Jen-Hsiang Chuang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Jen-Hsiang Chuang has a total of 365 co-authors. Here are the top co-authors by number of shared publications:
- Wan-Ting Huang
Global Health Program, College of Public Health, National Taiwan University, Taipei City, 10055, Taiwan.
16 shared publications Hsu-Sung Kuo
6 shared publicationsDa-Wei Wang
Institute of Information Science, Academia Sinica, Taipei
5 shared publications- I-Feng Lin
Institute of Public Health, School of Medicine, National Yang-Ming University, Taipei, Taiwan
5 shared publications Yu-Lun Liu
Centers for Disease Control, Ministry of Health and Welfare, Taipei, Taiwan
5 shared publications- Ding-Ping Liu
Institute of Epidemiology and Preventive Medicine, College of Public Health, National Taiwan University, Taipei, Taiwan
4 shared publications
Latest Publications
- Open Access
- 8 February 2023
- Published by Elsevier in Journal of Microbiology, Immunology and Infection
- Vol. 56 (3) , 558-565
Risk of myocarditis and pericarditis following coronavirus disease 2019 messenger RNA Vaccination—A nationwide study
- 8 February 2023
- Published by Elsevier in Journal of Microbiology, Immunology and Infection
- Vol. 56 (3) , 558-565
Open AccessRisk of myocarditis and pericarditis following coronavirus disease 2019 messenger RNA Vaccination—A nationwide study
- Open Access
- 27 December 2022
- Published by Taylor & Francis in Emerging Microbes & Infections
- Vol. 12 (1) , 2155584
Influenza vaccination is associated with a reduced risk of invasive aspergillosis in high-risk individuals in Taiwan: a population-based cohort study
Invasive aspergillosis (IA) has become the emerging life-threatening disease in recent years. Influenza has been identified as an independent risk factor for IA. Vaccination is the most effective way to prevent influenza, while whether it can reduce IA in high-risk population still uncertain. We aimed to investigate the association between influenza vaccination and the risk of IA in high-risk population. We performed a population-based cohort study of people who qualified for government-funded influenza vaccination and were at high risk for IA at the start of the influenza season each year between 2016 and 2019. We utilized Taiwan’s National Health Insurance Research Database to identify the influenza vaccination status and IA diagnosis during the follow-up period. We compared the risk of IA between people with and without vaccination using multivariable logistic regression analysis. Out of total 8,544,451 people who were eligible during the 3 influenza seasons, 3,136,477 (36.7%) were vaccinated. A total of 1179 IA cases with the incidence of 13.8 cases per 100,000 high-risk individuals were identified during the follow-up. Compared to non-vaccinated group, vaccinated individuals had a 21% risk reduction of IA (adjusted odds ratio 0.79, 95% confidence interval 0.70–0.90). Influenza vaccination was associated with a lower risk of IA among males, immunosuppressive conditions, malignancy, diabetes, and those having host factors according to the European Organization for Research and Treatment of Cancer and the Mycoses Study Group Education and Research Consortium. Influenza vaccination is recommended for high-risk population to reduce the risk of IA.
- 27 December 2022
- Published by Taylor & Francis in Emerging Microbes & Infections
- Vol. 12 (1) , 2155584
Open AccessInfluenza vaccination is associated with a reduced risk of invasive aspergillosis in high-risk individuals in Taiwan: a population-based cohort study
Invasive aspergillosis (IA) has become the emerging life-threatening disease in recent years. Influenza has been identified as an independent risk factor for IA. Vaccination is the most effective way to prevent influenza, while whether it can reduce IA in high-risk population still uncertain. We aimed to investigate the association between influenza vaccination and the risk of IA in high-risk population. We performed a population-based cohort study of people who qualified for government-funded influenza vaccination and were at high risk for IA at the start of the influenza season each year between 2016 and 2019. We utilized Taiwan’s National Health Insurance Research Database to identify the influenza vaccination status and IA diagnosis during the follow-up period. We compared the risk of IA between people with and without vaccination using multivariable logistic regression analysis. Out of total 8,544,451 people who were eligible during the 3 influenza seasons, 3,136,477 (36.7%) were vaccinated. A total of 1179 IA cases with the incidence of 13.8 cases per 100,000 high-risk individuals were identified during the follow-up. Compared to non-vaccinated group, vaccinated individuals had a 21% risk reduction of IA (adjusted odds ratio 0.79, 95% confidence interval 0.70–0.90). Influenza vaccination was associated with a lower risk of IA among males, immunosuppressive conditions, malignancy, diabetes, and those having host factors according to the European Organization for Research and Treatment of Cancer and the Mycoses Study Group Education and Research Consortium. Influenza vaccination is recommended for high-risk population to reduce the risk of IA.
