alpha-amylase. Our data also suggest that high levels of alpha-amylase may downregulate PPH22, leading to cell lysis. In conclusion, overproduction of heterologous alpha-amylase in S. cerevisiae results in a negative regulation of PP2A, which causes mitotic delay and leads to cell lysis.
Collapse
Affiliation(s)
- B D Wang
- Institute of Molecular Biology, Academia Sinica, Nankang, Taipei 115, Taiwan.
| | | |
Collapse
|
41
|
Lin SH, Huang HJ, Yang BC, Kuo TT. UV-induced increase in RNA polymerase activity in Xanthomonas oryzae pathovar oryzae. Curr Microbiol 2001; 43:120-3. [PMID: 11391475 DOI: 10.1007/s002840010272] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2000] [Accepted: 01/10/2001] [Indexed: 11/28/2022]
Abstract
UV radiation is thought to inhibit transcriptional elongation, as a result of the formation of pyrimidine dimers in the DNA template, as well as to activate specific transcription factors. However, the effect of UV radiation on the enzymatic activity of RNA polymerase has remained unknown. With the use of an in vitro assay, UV irradiation of Xanthomonas oryzae pathovar oryzae has now been shown to increase RNA polymerase activity. This effect was maximal at a UV dose of approximately 12 J m(-2) and at approximately 60 min after irradiation. It was also not inhibited by pretreatment of cells with chloramphenicol, an inhibitor of protein synthesis. Immunoprecipitation with antibodies to the RNA polymerase core enzyme revealed that exposure of the bacterial cells to UV radiation induced the association of the core enzyme with a protein of approximately 29 kDa. These results demonstrate that UV radiation increases the activity of RNA polymerase, and they suggest that this effect may be related to the repair of DNA damage.
Collapse
Affiliation(s)
- S H Lin
- Room 121, Institute of Molecular Biology 48, Academia Sinica, Nankang, 115 Taipei, Taiwan, Republic of China
| | | | | | | |
Collapse
|
42
|
Abstract
Two patients presenting with chronic pigmented purpuric dermatosis (CPPD) on the dorsum of both feet were found to show granulomatous inflammation superimposed on the pathological changes of CPPD. Two similar cases have been reported from Japan. The unique clinicopathological features of this group of patients suggest that they have a rare granulomatous variant of CPPD.
Collapse
Affiliation(s)
- W R Wong
- Department of Dermatology, Chang Gung Memorial Hospital, 199 Tung Hwa North Road, Taipei 105, Taiwan.
| | | | | | | |
Collapse
|
43
|
Abstract
The role of the LexA protein and, specifically, its effect on recA expression were analyzed in Xanthomonas campestris pathovar citri (X.c. pv. citri). Overexpression of LexA from X.c. pv. citri, in the plant pathogen, as well as in Escherichia coli, results in increased sensitivity to the DNA-damaging agents mitomycin C and ultraviolet radiation, indicating that the recombinant X.c. pv. citri LexA protein is functional in a different bacterial species. Immunoblot analysis revealed that the overexpressed LexA protein functioned as a repressor of recA expression in X.c. pv. citri, and that the mitomycin C-induced increase in the abundance of RecA was accompanied by specific proteolysis of LexA that required RecA. Although the LexA protein from X.c. pv. citri also blocked the expression of recA in E. coli, the E. coli RecA protein was not able to support the autocatalytic cleavage of LexA from the plant pathogen. The transcription start site of the X.c. pv. citri lexA gene was identified, and the region upstream of this gene was shown to confer responsiveness to mitomycin C on a luciferase reporter gene construct. Electrophoretic mobility-shift assays demonstrated that X.c. pv. citri LexA interacts with the promoter region of X.c. pv. citri lexA, as well as with those of the recA genes of X.c. pv. citri and E. coli. These results indicate that LexA functions as a repressor of gene expression in X.c. pv. citri just as it does in E. coli.
