Yen-Pin Chen

Yen-Pin Chen

Auto-generated profile, based on publicly available information

Yen-Pin Chen

Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei City, Taiwan

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
27 January 2021 in Journal of Medical Internet Research
Verified
Journal Article
Open access
YCYen-Pin Chen
Yen-Pin Chen
YLYuan-Hsun Lo
Yuan-Hsun Lo
FLFeipei Lai
Feipei Lai
CHChien-Hua Huang
Chien-Hua Huang
Background: The electronic health record (EHR) contains a wealth of medical information. An organized EHR can greatly help doctors treat patients. In some cases, only limited patient information is collected to help doctors make treatment decisions. Because EHRs can serve as a reference for this limited information, doctors’ treatment capabilities can be enhanced. Natural language processing and deep learning methods can help organize and translate EHR information into medical knowledge and experience. Objective: In this study, we aimed to create a model to extract concept embeddings from EHRs for disease pattern retrieval and further classification tasks. Methods: We collected 1,040,989 emergency department visits from the National Taiwan University Hospital Integrated Medical Database and 305,897 samples from the National Hospital and Ambulatory Medical Care Survey Emergency Department data. After data cleansing and preprocessing, the data sets were divided into training, validation, and test sets. We proposed a Transformer-based model to embed EHRs and used Bidirectional Encoder Representations from Transformers (BERT) to extract features from free text and concatenate features with structural data as input to our proposed model. Then, Deep InfoMax (DIM) and Simple Contrastive Learning of Visual Representations (SimCLR) were used for the unsupervised embedding of the disease concept. The pretrained disease concept-embedding model, named EDisease, was further finetuned to adapt to the critical care outcome prediction task. We evaluated the performance of embedding using t-distributed stochastic neighbor embedding (t-SNE) to perform dimension reduction for visualization. The performance of the finetuned predictive model was evaluated against published models using the area under the receiver operating characteristic (AUROC). Results: The performance of our model on the outcome prediction had the highest AUROC of 0.876. In the ablation study, the use of a smaller data set or fewer unsupervised methods for pretraining deteriorated the prediction performance. The AUROCs were 0.857, 0.870, and 0.868 for the model without pretraining, the model pretrained by only SimCLR, and the model pretrained by only DIM, respectively. On the smaller finetuning set, the AUROC was 0.815 for the proposed model. Conclusions: Through contrastive learning methods, disease concepts can be embedded meaningfully. Moreover, these methods can be used for disease retrieval tasks to enhance clinical practice capabilities. The disease concept model is also suitable as a pretrained model for subsequent prediction tasks.

1 July 2019 in Resuscitation
Verified
Journal Article
Closed access
TLTsung-Chien Lu
Tsung-Chien Lu
YCYao-Ting Chang
Yao-Ting Chang
THTe-Wei Ho
Te-Wei Ho
YCYi Chen
Yi Chen
YLYi-Ting Lee
Yi-Ting Lee
ATAnne M. Turner
Anne M. Turner

29 April 2020 in JMIR Medical Informatics
Verified
Journal Article
Open access
YCYen-Pin Chen
Yen-Pin Chen
YCYi-Ying Chen
Yi-Ying Chen
JLJr-Jiun Lin
Jr-Jiun Lin
CHChien-Hua Huang
Chien-Hua Huang
FLFeipei Lai
Feipei Lai
Background: Doctors must care for many patients simultaneously, and it is time-consuming to find and examine all patients’ medical histories. Discharge diagnoses provide hospital staff with sufficient information to enable handling multiple patients; however, the excessive amount of words in the diagnostic sentences poses problems. Deep learning may be an effective solution to overcome this problem, but the use of such a heavy model may also add another obstacle to systems with limited computing resources.Objective: We aimed to build a diagnoses-extractive summarization model for hospital information systems and provide a service that can be operated even with limited computing resources.Methods: We used a Bidirectional Encoder Representations from Transformers (BERT)-based structure with a two-stage training method based on 258,050 discharge diagnoses obtained from the National Taiwan University Hospital Integrated Medical Database, and the highlighted extractive summaries written by experienced doctors were labeled. The model size was reduced using a character-level token, the number of parameters was decreased from 108,523,714 to 963,496, and the model was pretrained using random mask characters in the discharge diagnoses and International Statistical Classification of Diseases and Related Health Problems sets. We then fine-tuned the model using summary labels and cleaned up the prediction results by averaging all probabilities for entire words to prevent character level–induced fragment words. Model performance was evaluated against existing models BERT, BioBERT, and Long Short-Term Memory (LSTM) using the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) L score, and a questionnaire website was built to collect feedback from more doctors for each summary proposal.Results: The area under the receiver operating characteristic curve values of the summary proposals were 0.928, 0.941, 0.899, and 0.947 for BERT, BioBERT, LSTM, and the proposed model (AlphaBERT), respectively. The ROUGE-L scores were 0.697, 0.711, 0.648, and 0.693 for BERT, BioBERT, LSTM, and AlphaBERT, respectively. The mean (SD) critique scores from doctors were 2.232 (0.832), 2.134 (0.877), 2.207 (0.844), 1.927 (0.910), and 2.126 (0.874) for reference-by-doctor labels, BERT, BioBERT, LSTM, and AlphaBERT, respectively. Based on the paired t test, there was a statistically significant difference in LSTM compared to the reference (P<.001), BERT (P=.001), BioBERT (P<.001), and AlphaBERT (P=.002), but not in the other models.Conclusions: Use of character-level tokens in a BERT model can greatly decrease the model size without significantly reducing performance for diagnoses summarization. A well-developed deep-learning model will enhance doctors’ abilities to manage patients and promote medical studies by providing the capability to use extensive unstructured free-text notes.