- Open Access
- 5 August 2020
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 22 (8) , e15394
Applying Machine Learning Models with An Ensemble Approach for Accurate Real-Time Influenza Forecasting in Taiwan: Development and Validation Study
Background: Changeful seasonal influenza activity in subtropical areas such as Taiwan causes problems in epidemic preparedness. The Taiwan Centers for Disease Control has maintained real-time national influenza surveillance systems since 2004. Except for timely monitoring, epidemic forecasting using the national influenza surveillance data can provide pivotal information for public health response. Objective: We aimed to develop predictive models using machine learning to provide real-time influenza-like illness forecasts. Methods: Using surveillance data of influenza-like illness visits from emergency departments (from the Real-Time Outbreak and Disease Surveillance System), outpatient departments (from the National Health Insurance database), and the records of patients with severe influenza with complications (from the National Notifiable Disease Surveillance System), we developed 4 machine learning models (autoregressive integrated moving average, random forest, support vector regression, and extreme gradient boosting) to produce weekly influenza-like illness predictions for a given week and 3 subsequent weeks. We established a framework of the machine learning models and used an ensemble approach called stacking to integrate these predictions. We trained the models using historical data from 2008-2014. We evaluated their predictive ability during 2015-2017 for each of the 4-week time periods using Pearson correlation, mean absolute percentage error (MAPE), and hit rate of trend prediction. A dashboard website was built to visualize the forecasts, and the results of real-world implementation of this forecasting framework in 2018 were evaluated using the same metrics. Results: All models could accurately predict the timing and magnitudes of the seasonal peaks in the then-current week (nowcast) (ρ=0.802-0.965; MAPE: 5.2%-9.2%; hit rate: 0.577-0.756), 1-week (ρ=0.803-0.918; MAPE: 8.3%-11.8%; hit rate: 0.643-0.747), 2-week (ρ=0.783-0.867; MAPE: 10.1%-15.3%; hit rate: 0.669-0.734), and 3-week forecasts (ρ=0.676-0.801; MAPE: 12.0%-18.9%; hit rate: 0.643-0.786), especially the ensemble model. In real-world implementation in 2018, the forecasting performance was still accurate in nowcasts (ρ=0.875-0.969; MAPE: 5.3%-8.0%; hit rate: 0.582-0.782) and remained satisfactory in 3-week forecasts (ρ=0.721-0.908; MAPE: 7.6%-13.5%; hit rate: 0.596-0.904). Conclusions: This machine learning and ensemble approach can make accurate, real-time influenza-like illness forecasts for a 4-week period, and thus, facilitate decision making.