Collapse
Affiliation(s)
- Y C Yang
- Institute of Life Science, National Defense Medical Center, Taipei, Taiwan, Republic of China
| | | | | | | |
Collapse
|
44
|
Abstract
An oversecreting mutant of Saccharomyces cerevisiae was obtained from about 400 meiotic segregants derived from thediploid cells made by crossing the HBsAg-induced mutant NI-C with the wild-type strain Sey6211. When transformed with a plasmid containing mouse alpha-amylase cDNA, the mutant (NI-C-D4) exhibited an increased capacity (up to 13-fold) for the secretion of mouse alpha-amylase, higher than the parental strains and other standard wild-type strains. It was also shown that alpha-amylase secreted by the oversecreting mutant had a higher activity and contained more of the non-glycosylated form than the glycosylated form. This isolated oversecreting, low-glycosylation mutant may prove to be a potential S. cerevisiae host for the production of foreign proteins. Further genetic analysis suggested that the mutation responsible for the mutant's oversecretion was partially dominant and that both the oversecretion and low-glycosylation phenotypes were governed by a single chromosome mutation. These pleiotrophic phenotypes may be attributed to a defect in the synthesis of an ER-resident chaperone.
Collapse
Affiliation(s)
- B D Wang
- Institute of Molecular Biology, Academia Sinica, Nankang, Taipei, Taiwan.
| | | | | |
Collapse
|
45
|
Lin SY, Tsang NM, Kao SC, Hsieh YL, Chen YP, Tsai CS, Kuo TT, Hao SP, Chen IH, Hong JH. Presence of Epstein-Barr virus latent membrane protein 1 gene in the nasopharyngeal swabs from patients with nasopharyngeal carcinoma. Head Neck 2001; 23:194-200. [PMID: 11428449 DOI: 10.1002/1097-0347(200103)23:3<194::aid-hed1018>3.0.co;2-x] [Citation(s) in RCA: 45] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Nasopharyngeal carcinoma (NPC) is the most common head and neck malignancy in southeastern China and Taiwan. Early detection of the local disease followed immediately by proper treatment is essential to increase the cure and survival rates. Because every NPC tumor cell carries Epstein-Barr Virus (EBV) genomes, detection of EBV genomic DNA such as latent membrane protein 1 gene (LMP1) might indicate the presence of NPC. We developed a simple and noninvasive technique of nasopharyngeal swabbing to acquire nasopharyngeal cells for detecting the presence of EBV genome. The aim of this study was to investigate the feasibility and reliability of this technique. METHODS We collected nasopharyngeal cells by means of a nasopharyngeal swabbing technique and detected the presence of EBV LMP1 with polymerase chain reaction (PCR). Thirty-eight swab specimens were obtained from patients with NPC who were newly diagnosed or were just beginning radiotherapy. Two groups of control subjects were recruited, including 20 patients with other head and neck cancers and eight family members of the NPC patients. An additional group of 65 NPC patients were enrolled in the course of regular follow-up after definitive radiotherapy. RESULTS All of the samples yielded sufficient DNA for PCR amplification. Thirty-six of 38 NPC swab samples were positive for EBV LMP1, and all the control subjects had swab sample results negative for EBV. All five patients with suspected local recurrence exhibited positive EBV test results. CONCLUSIONS Demonstration of EBV LMP1 in the nasopharyngeal swab specimens detected NPC with a sensitivity of 94.7% and specificity of 100%. This study confirms the reliability and feasibility of nasopharyngeal swab in the predicting and screening of NPC.
Collapse
Affiliation(s)
- S Y Lin
- Department of Radiation Oncology, Chang Gung Memorial Hospital, Taoyuan, Taiwan, Republic of China.
| | | | | | | | | | | | | | | | | | | |
Collapse
|
46
|
Chien LF, Kuo TT. Reduction in mitochondrial respiratory capacity in Saccharomyces cerevisiae induced by expression of hepatitis B virus surface antigen. Microbios 2001; 105:29-41. [PMID: 11368090] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Subscribe] [Scholar Register] [Indexed: 04/16/2023]
Abstract
Transformants of Saccharomyces cerevisiae strain TL154 (MATalpha, trp1, leu2) expressing hepatitis B virus surface antigen showed reduced rates of cell growth compared with those of nontransformed cells. The rates of phosphorylative, nonphosphorylative, and uncoupled respiration in mitochondria isolated from the transformants were reduced relative to those of mitochondria derived from nontransformed cells, regardless of whether the cells were cultured in rich or minimal medium. The electrophoretic protein profiles of cell and mitochondrial extracts did not differ substantially between transformed and nontransformed cells. These results suggest that the reduced rate of mitochondrial respiration in the transformants may be due to impairment of metabolic function rather than to inhibition of the expression of components of the respiratory chain.
