Jiahui Zhong

Jiahui Zhong

Auto-generated profile, based on publicly available information

Jiahui Zhong

Graduate School of Guangzhou University of Traditional Chinese Medicine, Guangzhou City, Guangdong Province, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
19 July 2023 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
MZMengjian Zhang
Mengjian Zhang
GWGuihua Wen
Guihua Wen
JZJiahui Zhong
Jiahui Zhong
DCDongliang Chen
Dongliang Chen
CWChangjun Wang
Changjun Wang
SZShijun Zhang
Shijun Zhang
Medical images such as facial and tongue images have been widely used for intelligence-assisted diagnosis, which can be regarded as the multi-label classification task for disease location (DL) and disease nature (DN) of biomedical images. Compared with complicated convolutional neural networks and Transformers for this task, recent MLP-like architectures are not only simple and less computationally expensive, but also have stronger generalization capabilities. However, MLP-like models require better input features from the image. Thus, this study proposes a novel convolution complex transformation MLP-like (CCT-MLP) model for the multi-label DL and DN recognition task for facial and tongue images. Notably, the convolutional Tokenizer and multiple convolutional layers are first used to extract the better shallow features from input biomedical images to make up for the loss of spatial information obtained by the simple MLP structure. Subsequently, the Channel-MLP architecture with complex transformations is used to extract deep-level contextual features. In this way, multi-channel features are extracted and mixed to perform the multi-label classification of the input biomedical images. Experimental results on our constructed multi-label facial and tongue image datasets demonstrate that our method outperforms existing methods in terms of both accuracy (Acc) and mean average precision (mAP).

7 November 2022 in Journal of Healthcare Engineering
Verified
Journal Article
Open access
PDF file
MLMinghuan Li
Minghuan Li
GWGuihua Wen
Guihua Wen
JZJiahui Zhong
Jiahui Zhong
PYPei Yang
Pei Yang
Traditional Chinese Medicine (TCM) is one of the oldest medical systems in the world, and inquiry is an essential part of TCM diagnosis. The development of artificial intelligence has led to the proposal of several computational TCM diagnostic methods. However, there are few research studies among them, and they have the following flaws: (1) insufficient engagement with the patient, (2) barren TCM consultation philosophy, and (3) inadequate validation of the method. As TCM inquiry knowledge is abstract and there are few relevant datasets, we devise a novel knowledge representation technique. The mapping of symptoms and syndromes is constructed based on the diagnostics of traditional Chinese medicine. As a guide, the inquiry knowledge base is constructed utilizing the “Ten Brief Inquiries,” TCM’s domain knowledge. Subsequently, a corresponding assessment approach is proposed for an intelligent consultation model for syndrome differentiation. We establish three criteria: the quality of the generated question-answer pairs, the accuracy of model identification, and the average number of questions. Three TCM specialists are asked to undertake a manual evaluation of the model separately. The results reveal that our approach is capable of pretty accurate syndrome differentiation. Furthermore, the model’s question and answer pairs for simulated consultations are relevant, accurate, and efficient.

15 December 2023 in Medicine
Verified
Journal Article
Open access
XHXiwei Huang
Xiwei Huang
SPShuwen Pang
Shuwen Pang
YZYueli Zhao
Yueli Zhao
JQJing Qian
Jing Qian
JZJiahui Zhong
Jiahui Zhong
SLShuai Liu
Shuai Liu
Background: Non-pharmacological treatments, particularly TCM health exercises, have garnered attention for their affordability, ease of access, and potential health advantages. Despite this interest, systematic and direct comparative studies assessing the effectiveness and safety of these therapies in patients with CHD-CHF remain scarce. Methods: This study aimed to compare the efficacy and safety of conventional treatment, conventional treatment integrated with aerobic endurance training, and various TCM health exercises in treating patients with CHD-CHF using NMA. The analysis was designed to provide a reference for developing treatment plans. To achieve this, literature databases were searched for RCTs on different TCM health exercises for CHD-CHF patients up to December 6, 2022. Major outcomes analyzed included NT-proBNP, LVEF, 6-minute walk test, MLHFQ, clinical effectiveness, and adverse event occurrence. The Cochrane risk of bias tool was employed to assess the risk of bias in the included RCT studies. Systematic review with NMA was conducted using RevMan 5.4 and Stata for cumulative ranking, and comparative adjustment funnel plot analysis. Results: Traditional Chinese medicine gong methods included BaDuanJin (A) and TaiChiQuan (B). The NMA and SUCRA results revealed that: A + D and A + C + D were most likely to be the best interventions to improve NT-proBNP; B + D and A + C + D were most likely to be the best interventions to improve LVEF; A + D and A + C + D were the best interventions to improve 6WMT in CHD-CHF patients; B + C + D had the best effect on shrinking LVESD;A + D and B + C + D was likely the best interventions for contracting LVEDD;B + D and A + D were consistent in their capacity to improve MLHFQ in patients with CHD-CHF, but B + D had better efficacy. Unlike A + C + D, B + C + D was the best intervention to improve MLHFQ. In contrast with interventions, including Dand C + D, B + D was the most clinically effective intervention. Unlike interventions including B + C + D, C + D, and D, A + C + D was the most clinically efficient intervention. Conclusion: The findings of this NMA showed that traditional Chinese health exercises integrated with conventional treatment are more effective than conventional treatment (D) alone in patients with CHD-CHF, with A + D, B + D, B + C + D, and A + C + D considered potentially optimal treatment interventions.