- 5 August 2020
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 22 (8) , e15394
Open AccessApplying Machine Learning Models with An Ensemble Approach for Accurate Real-Time Influenza Forecasting in Taiwan: Development and Validation Study
Background: Changeful seasonal influenza activity in subtropical areas such as Taiwan causes problems in epidemic preparedness. The Taiwan Centers for Disease Control has maintained real-time national influenza surveillance systems since 2004. Except for timely monitoring, epidemic forecasting using the national influenza surveillance data can provide pivotal information for public health response. Objective: We aimed to develop predictive models using machine learning to provide real-time influenza-like illness forecasts. Methods: Using surveillance data of influenza-like illness visits from emergency departments (from the Real-Time Outbreak and Disease Surveillance System), outpatient departments (from the National Health Insurance database), and the records of patients with severe influenza with complications (from the National Notifiable Disease Surveillance System), we developed 4 machine learning models (autoregressive integrated moving average, random forest, support vector regression, and extreme gradient boosting) to produce weekly influenza-like illness predictions for a given week and 3 subsequent weeks. We established a framework of the machine learning models and used an ensemble approach called stacking to integrate these predictions. We trained the models using historical data from 2008-2014. We evaluated their predictive ability during 2015-2017 for each of the 4-week time periods using Pearson correlation, mean absolute percentage error (MAPE), and hit rate of trend prediction. A dashboard website was built to visualize the forecasts, and the results of real-world implementation of this forecasting framework in 2018 were evaluated using the same metrics. Results: All models could accurately predict the timing and magnitudes of the seasonal peaks in the then-current week (nowcast) (ρ=0.802-0.965; MAPE: 5.2%-9.2%; hit rate: 0.577-0.756), 1-week (ρ=0.803-0.918; MAPE: 8.3%-11.8%; hit rate: 0.643-0.747), 2-week (ρ=0.783-0.867; MAPE: 10.1%-15.3%; hit rate: 0.669-0.734), and 3-week forecasts (ρ=0.676-0.801; MAPE: 12.0%-18.9%; hit rate: 0.643-0.786), especially the ensemble model. In real-world implementation in 2018, the forecasting performance was still accurate in nowcasts (ρ=0.875-0.969; MAPE: 5.3%-8.0%; hit rate: 0.582-0.782) and remained satisfactory in 3-week forecasts (ρ=0.721-0.908; MAPE: 7.6%-13.5%; hit rate: 0.596-0.904). Conclusions: This machine learning and ensemble approach can make accurate, real-time influenza-like illness forecasts for a 4-week period, and thus, facilitate decision making.
- Open Access
- 5 February 2020
- Published by American Medical Association (AMA) in JAMA Network Open
- Vol. 3 (2) , e200206
Assessment of Expert-Level Automated Detection of Plasmodium falciparum in Digitized Thin Blood Smear Images
Malaria, a mosquito-borne disease caused by Plasmodium species, is a severe and reemerging global health issue despite years of effort in global malaria control. In 2017, an estimated 219 million cases of malaria and 435 000 malaria-related deaths occurred worldwide.1 Most patients were in the World Health Organization African region (92%) and South-East Asian region (5%). Although Taiwan has been certified malaria free for more than 5 decades, imported cases, mostly from Africa and Southeast Asia and caused by Plasmodium falciparum, still occur every year.2
- 5 February 2020
- Published by American Medical Association (AMA) in JAMA Network Open
- Vol. 3 (2) , e200206
Open AccessAssessment of Expert-Level Automated Detection of Plasmodium falciparum in Digitized Thin Blood Smear Images
Malaria, a mosquito-borne disease caused by Plasmodium species, is a severe and reemerging global health issue despite years of effort in global malaria control. In 2017, an estimated 219 million cases of malaria and 435 000 malaria-related deaths occurred worldwide.1 Most patients were in the World Health Organization African region (92%) and South-East Asian region (5%). Although Taiwan has been certified malaria free for more than 5 decades, imported cases, mostly from Africa and Southeast Asia and caused by Plasmodium falciparum, still occur every year.2
- Open Access
- 8 July 2019
- Published by JMIR Publications Inc. in JMIR Preprints
Applying Machine Learning Models with An Ensemble Approach for Accurate Real-Time Influenza Forecasting in Taiwan: Development and Validation Study (Preprint)
