Tao Yang

Tao Yang

Auto-generated profile, based on publicly available information

Tao Yang

Crown Bioscience, Inc., San Diego, CA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
21 December 2020 in JMIR Medical Informatics
Verified
Journal Article
Open access
WGWenye Geng
Wenye Geng
XQXuanfeng Qin
Xuanfeng Qin
TYTao Yang
Tao Yang
ZCZhilei Cong
Zhilei Cong
ZWZhuo Wang
Zhuo Wang
LJLin Jiang
Lin Jiang
Background: Integrative medicine is a form of medicine that combines practices and treatments from alternative medicine with conventional medicine. The diagnosis in integrative medicine involves the clinical diagnosis based on modern medicine and syndrome pattern diagnosis. Electronic medical records (EMRs) are the systematized collection of patients health information stored in a digital format that can be shared across different health care settings. Although syndrome and sign information or relative information can be extracted from the EMR and content texts can be mapped to computability vectors using natural language processing techniques, application of artificial intelligence techniques to support physicians in medical practices remains a major challenge. Objective: The purpose of this study was to investigate model-based reasoning (MBR) algorithms for the clinical diagnosis in integrative medicine based on EMRs and natural language processing. We also estimated the associations among the factors of sample size, number of syndrome pattern type, and diagnosis in modern medicine using the MBR algorithms. Methods: A total of 14,075 medical records of clinical cases were extracted from the EMRs as the development data set, and an external test data set consisting of 1000 medical records of clinical cases was extracted from independent EMRs. MBR methods based on word embedding, machine learning, and deep learning algorithms were developed for the automatic diagnosis of syndrome pattern in integrative medicine. MBR algorithms combining rule-based reasoning (RBR) were also developed. A standard evaluation metrics consisting of accuracy, precision, recall, and F1 score was used for the performance estimation of the methods. The association analyses were conducted on the sample size, number of syndrome pattern type, and diagnosis of lung diseases with the best algorithms. Results: The Word2Vec convolutional neural network (CNN) MBR algorithms showed high performance (accuracy of 0.9586 in the test data set) in the syndrome pattern diagnosis of lung diseases. The Word2Vec CNN MBR combined with RBR also showed high performance (accuracy of 0.9229 in the test data set). The diagnosis of lung diseases could enhance the performance of the Word2Vec CNN MBR algorithms. Each group sample size and syndrome pattern type affected the performance of these algorithms. Conclusions: The MBR methods based on Word2Vec and CNN showed high performance in the syndrome pattern diagnosis of lung diseases in integrative medicine. The parameters of each group’s sample size, syndrome pattern type, and diagnosis of lung diseases were associated with the performance of the methods. Trial Registration: ClinicalTrials.gov NCT03274908; https://clinicaltrials.gov/ct2/show/NCT03274908

