Taoran Liu

Dr. Taoran Liu

Infectious Diseases and Public Health, City University of Hong Kong, Hong Kong, China
orcid

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

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

Representative Publications

View All Publications
14 June 2021 in Vaccines
Verified
Journal Article
Open access
PDF file
TLTaoran Liu
Taoran Liu
ZHZonglin He
Zonglin He
JHJian Huang
Jian Huang
NYNi Yan
Ni Yan
QCQian Chen
Qian Chen
WMWai-Kit Ming
Wai-Kit Ming
Objectives: To investigate the differences in vaccine hesitancy and preference of the currently available COVID-19 vaccines between two countries, namely, China and the United States (U.S.). Method: A cross-national survey was conducted in both China and the United States, and discrete choice experiments, as well as Likert scales, were utilized to assess vaccine preference and the underlying factors contributing to vaccination acceptance. Propensity score matching (PSM) was performed to enable a direct comparison between the two countries. Results: A total of 9077 (5375 and 3702 from China and the United States, respectively) respondents completed the survey. After propensity score matching, over 82.0% of respondents from China positively accepted the COVID-19 vaccination, while 72.2% of respondents from the United States positively accepted it. Specifically, only 31.9% of Chinese respondents were recommended by a doctor to have COVID-19 vaccination, while more than half of the U.S. respondents were recommended by a doctor (50.2%), local health board (59.4%), or friends and families (64.8%). The discrete choice experiments revealed that respondents from the United States attached the greatest importance to the efficacy of COVID-19 vaccines (44.41%), followed by the cost of vaccination (29.57%), whereas those from China held a different viewpoint, that the cost of vaccination covered the largest proportion in their trade-off (30.66%), and efficacy ranked as the second most important attribute (26.34%). Additionally, respondents from China tended to be much more concerned about the adverse effect of vaccination (19.68% vs. 6.12%) and have a lower perceived severity of being infected with COVID-19. Conclusion: Although the overall acceptance and hesitancy of COVID-19 vaccination in both countries are high, underpinned distinctions between these countries were observed. Owing to the differences in COVID-19 incidence rates, cultural backgrounds, and the availability of specific COVID-19 vaccines in the two countries, vaccine rollout strategies should be nation-dependent.

15 September 2020 in Journal of Medical Internet Research
Verified
Journal Article
Open access
JSJiayi Shen
Jiayi Shen
JCJiebin Chen
Jiebin Chen
ZZZequan Zheng
Zequan Zheng
JZJiabin Zheng
Jiabin Zheng
ZLZherui Liu
Zherui Liu
WMWai-Kit Ming
Wai-Kit Ming
Background: Gestational diabetes mellitus (GDM) can cause adverse consequences to both mothers and their newborns. However, pregnant women living in low- and middle-income areas or countries often fail to receive early clinical interventions at local medical facilities due to restricted availability of GDM diagnosis. The outstanding performance of artificial intelligence (AI) in disease diagnosis in previous studies demonstrates its promising applications in GDM diagnosis. Objective: This study aims to investigate the implementation of a well-performing AI algorithm in GDM diagnosis in a setting, which requires fewer medical equipment and staff and to establish an app based on the AI algorithm. This study also explores possible progress if our app is widely used. Methods: An AI model that included 9 algorithms was trained on 12,304 pregnant outpatients with their consent who received a test for GDM in the obstetrics and gynecology department of the First Affiliated Hospital of Jinan University, a local hospital in South China, between November 2010 and October 2017. GDM was diagnosed according to American Diabetes Association (ADA) 2011 diagnostic criteria. Age and fasting blood glucose were chosen as critical parameters. For validation, we performed k-fold cross-validation (k=5) for the internal dataset and an external validation dataset that included 1655 cases from the Prince of Wales Hospital, the affiliated teaching hospital of the Chinese University of Hong Kong, a non-local hospital. Accuracy, sensitivity, and other criteria were calculated for each algorithm. Results: The areas under the receiver operating characteristic curve (AUROC) of external validation dataset for support vector machine (SVM), random forest, AdaBoost, k-nearest neighbors (kNN), naive Bayes (NB), decision tree, logistic regression (LR), eXtreme gradient boosting (XGBoost), and gradient boosting decision tree (GBDT) were 0.780, 0.657, 0.736, 0.669, 0.774, 0.614, 0.769, 0.742, and 0.757, respectively. SVM also retained high performance in other criteria. The specificity for SVM retained 100% in the external validation set with an accuracy of 88.7%. Conclusions: Our prospective and multicenter study is the first clinical study that supports the GDM diagnosis for pregnant women in resource-limited areas, using only fasting blood glucose value, patients’ age, and a smartphone connected to the internet. Our study proved that SVM can achieve accurate diagnosis with less operation cost and higher efficacy. Our study (referred to as GDM-AI study, ie, the study of AI-based diagnosis of GDM) also shows our app has a promising future in improving the quality of maternal health for pregnant women, precision medicine, and long-distance medical care. We recommend future work should expand the dataset scope and replicate the process to validate the performance of the AI algorithms.