BACKGROUND Changeful seasonal influenza activity in subtropical areas such as Taiwan causes problems in epidemic preparedness. The Taiwan Centers for Disease Control has maintained real-time national influenza surveillance systems since 2004. Except for timely monitoring, epidemic forecasting using the national influenza surveillance data can provide pivotal information for public health response. OBJECTIVE We aimed to develop predictive models using machine learning to provide real-time influenza-like illness forecasts. METHODS Using surveillance data of influenza-like illness visits from emergency departments (from the Real-Time Outbreak and Disease Surveillance System), outpatient departments (from the National Health Insurance database), and the records of patients with severe influenza with complications (from the National Notifiable Disease Surveillance System), we developed 4 machine learning models (autoregressive integrated moving average, random forest, support vector regression, and extreme gradient boosting) to produce weekly influenza-like illness predictions for a given week and 3 subsequent weeks. We established a framework of the machine learning models and used an ensemble approach called stacking to integrate these predictions. We trained the models using historical data from 2008-2014. We evaluated their predictive ability during 2015-2017 for each of the 4-week time periods using Pearson correlation, mean absolute percentage error (MAPE), and hit rate of trend prediction. A dashboard website was built to visualize the forecasts, and the results of real-world implementation of this forecasting framework in 2018 were evaluated using the same metrics. RESULTS All models could accurately predict the timing and magnitudes of the seasonal peaks in the then-current week (nowcast) (ρ=0.802-0.965; MAPE: 5.2%-9.2%; hit rate: 0.577-0.756), 1-week (ρ=0.803-0.918; MAPE: 8.3%-11.8%; hit rate: 0.643-0.747), 2-week (ρ=0.783-0.867; MAPE: 10.1%-15.3%; hit rate: 0.669-0.734), and 3-week forecasts (ρ=0.676-0.801; MAPE: 12.0%-18.9%; hit rate: 0.643-0.786), especially the ensemble model. In real-world implementation in 2018, the forecasting performance was still accurate in nowcasts (ρ=0.875-0.969; MAPE: 5.3%-8.0%; hit rate: 0.582-0.782) and remained satisfactory in 3-week forecasts (ρ=0.721-0.908; MAPE: 7.6%-13.5%; hit rate: 0.596-0.904). CONCLUSIONS This machine learning and ensemble approach can make accurate, real-time influenza-like illness forecasts for a 4-week period, and thus, facilitate decision making.
- 8 July 2019
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessApplying Machine Learning Models with An Ensemble Approach for Accurate Real-Time Influenza Forecasting in Taiwan: Development and Validation Study (Preprint)
BACKGROUND Changeful seasonal influenza activity in subtropical areas such as Taiwan causes problems in epidemic preparedness. The Taiwan Centers for Disease Control has maintained real-time national influenza surveillance systems since 2004. Except for timely monitoring, epidemic forecasting using the national influenza surveillance data can provide pivotal information for public health response. OBJECTIVE We aimed to develop predictive models using machine learning to provide real-time influenza-like illness forecasts. METHODS Using surveillance data of influenza-like illness visits from emergency departments (from the Real-Time Outbreak and Disease Surveillance System), outpatient departments (from the National Health Insurance database), and the records of patients with severe influenza with complications (from the National Notifiable Disease Surveillance System), we developed 4 machine learning models (autoregressive integrated moving average, random forest, support vector regression, and extreme gradient boosting) to produce weekly influenza-like illness predictions for a given week and 3 subsequent weeks. We established a framework of the machine learning models and used an ensemble approach called stacking to integrate these predictions. We trained the models using historical data from 2008-2014. We evaluated their predictive ability during 2015-2017 for each of the 4-week time periods using Pearson correlation, mean absolute percentage error (MAPE), and hit rate of trend prediction. A dashboard website was built to visualize the forecasts, and the results of real-world implementation of this forecasting framework in 2018 were evaluated using the same metrics. RESULTS All models could accurately predict the timing and magnitudes of the seasonal peaks in the then-current week (nowcast) (ρ=0.802-0.965; MAPE: 5.2%-9.2%; hit rate: 0.577-0.756), 1-week (ρ=0.803-0.918; MAPE: 8.3%-11.8%; hit rate: 0.643-0.747), 2-week (ρ=0.783-0.867; MAPE: 10.1%-15.3%; hit rate: 0.669-0.734), and 3-week forecasts (ρ=0.676-0.801; MAPE: 12.0%-18.9%; hit rate: 0.643-0.786), especially the ensemble model. In real-world implementation in 2018, the forecasting performance was still accurate in nowcasts (ρ=0.875-0.969; MAPE: 5.3%-8.0%; hit rate: 0.582-0.782) and remained satisfactory in 3-week forecasts (ρ=0.721-0.908; MAPE: 7.6%-13.5%; hit rate: 0.596-0.904). CONCLUSIONS This machine learning and ensemble approach can make accurate, real-time influenza-like illness forecasts for a 4-week period, and thus, facilitate decision making.
