Zhe Chen

Zhe Chen

Auto-generated profile, based on publicly available information

Zhe Chen

Evidence-Based Medicine Center, Tianjin University of Traditional Chinese Medicine, Tianjin, China

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
19 December 2023 in Integrative Medicine Research
Verified
Journal Article
Open access
ZCZhe Chen
Zhe Chen
DZDong Zhang
Dong Zhang
CLChunxiang Liu
Chunxiang Liu
HWHui Wang
Hui Wang
XJXinyao Jin
Xinyao Jin
JZJunhua Zhang
Junhua Zhang
With the development of traditional Chinese medicine (TCM) syndrome knowledge accumulation and artificial intelligence (AI), this study proposes a holistic TCM syndrome differentiation model for the classification prediction of multiple TCM syndromes based on deep learning and accelerates the construction of modern foundational TCM equipment. We searched publicly available TCM guidelines and textbooks for expert knowledge and validated these sources using ten-fold cross-validation. Based on the BERT and CNN models, with the classification constraints from TCM holistic syndrome differentiation, the TCM-BERT-CNN model was constructed, which completes the end-to-end TCM holistic syndrome text classification task through symptom input and syndrome output. We assessed the performance of the model using precision, recall, and F1 scores as evaluation metrics. The TCM-BERT-CNN model had a higher precision (0.926), recall (0.9238), and F1 score (0.9247) than the BERT, TextCNN, LSTM RNN, and LSTM ATTENTION models and achieved superior results in model performance and predictive classification of most TCM syndromes. Symptom feature visualization demonstrated that the TCM-BERT-CNN model can effectively identify the correlation and characteristics of symptoms in different syndromes with a strong correlation, which conforms to the diagnostic characteristics of TCM syndromes. The TCM-BERT-CNN model proposed in this study is in accordance with the TCM diagnostic characteristics of holistic syndrome differentiation and can effectively complete diagnostic prediction tasks for various TCM syndromes. The results of this study provide new insights into the development of deep learning models for holistic syndrome differentiation in TCM.

1 December 2012 in Fitoterapia
Verified
Journal Article
Closed access
YYYonglei Yuan
Yonglei Yuan
LJLong Ji
Long Ji
LLLiping Luo
Liping Luo
JLJuan Lu
Juan Lu
XMXiaoqiong Ma
Xiaoqiong Ma
ZCZhe Chen
Zhe Chen

8 September 2021 in Integrative Medicine Research
Verified
Journal Article
Open access
HHHaiyin Hu
Haiyin Hu
ZJZhaochen Ji
Zhaochen Ji
CFChaonan Feng
Chaonan Feng
WPWentai Pang
Wentai Pang
ZCZhe Chen
Zhe Chen
HWHui Wang
Hui Wang
Background: A large number of protocols for Systematic Reviews (SR) of Traditional Chinese Medicine (TCM) for coronavirus disease 2019 (COVID-19) have been registered in the International Prospective Register of Systematic Reviews (PROSPERO). This study aimed to analyze the innovativeness and rigorousness of the SR protocols and make recommendations for the design and implementation of future SRs on TCM for COVID-19. This effort is likely to enhance the value of the produced information and prevent the futility of the research. Methods: PROSPERO was searched comprehensively for identifying SRs of TCM for COVID-19 from the inception of the database to August 2020. Two researchers independently screened the literature, extracted the data, and cross-checked the retrieved information for consistency. The following details were recorded: database, registration time, organizations, types of research included, participants, interventions, and outcome measures. All extracted data were analyzed by an overview. The "P - participants, I - interventions, C - controls, and O - outcomes (PICO)" included in the protocols were compared for similarity. The outcomes of the included SR protocols were compared with the newly published Core Outcome Sets (COSs). Results: A total of 80 protocols of SR related to TCM for COVID-19 were obtained after a primary search, and finally 71 protocols were included. The majority of the protocols were from China. Thirty-two organizations participated in the protocol registrations, including 11 hospitals and 21 universities/colleges. However, some protocols were not innovative or rigorous enough, as the PICO of some protocols were similar and non-specific, and the searched literature was incomprehensive. In addition, COS is not commonly adopted. Conclusions: Registering a protocol of SR is an effective way to ensure the usefulness of the produced information, and to avoid the duplication of research and the wastage of resources. In future SR protocols, it is important to focus on and solve the methodological problems such as non-specific PICO, incomprehensive literature retrieval, and improper outcome measures. (C) 2021KoreaInstituteofOrientalMedicine. PublishedbyElsevierB.V.

1 January 2020 in Evidence-Based Complementary and Alternative Medicine
Verified
Journal Article
Open access
PDF file
ZCZhe Chen
Zhe Chen
QSQingyang Shi
Qingyang Shi
LTLizi Tan
Lizi Tan
YPYingying Peng
Yingying Peng
CLChunxiang Liu
Chunxiang Liu
JZJunhua Zhang
Junhua Zhang
Background. Traditional Chinese Patent Medicine (TCPM) is now being used more and more extensively for primary hypertension in China. However, the comparative efficacy and safety of it need more clarified evidence. Thus, we conducted a Bayesian network meta‐analysis to compare TCPMs with other interventions. Methods. We searched China National Knowledge Infrastructure (CNKI), WanFang Data, PubMed, Embase, and Cochrane Library from inception to April 2019 for randomized controlled trials (RCTs) with diagnosis of primary hypertension that compared the efficacy of TCPMs with antihypertension drugs (ADs). Two researchers screened literature, extracted data, and evaluated risk of bias independently. The primary outcomes were systolic blood pressure (SBP) and diastolic blood pressure (DBP). The secondary outcomes were adverse effects (AEs), total cholesterol (TC), and triglyceride (TG). We used the Bayesian network meta‐analysis to compare interventions and described the categorical variable and the continuous variable as odds ratio (OR) and mean difference (MD), respectively. Besides, we ranked all interventions via the Surface Under the Cumulative Ranking (SUCRA) values and conducted metaregression with nine covariates as additional analysis. Results. We included 192 studies with 23366 patients diagnosed as primary hypertension in total. For SBP reduction, eighteen interventions were significantly better than AD. Among them, Yinxingye (YXY) + AD (MD = −12, 95% CrI [−16, −8.5]) was superior to others in the rank plot with SUCRA 0.91. For DBP reduction, sixteen interventions were significantly better than AD. Among them, Qinggan Jiangya (QGJY) + AD (MD = −8.7, 95% CrI [−12, −5.5]) and Qiju Dihuang (QJDH) + AD (MD = −8.8, 95% CrI [−12, −5.2]) were superior to others in the rank plot with SUCRA 0.89. To summarize the SUCRA values, we found that QGJY + AD and YXY + AD had the most significant reductions for both SBP and DBP. YXY + AD was the best one for both TC (MD = −1.3, 95% CrI [−1.9, −0.64]) and TG (MD = −0.52, 95% CrI [−0.92, −0.11]) reductions. Considering adverse effects, we found two interventions had significant differences comparing with AD. Among them, YXY + AD was the best one with SUCRA of 0.01. Conclusion. In all TCPMs, QGJY + AD and YXY + AD may be the best options for hypertension. Meanwhile, YXY + AD can improve blood lipids in patients with hypertension. However, due to the vague reports of adverse effects and other limitations, more evidence, especially that provided by high‐quality studies, is needed to prove the advantages of TCMPs.