Haojie Du

Mr. Haojie Du

orcid

Research Focus & Metrics

Representative Publications

View All Publications
3 October 2025 in JMIR Formative Research
Verified
Journal Article
Open access
HBHe Ba
He Ba
HDHaojie Du
Haojie Du
CCChien-shan Cheng
Chien-shan Cheng
YZYuan Zhang
Yuan Zhang
LRLinjie Ruan
Linjie Ruan
ZCZhen Chen
Zhen Chen
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Syndrome differentiation is crucial in traditional Chinese medicine (TCM) diagnosis and treatment, but it heavily relies on expert experience, limiting systematic standardization. Objective: This study developed and validated a BERT (bidirectional encoder representations from transformers)–based model, the traditional Chinese medicine pancreatic cancer syndrome differentiation bidirectional encoder representations from transformers (TCMPCSD-BERT), using in-house pancreatic cancer medical records, to digitalize expert knowledge and support standardized syndrome differentiation in TCM. Methods: A retrospective dataset of pancreatic cancer cases (2011-2024) from Fudan University Shanghai Cancer Center was annotated into 4 TCM syndrome types by 2 experts (Cohen κ=0.913). The proposed TCMPCSD-BERT model was compared with conventional models (long short-term memory and text convolutional neural network) embedded in TCM diagnostic tools and with large language models (LLMs; ChatGPT-4o, Kimi, Ernie Bot 4.0 Turbo, and Zhipu Qingyan) under a prompt engineering framework. Performance evaluation on in-house data was supplemented with attention visualizations and integrated gradients analyses for interpretability. The McNemar test assessed classification accuracy differences, while bootstrap 95% CIs quantified statistical uncertainty and stability. The Welch t test (2-tailed) was used to evaluate mean differences between TCMPCSD-BERT and the comparator models. Results: Among 6830 records, case counts were damp-heat syndrome (n=1694), spleen-deficiency syndrome (n=1185), damp-heat with spleen-deficiency syndrome (n=1178), and others (n=2773). On the test set, McNemar test showed significantly higher accuracy for TCMPCSD-BERT than the 3 baseline models and generally better performance than LLMs. In all comparisons, TCMPCSD-BERT achieved higher mean macroprecision, macrorecall, macro–F1-score, and accuracy, with nonoverlapping 95% bootstrap CIs and significant Welch t test results (P<.01). The model achieved a macroprecision of 0.935 (95% CI 0.918-0.951), macrorecall of 0.921 (95% CI 0.900-0.942), macro–F1-score of 0.927 (95% CI 0.908-0.945), and accuracy of 0.919 (95% CI 0.899-0.939). Attention visualizations suggested the model could capture less common TCM term associations, while integrated gradients highlighted high-attribution diagnostic features (eg, “gray-white stool” 0.933 in damp-heat syndrome; “indigestion” 1.204 in spleen-deficiency syndrome). Misclassification analyses indicated challenges in handling overlapping or atypical symptom presentations. Compared with LLMs, web-based platforms, and diagnostic instruments, TCMPCSD-BERT appeared to provide relatively higher accuracy, interpretability, and efficiency in processing long unstructured texts for syndrome differentiation. Conclusions: The TCMPCSD-BERT model shows potential for automated syndrome differentiation from unstructured clinical texts and broader application in TCM. Based on this study, it appears to improve operability over 4-diagnostic instruments and online platforms, and offers greater stability and accuracy than LLMs in specific tasks. However, these findings should be interpreted cautiously, given the subjectivity of syndrome definitions, data imbalance, and reliance on preprocessed, expert-annotated data. Further studies involving larger and more diverse populations are needed to validate its generalizability and support its broader application in real-world settings.