- Top Cited Papers
- 1 March 2018
- Published by Elsevier in The Lancet
- Vol. 391 (10127) , 1285-1300
Estimates of global seasonal influenza-associated respiratory mortality: a modelling study
- 1 March 2018
- Published by Elsevier in The Lancet
- Vol. 391 (10127) , 1285-1300
Top Cited PapersEstimates of global seasonal influenza-associated respiratory mortality: a modelling study
- Open Access
- 8 November 2017
- Published by PAGEPress Publications in Geospatial Health
- Vol. 12 (2) , 573
Balancing geo-privacy and spatial patterns in epidemiological studies
To balance the protection of geo-privacy and the accuracy of spatial patterns, we developed a geo-spatial tool (GeoMasker) intended to mask the residential locations of patients or cases in a geographic information system (GIS). To elucidate the effects of geo-masking parameters, we applied 2010 dengue epidemic data from Taiwan testing the tool’s performance in an empirical situation. The similarity of pre- and post-spatial patterns was measured by D statistics under a 95% confidence interval. In the empirical study, different magnitudes of anonymisation (estimated Kanonymity ≥10 and 100) were achieved and different degrees of agreement on the pre- and post-patterns were evaluated. The application is beneficial for public health workers and researchers when processing data with individuals’ spatial information.
- 8 November 2017
- Published by PAGEPress Publications in Geospatial Health
- Vol. 12 (2) , 573
Open AccessBalancing geo-privacy and spatial patterns in epidemiological studies
To balance the protection of geo-privacy and the accuracy of spatial patterns, we developed a geo-spatial tool (GeoMasker) intended to mask the residential locations of patients or cases in a geographic information system (GIS). To elucidate the effects of geo-masking parameters, we applied 2010 dengue epidemic data from Taiwan testing the tool’s performance in an empirical situation. The similarity of pre- and post-spatial patterns was measured by D statistics under a 95% confidence interval. In the empirical study, different magnitudes of anonymisation (estimated Kanonymity ≥10 and 100) were achieved and different degrees of agreement on the pre- and post-patterns were evaluated. The application is beneficial for public health workers and researchers when processing data with individuals’ spatial information.
- Open Access
- 1 January 2017
- Published by IOS Press
- Vol. 245, 808-812
Toward Automatic Reporting of Infectious Diseases
Accurate, complete, and timely disease surveillance data are vital for disease control. We report a national scale effort to automatically extract information from electronic medical records as well as electronic laboratory systems. The extracted information is then transferred to the centers of disease control after a proper confirmation process. The coverage rates of the automated reporting systems are over 50%. Not only is the workload of surveillance greatly reduced, but also reporting is completed in near real-time. From our experiences, a system sustainable strategy, well-defined working plan, and multifaceted team coordination work effectively. Knowledge management reduces the cost to maintain the system. Training courses with hands-on practice and reference documents are useful for LOINC adoption.
- 1 January 2017
- Published by IOS Press
- Vol. 245, 808-812
Open AccessToward Automatic Reporting of Infectious Diseases
Accurate, complete, and timely disease surveillance data are vital for disease control. We report a national scale effort to automatically extract information from electronic medical records as well as electronic laboratory systems. The extracted information is then transferred to the centers of disease control after a proper confirmation process. The coverage rates of the automated reporting systems are over 50%. Not only is the workload of surveillance greatly reduced, but also reporting is completed in near real-time. From our experiences, a system sustainable strategy, well-defined working plan, and multifaceted team coordination work effectively. Knowledge management reduces the cost to maintain the system. Training courses with hands-on practice and reference documents are useful for LOINC adoption.