Collapse
Affiliation(s)
- L F Chien
- Institute of Molecular Biology, Academia Sinica, Taiwan, Republic of China
| | | |
Collapse
|
47
|
Shieh WJ, Jung SM, Hsueh C, Kuo TT, Mounts A, Parashar U, Yang CF, Guarner J, Ksiazek TG, Dawson J, Goldsmith C, Chang GJ, Oberste SM, Pallansch MA, Anderson LJ, Zaki SR. Pathologic studies of fatal cases in outbreak of hand, foot, and mouth disease, Taiwan. Emerg Infect Dis 2001; 7:146-8. [PMID: 11266307 PMCID: PMC2631691 DOI: 10.3201/eid0701.700146] [Citation(s) in RCA: 43] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022] Open
Abstract
In 1998, an outbreak of enterovirus 71-associated hand, foot, and mouth disease occurred in Taiwan. Pathologic studies of two fatal cases with similar clinical features revealed two different causative agents, emphasizing the need for postmortem examinations and modern pathologic techniques in an outbreak investigation.
Collapse
Affiliation(s)
- W J Shieh
- Centers for Disease Control and Prevention, 1600 Clifton Road, Mail Stop G32, Atlanta, GA 30333, USA.
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
48
|
Hsueh C, Jung SM, Shih SR, Kuo TT, Shieh WJ, Zaki S, Lin TY, Chang LY, Ning HC, Yen DC. Acute encephalomyelitis during an outbreak of enterovirus type 71 infection in Taiwan: report of an autopsy case with pathologic, immunofluorescence, and molecular studies. Mod Pathol 2000; 13:1200-5. [PMID: 11106077 DOI: 10.1038/modpathol.3880222] [Citation(s) in RCA: 86] [Impact Index Per Article: 3.6] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
We report a fatal case of enterovirus type 71 (EV 71) infection in an 8-year-old girl during a summer outbreak of hand, foot, and mouth disease in 1998 in Taiwan. The clinical course was rapidly progressive, with manifestations of hand, foot, and mouth disease, aseptic meningitis, encephalomyelitis, and pulmonary edema. The patient died 24 hours after admission. Postmortem study revealed extensive inflammation in the meninges and central nervous system and marked pulmonary edema with focal hemorrhage. Brain stem and spinal cord were most severely involved. The inflammatory infiltrates consisted largely of neutrophils involving primarily the gray matter with perivascular lymphocytic cuffing, and neuronophagia. The lungs and heart showed no evidence of inflammation. EV 71 was isolated from the fresh brain tissues and identified by immunofluorescence method with type-specific EV 71 monoclonal antibody. It was also confirmed by neutralization test and reverse-transcriptase polymerase chain reaction with sequence analysis. The present case was the first example in which EV 71 was demonstrated to be the causative agent of fatal encephalomyelitis during its epidemic in Taiwan.