2 March 2021 in Journal of Medical Internet Research
Verified
Journal Article
Open access
TLTaoran Liu
Taoran Liu
WTWinghei Tsang
Winghei Tsang
YXYifei Xie
Yifei Xie
KTKang Tian
Kang Tian
FHFengqiu Huang
Fengqiu Huang
WMWai-Kit Ming
Wai-Kit Ming
Background: Artificial intelligence (AI) methods can potentially be used to relieve the pressure that the COVID-19 pandemic has exerted on public health. In cases of medical resource shortages caused by the pandemic, changes in people’s preferences for AI clinicians and traditional clinicians are worth exploring. Objective: We aimed to quantify and compare people’s preferences for AI clinicians and traditional clinicians before and during the COVID-19 pandemic, and to assess whether people’s preferences were affected by the pressure of pandemic. Methods: We used the propensity score matching method to match two different groups of respondents with similar demographic characteristics. Respondents were recruited in 2017 and 2020. A total of 2048 respondents (2017: n=1520; 2020: n=528) completed the questionnaire and were included in the analysis. Multinomial logit models and latent class models were used to assess people’s preferences for different diagnosis methods. Results: In total, 84.7% (1115/1317) of respondents in the 2017 group and 91.3% (482/528) of respondents in the 2020 group were confident that AI diagnosis methods would outperform human clinician diagnosis methods in the future. Both groups of matched respondents believed that the most important attribute of diagnosis was accuracy, and they preferred to receive combined diagnoses from both AI and human clinicians (2017: odds ratio [OR] 1.645, 95% CI 1.535-1.763; P<.001; 2020: OR 1.513, 95% CI 1.413-1.621; P<.001; reference: clinician diagnoses). The latent class model identified three classes with different attribute priorities. In class 1, preferences for combined diagnoses and accuracy remained constant in 2017 and 2020, and high accuracy (eg, 100% accuracy in 2017: OR 1.357, 95% CI 1.164-1.581) was preferred. In class 2, the matched data from 2017 were similar to those from 2020; combined diagnoses from both AI and human clinicians (2017: OR 1.204, 95% CI 1.039-1.394; P=.011; 2020: OR 2.009, 95% CI 1.826-2.211; P<.001; reference: clinician diagnoses) and an outpatient waiting time of 20 minutes (2017: OR 1.349, 95% CI 1.065-1.708; P<.001; 2020: OR 1.488, 95% CI 1.287-1.721; P<.001; reference: 0 minutes) were consistently preferred. In class 3, the respondents in the 2017 and 2020 groups preferred different diagnosis methods; respondents in the 2017 group preferred clinician diagnoses, whereas respondents in the 2020 group preferred AI diagnoses. In the latent class, which was stratified according to sex, all male and female respondents in the 2017 and 2020 groups believed that accuracy was the most important attribute of diagnosis. Conclusions: Individuals’ preferences for receiving clinical diagnoses from AI and human clinicians were generally unaffected by the pandemic. Respondents believed that accuracy and expense were the most important attributes of diagnosis. These findings can be used to guide policies that are relevant to the development of AI-based health care.