- Open Access
- 6 October 2015
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 10 (10) , e0139687
National Trend and Characteristics of Acute Hepatitis C among HIV-Infected Individuals: A Matched Case-Control Study—Taiwan, 2001–2014
Hepatitis C virus (HCV) infection has been increasingly recognized among HIV-infected men who have sex with men (MSM) worldwide. We investigated the trend of and factors associated with acute hepatitis C (AHC) among HIV-infected individuals in Taiwan. The National Disease Surveillance System collects characteristics of AHC, HIV, syphilis, and gonorrhea cases through mandatory reports and patient interviews. Reported AHC patients in 2014 were interviewed additionally on sexual and parenteral exposures. Information on HCV genotypes were collected from the largest medical center serving HIV-infected Taiwanese. We defined an HIV/AHC case as a documented negative HCV antibody test result followed within 12 months by a positive test in a previously reported HIV-infected individual. Each case was matched to two HIV-infected, non-AHC controls for age, age of HIV diagnosis, sex, transmission route, HIV diagnosis date, and county/city. Conditional logistic regression was used to identify associated characteristics. During 2001–2014, 93 of 6,624 AHC reports were HIV/AHC cases; the annual case count increased from one in 2009 to 34 in 2014. All were males (81 [87%] MSM) aged 21–49 years with AHC diagnosed 2–5,923 days after HIV diagnoses. Sixty-eight (73%) lived in the Taipei metropolitan area. Detected HCV genotypes were 2a (n = 6), 1b (n = 5), 1b + 2a (n = 1) and 2b (n = 1). Among 28 HIV/AHC patients interviewed in 2014, 13 (46%) reported engaging in unprotected sex ≤3 months before AHC diagnosis. Seventy-nine HIV/AHC cases were matched to 158 controls. HIV/AHC was associated with recent syphilis (adjusted odds ratio [aOR], 10.9; 95% confidence interval [CI], 4.2–28.6) and last syphilis >6 months (aOR, 2.9; 95% CI, 1.2–6.9). HIV/AHC cases continued to increase particularly among sexually active HIV-infected MSM with a syphilis diagnosis in northern Taiwan. We recommend surveillance of associated behavioral and virologic characteristics and HCV counseling and testing for HIV-infected men in Taiwan.
- 6 October 2015
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 10 (10) , e0139687
Open AccessNational Trend and Characteristics of Acute Hepatitis C among HIV-Infected Individuals: A Matched Case-Control Study—Taiwan, 2001–2014
Hepatitis C virus (HCV) infection has been increasingly recognized among HIV-infected men who have sex with men (MSM) worldwide. We investigated the trend of and factors associated with acute hepatitis C (AHC) among HIV-infected individuals in Taiwan. The National Disease Surveillance System collects characteristics of AHC, HIV, syphilis, and gonorrhea cases through mandatory reports and patient interviews. Reported AHC patients in 2014 were interviewed additionally on sexual and parenteral exposures. Information on HCV genotypes were collected from the largest medical center serving HIV-infected Taiwanese. We defined an HIV/AHC case as a documented negative HCV antibody test result followed within 12 months by a positive test in a previously reported HIV-infected individual. Each case was matched to two HIV-infected, non-AHC controls for age, age of HIV diagnosis, sex, transmission route, HIV diagnosis date, and county/city. Conditional logistic regression was used to identify associated characteristics. During 2001–2014, 93 of 6,624 AHC reports were HIV/AHC cases; the annual case count increased from one in 2009 to 34 in 2014. All were males (81 [87%] MSM) aged 21–49 years with AHC diagnosed 2–5,923 days after HIV diagnoses. Sixty-eight (73%) lived in the Taipei metropolitan area. Detected HCV genotypes were 2a (n = 6), 1b (n = 5), 1b + 2a (n = 1) and 2b (n = 1). Among 28 HIV/AHC patients interviewed in 2014, 13 (46%) reported engaging in unprotected sex ≤3 months before AHC diagnosis. Seventy-nine HIV/AHC cases were matched to 158 controls. HIV/AHC was associated with recent syphilis (adjusted odds ratio [aOR], 10.9; 95% confidence interval [CI], 4.2–28.6) and last syphilis >6 months (aOR, 2.9; 95% CI, 1.2–6.9). HIV/AHC cases continued to increase particularly among sexually active HIV-infected MSM with a syphilis diagnosis in northern Taiwan. We recommend surveillance of associated behavioral and virologic characteristics and HCV counseling and testing for HIV-infected men in Taiwan.