24 June 2026 in Molecules
Verified
Journal Article
Open access
PDF file
婷潘婷 潘
婷 潘
BWBaozhu Wang
Baozhu Wang
HDHaojie Du
Haojie Du
YYYuhan Yan
Yuhan Yan
Kai ZhangKai Zhang
Kai Zhang
ZZZhijun Zhang
Zhijun Zhang
Bacterial infections pose a serious threat to human health, and antibiotics remain the first-line therapeutic agents in clinical practice. However, the vast majority of antibiotics lack the ability to penetrate cell membranes, which severely limits the number of clinically available options for treating intracellular bacterial infections. Developing efficient intracellular antibiotic delivery strategies is therefore of considerable clinical significance, both for reducing antibiotic dosage and for expanding the repertoire of drugs applicable to intracellular infections. To address this challenge, we constructed a protein-based delivery platform mediated by a cell-penetrating miniprotein for efficient intracellular antibiotic delivery. In this system, bovine serum albumin (BSA), which possesses broad antibiotic-binding capability, was employed as the drug carrier, while the cell-penetrating miniprotein ZF5.3, which is capable of endosomal escape, served as the transmembrane delivery mediator. ZF5.3 was conjugated to BSA via a bioorthogonal reaction, and ceftriaxone (CRO) was selected as the model antibiotic to construct a nanoscale delivery system. The binding interaction between CRO and BSA was characterized using UV-Vis, HPLC, and molecular docking techniques. The assembly of the ZF5.3–BSA delivery platform was confirmed by UV-Vis absorption spectroscopy and gel electrophoresis. Intracellular delivery efficiency was evaluated by confocal fluorescence imaging and flow cytometry, and the results demonstrated that ZF5.3 conjugation enhanced intracellular protein delivery efficiency by over 5-fold. Fluorescence co-localization analysis revealed that ZF5.3-mediated cargo is mainly distributed in the cytoplasm and does not completely co-localize with lysosomal markers, suggesting its ability to effectively escape from lysosomes. An intracellular infection model using Staphylococcus aureus was established. Colony-forming unit (CFU) counting experiments confirmed that the delivery system significantly enhanced the intracellular antibacterial activity of ceftriaxone. CCK8 cytotoxicity assays confirmed that the system is non-toxic to cells.

26 December 2024 in JMIR Preprints
Verified
Preprint
Open access
HBHe Ba
He Ba
HDHaojie Du
Haojie Du
CCChien-shan Cheng
Chien-shan Cheng
YZYuan Zhang
Yuan Zhang
LRLinjie Ruan
Linjie Ruan
ZCZhen Chen
Zhen Chen
BACKGROUND Syndrome differentiation is crucial in traditional Chinese medicine (TCM) diagnosis and treatment, but it heavily relies on expert experience, limiting systematic standardization. OBJECTIVE This study developed and validated a BERT (bidirectional encoder representations from transformers)–based model, the traditional Chinese medicine pancreatic cancer syndrome differentiation bidirectional encoder representations from transformers (TCMPCSD-BERT), using in-house pancreatic cancer medical records, to digitalize expert knowledge and support standardized syndrome differentiation in TCM. METHODS A retrospective dataset of pancreatic cancer cases (2011-2024) from Fudan University Shanghai Cancer Center was annotated into 4 TCM syndrome types by 2 experts (Cohen κ=0.913). The proposed TCMPCSD-BERT model was compared with conventional models (long short-term memory and text convolutional neural network) embedded in TCM diagnostic tools and with large language models (LLMs; ChatGPT-4o, Kimi, Ernie Bot 4.0 Turbo, and Zhipu Qingyan) under a prompt engineering framework. Performance evaluation on in-house data was supplemented with attention visualizations and integrated gradients analyses for interpretability. The McNemar test assessed classification accuracy differences, while bootstrap 95% CIs quantified statistical uncertainty and stability. The Welch t test (2-tailed) was used to evaluate mean differences between TCMPCSD-BERT and the comparator models. RESULTS Among 6830 records, case counts were damp-heat syndrome (n=1694), spleen-deficiency syndrome (n=1185), damp-heat with spleen-deficiency syndrome (n=1178), and others (n=2773). On the test set, McNemar test showed significantly higher accuracy for TCMPCSD-BERT than the 3 baseline models and generally better performance than LLMs. In all comparisons, TCMPCSD-BERT achieved higher mean macroprecision, macrorecall, macro–F1-score, and accuracy, with nonoverlapping 95% bootstrap CIs and significant Welch t test results (P<.01). The model achieved a macroprecision of 0.935 (95% CI 0.918-0.951), macrorecall of 0.921 (95% CI 0.900-0.942), macro–F1-score of 0.927 (95% CI 0.908-0.945), and accuracy of 0.919 (95% CI 0.899-0.939). Attention visualizations suggested the model could capture less common TCM term associations, while integrated gradients highlighted high-attribution diagnostic features (eg, “gray-white stool” 0.933 in damp-heat syndrome; “indigestion” 1.204 in spleen-deficiency syndrome). Misclassification analyses indicated challenges in handling overlapping or atypical symptom presentations. Compared with LLMs, web-based platforms, and diagnostic instruments, TCMPCSD-BERT appeared to provide relatively higher accuracy, interpretability, and efficiency in processing long unstructured texts for syndrome differentiation. CONCLUSIONS The TCMPCSD-BERT model shows potential for automated syndrome differentiation from unstructured clinical texts and broader application in TCM. Based on this study, it appears to improve operability over 4-diagnostic instruments and web-based platforms, and offers greater stability and accuracy than LLMs in specific tasks. However, these findings should be interpreted cautiously, given the subjectivity of syndrome definitions, data imbalance, and reliance on preprocessed, expert-annotated data. Further studies involving larger and more diverse populations are needed to validate its generalizability and support its broader application in real-world settings.