Collapse
MESH Headings
- Antigens, Viral/analysis
- Base Sequence
- Child
- Coxsackievirus Infections/epidemiology
- Coxsackievirus Infections/pathology
- Coxsackievirus Infections/virology
- DNA Primers/chemistry
- DNA, Viral/analysis
- Disease Outbreaks
- Encephalitis, Viral/epidemiology
- Encephalitis, Viral/pathology
- Encephalitis, Viral/virology
- Enterovirus/genetics
- Enterovirus/immunology
- Enterovirus/isolation & purification
- Fatal Outcome
- Female
- Fluorescent Antibody Technique, Indirect
- Hand, Foot and Mouth Disease/epidemiology
- Hand, Foot and Mouth Disease/pathology
- Hand, Foot and Mouth Disease/virology
- Humans
- Microscopy, Fluorescence
- Molecular Sequence Data
- Reverse Transcriptase Polymerase Chain Reaction
Collapse
Affiliation(s)
- C Hsueh
- Department of Pathology, Chang Gung Memorial Hospital, Tao Yuan, Taiwan
| | | | | | | | | | | | | | | | | | | |
Collapse
|
49
|
Abstract
The protozoan Toxoplasma gondii is one of the most common infectious pathogenic parasites and can cause severe medical complications in infants and immunocompromised individuals. We report here the development of a real-time PCR-based assay for the detection of T. gondii. Oligonucleotide primers and a fluorescence-labeled TaqMan probe were designed to amplify the T. gondii B1 gene. After 40 PCR cycles, the cycle threshold values (C(T)) indicative of the quantity of the target gene were determined. Typically, a C(T) of 25.09 was obtained with DNA from 500 tachyzoites of the T. gondii RH strain. The intra-assay coefficients of variation (CV) were 0.4, 0.16, 0.24, and 0.79% for the four sets of quadruplicate assays, with a mean interassay CV of 0.4%. These values indicate the reproducibility of this assay. Upon optimization of assay conditions, we were able to obtain a standard curve with a linear range (correlation coefficient = 0.9988) across at least 6 logs of DNA concentration. Hence, we were able to quantitatively detect as little as 0.05 T. gondii tachyzoite in an assay. When tested with 30 paraffin-embedded fetal tissue sections, 10 sections (33%) showed a C(T) of <40 and were scored as positive for this test. These results were consistent with those obtained through our nested-PCR control experiments. We have developed a rapid, sensitive, and quantitative real-time PCR for detection of T. gondii. The advantages of this technique for the diagnosis of toxoplasmosis in a clinical laboratory are discussed.
Collapse
Affiliation(s)
- M H Lin
- School of Medical Technology, Chang Gung University, Tao-Yuan 333, Taiwan, Republic of China
| | | | | | | | | |
Collapse
|
50
|
Kuo MY, Yang MK, Chen WP, Kuo TT. High-frequency interconversion of turbid and clear plaque strains of bacteriophage f1 and associated host cell death. Can J Microbiol 2000; 46:841-7. [PMID: 11006845] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/17/2023]
Abstract
Under normal cultivation conditions, a mixture of turbid and clear plaques is often apparent in cultures of bacterial cells infected with filamentous bacteriophages. Beginning with a culture of wild-type filamentous phage f1, which itself produces turbid plaques, a clear plaque strain (c1) was isolated. From c1, the turbid plaque strain t1 was isolated; from t1, the clear plaque strain c2 was isolated; and from c2, the turbid plaque strain t2 was isolated. Each of these strains was generated with a frequency of approximately 1 x 10(-4). Although filamentous phages have been thought not to induce host cell death, both turbid and clear plaque strains of f1 killed host bacteria. Plating of bacterial cells 1 h after infection revealed that colonies produced by cells infected with either wild-type f1 or strain c2 were smaller than those derived from uninfected cells, and that colony formation by infected cells was reduced by 15% and 38%, respectively. The time course of bacterial growth revealed that, at 4 h after infection, the number of CFU per milliliter of culture of cells infected with wild-type f1 or with strain c2 was reduced by 27% and 95%, respectively, compared with that for uninfected cells. Microculture analysis also revealed that the percentages of nondividing cells in f1 or c2 infected were 19% and 52%, respectively, 4 h after infection with wild-type f1 or with strain c2; no such cells were detected in cultures of uninfected cells. Negative staining and electron microscopy showed that 20% and 61% of cells infected with wild-type f1 or with strain c2 were dead 4 h postinfection. Finally, although the rates of DNA synthesis were similar for infected and uninfected cells, the rates of RNA and protein synthesis were markedly reduced in infected cells.
Collapse
Affiliation(s)
- M Y Kuo
- Institute of Molecular Biology, Academia Sinica, Nankang, Taipei, Taiwan, Republic of China
| | | | | | | |
Collapse
|