23 February 2021 in Journal of Medical Internet Research
Verified
Journal Article
Open access
TLTaoran Liu
Taoran Liu
WTWinghei Tsang
Winghei Tsang
FHFengqiu Huang
Fengqiu Huang
OLOi Ying Lau
Oi Ying Lau
YCYanhui Chen
Yanhui Chen
WMWai-Kit Ming
Wai-Kit Ming
Background: Misdiagnosis, arbitrary charges, annoying queues, and clinic waiting times among others are long-standing phenomena in the medical industry across the world. These factors can contribute to patient anxiety about misdiagnosis by clinicians. However, with the increasing growth in use of big data in biomedical and health care communities, the performance of artificial intelligence (Al) techniques of diagnosis is improving and can help avoid medical practice errors, including under the current circumstance of COVID-19. Objective: This study aims to visualize and measure patients’ heterogeneous preferences from various angles of AI diagnosis versus clinicians in the context of the COVID-19 epidemic in China. We also aim to illustrate the different decision-making factors of the latent class of a discrete choice experiment (DCE) and prospects for the application of AI techniques in judgment and management during the pandemic of SARS-CoV-2 and in the future. Methods: A DCE approach was the main analysis method applied in this paper. Attributes from different dimensions were hypothesized: diagnostic method, outpatient waiting time, diagnosis time, accuracy, follow-up after diagnosis, and diagnostic expense. After that, a questionnaire is formed. With collected data from the DCE questionnaire, we apply Sawtooth software to construct a generalized multinomial logit (GMNL) model, mixed logit model, and latent class model with the data sets. Moreover, we calculate the variables’ coefficients, standard error, P value, and odds ratio (OR) and form a utility report to present the importance and weighted percentage of attributes. Results: A total of 55.8% of the respondents (428 out of 767) opted for AI diagnosis regardless of the description of the clinicians. In the GMNL model, we found that people prefer the 100% accuracy level the most (OR 4.548, 95% CI 4.048-5.110, P<.001). For the latent class model, the most acceptable model consists of 3 latent classes of respondents. The attributes with the most substantial effects and highest percentage weights are the accuracy (39.29% in general) and expense of diagnosis (21.69% in general), especially the preferences for the diagnosis “accuracy” attribute, which is constant across classes. For class 1 and class 3, people prefer the AI + clinicians method (class 1: OR 1.247, 95% CI 1.036-1.463, P<.001; class 3: OR 1.958, 95% CI 1.769-2.167, P<.001). For class 2, people prefer the AI method (OR 1.546, 95% CI 0.883-2.707, P=.37). The OR of levels of attributes increases with the increase of accuracy across all classes. Conclusions: Latent class analysis was prominent and useful in quantifying preferences for attributes of diagnosis choice. People’s preferences for the “accuracy” and “diagnostic expenses” attributes are palpable. AI will have a potential market. However, accuracy and diagnosis expenses need to be taken into consideration.