4 April 2023 in Cancer Research
Verified
Journal Article
Closed access
TYTao Yang
Tao Yang
RLRongfei Lu
Rongfei Lu
XXXiaofei Xu
Xiaofei Xu
LZLikun Zhang
Likun Zhang
DWDawei Wang
Dawei Wang
CECarl K. Edwards
Carl K. Edwards
Background. Th2 cytokines (e.g. IL-4, IL-5, IL13) drive defined allergic reactions and various autoimmune and inflammatory diseases including atopic dermatitis (AD), asthma and rhinitis. IL-4Ra is a receptor shared by both IL-4 and IL-13, thus blocking of IL-4Ra could prevent both IL-4 or IL-13 mediated Th2 inflammatory response. Dupilumab (Dupixent) is a humanized anti-IL-4Ra monoclonal antibody which binds to human IL-4Ra and attenuates IL-4/IL-13 mediated Th2 inflammation. It has been approved for treating moderate to severe AD and asthma. However, since Dupilumab isn’t cross-reacting to mouse IL-4Ra, there is an unmet need for a robust mouse model to evaluate Dupilumab biosimilars at preclinical stages. In this study, we described an oxazolone induced AD model in hIL-4/hIL-4Ra double knock-in mice and its application to evaluate Dupilumab and its biosimilars. Methods. The oxazolone induce AD mouse model was established in hIL-4/hIL-4Ra double knock-in mice by repeated topical applications of Oxazolone on ears. Oxazolone-induced mice received subcutaneous injection of Dupilumab at 25 mg/kg or 50 mg/kg. Dermatitis activity was assessed by measuring ear thickness, ear skin erosion, redness and scaling every other day. Serum were collected at the study end and IgE levels were measured by ELISA. In addition, spleens were also collected and their weights were compared. Ear were collected at study end and proceeded with cytokine analysis and pathology evaluation. Results. Repeated topical application of oxazolone on mouse ears induced AD-like phenotypes including ear skin swelling, erythema and scaling, drastic elevation of IgE in serum, excessive production of human IL-4 cytokine as well as excessive inflammatory cell infiltration in ear skin, which suggests oxazolone is able to induce AD in this hIL-4/hIL-4Ra double knock-in mice. Subcutaneous injection of Dupilumab at two different doses levels, 25 mg/kg and 50 mg/kg successfully ameliorated ear skin swelling, erythema and scaling at the study end. In addition, Dupilumab at both dose levels significantly reduced the IgE level in serum and mitigated the inflammatory cell infiltration, e.g. eosinophil infiltration, in mouse ear. Furthermore, Dupilumab treatment significantly reduced mouse IL-6 and mouse KC/GRO levels in mouse ear. However, Dupilumab at both dose levels did not change the serum levels of human IL-4 as well as some other Th1 cytokines such as IFN-γ, IL-1β, TNF-α, etc. in mouse ear. Conclusion. In summary, repeated challenge with Oxazolone in hIL-4/hIL-4Ra double knock-in mice resulted in the development of AD with a Th2-like hypersensitivity, mimicking the key features and pathology of the human disease, which responded to standard of care treatment Dupilumab. This provides a valuable translational model for the evaluation of future biosimilars of Dupilumab. Citation Format: Tao Yang, Rongfei Lu, Xiaofei Xu, Likun Zhang, Dawei Wang, Xinhe Feng, Xiaoyu An, Jessie (Jingjing) Wang, Xianfei He, Carl K. Edwards. Oxazolone induced atopic dermatitis mouse model using hIL-4/hIL-4Ra double knock-in mice, a preclinical mouse model for evaluating Dupilumab biosimilars. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5133.

31 July 2020 in JMIR Preprints
Verified
Preprint
Open access
WGWenye Geng
Wenye Geng
XQXuanfeng Qin
Xuanfeng Qin
TYTao Yang
Tao Yang
ZCZhilei Cong
Zhilei Cong
ZWZhuo Wang
Zhuo Wang
LJLin Jiang
Lin Jiang
BACKGROUND Integrative medicine is a form of medicine that combines practices and treatments from alternative medicine with conventional medicine. The diagnosis in integrative medicine involves the clinical diagnosis based on modern medicine and syndrome pattern diagnosis. Electronic medical records (EMRs) are the systematized collection of patients health information stored in a digital format that can be shared across different health care settings. Although syndrome and sign information or relative information can be extracted from the EMR and content texts can be mapped to computability vectors using natural language processing techniques, application of artificial intelligence techniques to support physicians in medical practices remains a major challenge. OBJECTIVE The purpose of this study was to investigate model-based reasoning (MBR) algorithms for the clinical diagnosis in integrative medicine based on EMRs and natural language processing. We also estimated the associations among the factors of sample size, number of syndrome pattern type, and diagnosis in modern medicine using the MBR algorithms. METHODS A total of 14,075 medical records of clinical cases were extracted from the EMRs as the development data set, and an external test data set consisting of 1000 medical records of clinical cases was extracted from independent EMRs. MBR methods based on word embedding, machine learning, and deep learning algorithms were developed for the automatic diagnosis of syndrome pattern in integrative medicine. MBR algorithms combining rule-based reasoning (RBR) were also developed. A standard evaluation metrics consisting of accuracy, precision, recall, and F1 score was used for the performance estimation of the methods. The association analyses were conducted on the sample size, number of syndrome pattern type, and diagnosis of lung diseases with the best algorithms. RESULTS The Word2Vec convolutional neural network (CNN) MBR algorithms showed high performance (accuracy of 0.9586 in the test data set) in the syndrome pattern diagnosis of lung diseases. The Word2Vec CNN MBR combined with RBR also showed high performance (accuracy of 0.9229 in the test data set). The diagnosis of lung diseases could enhance the performance of the Word2Vec CNN MBR algorithms. Each group sample size and syndrome pattern type affected the performance of these algorithms. CONCLUSIONS The MBR methods based on Word2Vec and CNN showed high performance in the syndrome pattern diagnosis of lung diseases in integrative medicine. The parameters of each group’s sample size, syndrome pattern type, and diagnosis of lung diseases were associated with the performance of the methods. CLINICALTRIAL ClinicalTrials.gov NCT03274908; https://clinicaltrials.gov/ct2/show/NCT03274908