26 April 2022 in Journal of Medical Internet Research
Verified
Journal Article
Open access
YCYen-Pin Chen
Yen-Pin Chen
YCYi-Ying Chen
Yi-Ying Chen
KYKai-Chou Yang
Kai-Chou Yang
FLFeipei Lai
Feipei Lai
CHChien-Hua Huang
Chien-Hua Huang
YTYi-Chin Tu
Yi-Chin Tu
Background: Vaccination is an important intervention to prevent the incidence and spread of serious diseases. Many factors including information obtained from the internet influence individuals’ decisions to vaccinate. Misinformation is a critical issue and can be hard to detect, although it can change people's minds, opinions, and decisions. The impact of misinformation on public health and vaccination hesitancy is well documented, but little research has been conducted on the relationship between the size of the population reached by misinformation and the vaccination decisions made by that population. A number of fact-checking services are available on the web, including the Islander news analysis system, a free web service that provides individuals with real-time judgment on web news. In this study, we used such services to estimate the amount of fake news available and used Google Trends levels to model the spread of fake news. We quantified this relationship using official public data on COVID-19 vaccination in Taiwan. Objective: In this study, we aimed to quantify the impact of the magnitude of the propagation of fake news on vaccination decisions. Methods: We collected public data about COVID-19 infections and vaccination from Taiwan's official website and estimated the popularity of searches using Google Trends. We indirectly collected news from 26 digital media sources, using the news database of the Islander system. This system crawls the internet in real time, analyzes the news, and stores it. The incitement and suspicion scores of the Islander system were used to objectively judge news, and a fake news percentage variable was produced. We used multivariable linear regression, chi-square tests, and the Johnson-Neyman procedure to analyze this relationship, using weekly data. Results: A total of 791,183 news items were obtained over 43 weeks in 2021. There was a significant increase in the proportion of fake news in 11 of the 26 media sources during the public vaccination stage. The regression model revealed a positive adjusted coefficient (β=0.98, P=.002) of vaccine availability on the following week's vaccination doses, and a negative adjusted coefficient (β=–3.21, P=.04) of the interaction term on the fake news percentage with the Google Trends level. The Johnson-Neiman plot of the adjusted effect for the interaction term showed that the Google Trends level had a significant negative adjustment effect on vaccination doses for the following week when the proportion of fake news exceeded 39.3%. Conclusions: There was a significant relationship between the amount of fake news to which the population was exposed and the number of vaccination doses administered. Reducing the amount of fake news and increasing public immunity to misinformation will be critical to maintain public health in the internet age.

1 November 2018 in Journal of Biomedical Informatics
Verified
Journal Article
Closed access
TLTsung-Chien Lu
Tsung-Chien Lu
YCYi Chen
Yi Chen
THTe-Wei Ho
Te-Wei Ho
YCYao-Ting Chang
Yao-Ting Chang
YLYi-Ting Lee
Yi-Ting Lee
ATAnne M. Turner
Anne M. Turner

5 April 2023 in Journal of Medical Internet Research
Verified
Journal Article
Open access
KCKah Meng Chong
Kah Meng Chong
HYHsiang-Wen Yang
Hsiang-Wen Yang
HHHsien-Chin He
Hsien-Chin He
WLWan-Ching Lien
Wan-Ching Lien
MYMei-Fen Yang
Mei-Fen Yang
PKPatrick Chow-In Ko
Patrick Chow-In Ko
Background: Basic life support (BLS) education is essential for improving bystander cardiopulmonary resuscitation (CPR) rates, but the imparting of such education faces obstacles during the outbreak of emerging infectious diseases, such as COVID-19. When face-to-face teaching is limited, distance learning—blended learning (BL) or an online-only model—is encouraged. However, evidence regarding the effect of online-only CPR training is scarce, and comparative studies on classroom-based BL (CBL) are lacking. While other strategies have recommended self-directed learning and deliberate practice to enhance CPR education, no previous studies have incorporated all of these instructional methods into a BLS course. Objective: This study aimed to demonstrate a novel BLS training model—remote practice BL (RBL)—and compare its educational outcomes with those of the conventional CBL model. Methods: A static-group comparison study was conducted. It included RBL and CBL courses that shared the same paradigm, comprising online lectures, a deliberate practice session with Little Anne quality CPR (QCPR) manikin feedback, and a final assessment session. In the main intervention, the RBL group was required to perform distant self-directed deliberate practice and complete the final assessment via an online video conference. Manikin-rated CPR scores were measured as the primary outcome; the number of retakes of the final examination was the secondary outcome. Results: A total of 52 and 104 participants from the RBL and CBL groups, respectively, were eligible for data analysis. A comparison of the 2 groups revealed that there were more women in the RBL group than the CBL group (36/52, 69.2% vs 51/104, 49%, respectively; P=.02). After adjustment, there were no significant differences in scores for QCPR release (96.9 vs 96.4, respectively; P=.61), QCPR depth (99.2 vs 99.5, respectively; P=.27), or QCPR rate (94.9 vs 95.5, respectively; P=.83). The RBL group spent more days practicing before the final assessment (12.4 vs 8.9 days, respectively; P<.001) and also had a higher number of retakes (1.4 vs 1.1 times, respectively; P<.001). Conclusions: We developed a remote practice BL–based method for online-only distant BLS CPR training. In terms of CPR performance, using remote self-directed deliberate practice was not inferior to the conventional classroom-based instructor-led method, although it tended to take more time to achieve the same effect. Trial Registration: Not applicable.