21 December 2021 in JMIR Public Health and Surveillance
Verified
Journal Article
Open access
WMWai-Kit Ming
Wai-Kit Ming
FHFengqiu Huang
Fengqiu Huang
QCQiuyi Chen
Qiuyi Chen
BLBeiting Liang
Beiting Liang
AJAoao Jiao
Aoao Jiao
QLQian Liu
Qian Liu
Background: Due to the COVID-19 pandemic, health information related to COVID-19 has spread across news media worldwide. Google is among the most used internet search engines, and the Google Trends tool can reflect how the public seeks COVID-19–related health information during the pandemic. Objective: The aim of this study was to understand health communication through Google Trends and news coverage and to explore their relationship with prevention and control of COVID-19 at the early epidemic stage. Methods: To achieve the study objectives, we analyzed the public’s information-seeking behaviors on Google and news media coverage on COVID-19. We collected data on COVID-19 news coverage and Google search queries from eight countries (ie, the United States, the United Kingdom, Canada, Singapore, Ireland, Australia, South Africa, and New Zealand) between January 1 and April 29, 2020. We depicted the characteristics of the COVID-19 news coverage trends over time, as well as the search query trends for the topics of COVID-19–related “diseases,” “treatments and medical resources,” “symptoms and signs,” and “public measures.” The search query trends provided the relative search volume (RSV) as an indicator to represent the popularity of a specific search term in a specific geographic area over time. Also, time-lag correlation analysis was used to further explore the relationship between search terms trends and the number of new daily cases, as well as the relationship between search terms trends and news coverage. Results: Across all search trends in eight countries, almost all search peaks appeared between March and April 2020, and declined in April 2020. Regarding COVID-19–related “diseases,” in most countries, the RSV of the term “coronavirus” increased earlier than that of “covid-19”; however, around April 2020, the search volume of the term “covid-19” surpassed that of “coronavirus.” Regarding the topic “treatments and medical resources,” the most and least searched terms were “mask” and “ventilator,” respectively. Regarding the topic “symptoms and signs,” “fever” and “cough” were the most searched terms. The RSV for the term “lockdown” was significantly higher than that for “social distancing” under the topic “public health measures.” In addition, when combining search trends with news coverage, there were three main patterns: (1) the pattern for Singapore, (2) the pattern for the United States, and (3) the pattern for the other countries. In the time-lag correlation analysis between the RSV for the topic “treatments and medical resources” and the number of new daily cases, the RSV for all countries except Singapore was positively correlated with new daily cases, with a maximum correlation of 0.8 for the United States. In addition, in the time-lag correlation analysis between the overall RSV for the topic “diseases” and the number of daily news items, the overall RSV was positively correlated with the number of daily news items, the maximum correlation coefficient was more than 0.8, and the search behavior occurred 0 to 17 days earlier than the news coverage. Conclusions: Our findings revealed public interest in masks, disease control, and public measures, and revealed the potential value of Google Trends in the face of the emergence of new infectious diseases. Also, Google Trends combined with news media can achieve more efficient health communication. Therefore, both news media and Google Trends can contribute to the early prevention and control of epidemics.

2 May 2021 in medRxiv
Verified
Preprint
Open access
PDF file
TLTaoran Liu
Taoran Liu
ZHZonglin He
Zonglin He
JHJian Huang
Jian Huang
NYNi Yan
Ni Yan
QCQian Chen
Qian Chen
WMWai-Kit Ming
Wai-Kit Ming
Objectives To investigate the differences in vaccine hesitancy and preference of the currently available COVID-19 vaccines between two countries, viz. China and the United States (US). Method A cross-national survey was conducted in both China and the US, and discrete choice experiments as well as Likert scales were utilized to assess vaccine preference and the underlying factors contributing to the vaccination acceptance. A propensity score matching (PSM) was performed to enable a direct comparison between the two countries. Results A total of 9,077 (5,375 and 3,702, respectively, from China and the US) respondents have completed the survey. After propensity score matching, over 82.0% respondents from China positively accept the COVID-19 vaccination, while 72.2% respondents form the US positively accept it. Specifically, only 31.9% of Chinese respondents were recommended by a doctor to have COVID-19 vaccination, while more than half of the US respondents were recommended by a doctor (50.2%), local health board (59.4%), or friends and families (64.8%). The discrete choice experiments revealed that respondents from the US attached the greatest importance to the efficacy of COVID-19 vaccines (44.41%), followed by the cost of vaccination (29.57%), whereas those from China held a different viewpoint that the cost of vaccination covers the largest proportion in their trade-off (30.66%), and efficacy ranked as the second most important attribute (26.34%). Also, respondents from China tend to concerned much more about the adverse effect of vaccination (19.68% vs 6.12%) and have lower perceived severity of being infected with COVID-19. Conclusion While the overall acceptance and hesitancy of COVID-19 vaccination in both countries are high, underpinned distinctions between countries are observed. Owing to the differences in COVID-19 incidence rates, cultural backgrounds, and the availability of specific COVID-19 vaccines in two countries, the vaccine rollout strategies should be nation-dependent.