An Ontology-Based Artificial Intelligence Model for Medicine Side-Effect Prediction: Taking Traditional Chinese Medicine as an Example

In this work, an ontology-based model for AI-assisted medicine side-effect (SE) prediction is developed, where three main components, including the drug model, the treatment model, and the AI-assisted prediction model, of the proposed model are presented. To validate the proposed model, an ANN structure is established and trained by two hundred forty-two TCM prescriptions. These data are gathered and classified from the most famous ancient TCM book, and more than one thousand SE reports, in which two ontology-based attributions, hot and cold, are introduced to evaluate whether the prescription will cause SE or not. The results preliminarily reveal that it is a relationship between the ontology-based attributions and the corresponding predicted indicator that can be learnt by AI for predicting the SE, which suggests the proposed model has a potential in AI-assisted SE prediction. However, it should be noted that the proposed model highly depends on the sufficient clinic data, and hereby, much deeper exploration is important for enhancing the accuracy of the prediction.

[1]  Xin Sun,et al.  Chinese Herbal Medicine Image Recognition and Retrieval by Convolutional Neural Network , 2016, PloS one.

[2]  Ling Zhu,et al.  Knowledge graph for TCM health preservation: Design, construction, and applications , 2017, Artif. Intell. Medicine.

[3]  Bo Yan,et al.  Classification of tongue color based on CNN , 2017, 2017 IEEE 2nd International Conference on Big Data Analysis (ICBDA)(.

[4]  Hongxia Guo,et al.  Research on TCM pulse condition identification using probabilistic neural networks , 2010, 2010 3rd International Conference on Biomedical Engineering and Informatics.

[5]  Ching-Hsing Luo,et al.  Neural network study for standardizing pulse-taking depth by the width of artery , 2015, Comput. Biol. Medicine.

[6]  Kilian Q. Weinberger,et al.  Feature hashing for large scale multitask learning , 2009, ICML '09.

[7]  Jun Dong,et al.  Wrist pulse signals analysis based on Deep Convolutional Neural Networks , 2014, 2014 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology.

[8]  David Zhang,et al.  Feature Extraction of Radial Arterial Pulse , 2014, 2014 International Conference on Medical Biometrics.

[9]  Joanne W Y Chung,et al.  Digitalizing traditional chinese medicine pulse diagnosis with artificial neural network. , 2012, Telemedicine journal and e-health : the official journal of the American Telemedicine Association.

[10]  Andrew Zisserman,et al.  Efficient Visual Search of Videos Cast as Text Retrieval , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Zhao Chen,et al.  Development of models for classification of action between heat-clearing herbs and blood-activating stasis-resolving herbs based on theory of traditional Chinese medicine , 2018, Chinese Medicine.

[12]  Zhaohui Wu,et al.  Knowledge discovery in traditional Chinese medicine: State of the art and perspectives , 2006, Artif. Intell. Medicine.

[13]  Siu Cheung Hui,et al.  Computational methods for Traditional Chinese Medicine: A survey , 2007, Comput. Methods Programs Biomed..

[14]  Tao Chen,et al.  Latent tree models and diagnosis in traditional Chinese medicine , 2008, Artif. Intell. Medicine.

[15]  A. Barabasi,et al.  Human symptoms–disease network , 2014, Nature Communications.

[16]  Aining Yin,et al.  Ontology development for unified traditional Chinese medical language system , 2004, Artif. Intell. Medicine.

[17]  Cungen Cao,et al.  Knowledge modeling and acquisition of traditional Chinese herbal drugs and formulae from text , 2004, Artif. Intell. Medicine.

[18]  Bo Zhang,et al.  Herb network construction and co-module analysis for uncovering the combination rule of traditional Chinese herbal formulae , 2010, BMC Bioinform..

[19]  Xie Zhu-fan,et al.  On standard nomenclature of basic Chinese medical terms (IIIB) , 2003 .

[20]  Baoyan Liu,et al.  Development of traditional Chinese medicine clinical data warehouse for medical knowledge discovery and decision support , 2010, Artif. Intell. Medicine.

[21]  Baogang Wei,et al.  Traditional Chinese medicine clinical records classification using knowledge-powered document embedding , 2016, 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[22]  Hua Xu,et al.  Named Entity Recognition in Chinese Clinical Text Using Deep Neural Network , 2015, MedInfo.

[23]  R. Velik.  An objective review of the technological developments for radial pulse diagnosis in Traditional Chinese Medicine , 2015 .

[24]  Xie Zhu-fan.  On standard nomenclature of basic Chinese medical terms (VA) , 2003 .

[25]  Aiping Lu,et al.  Syndrome differentiation in modern research of traditional Chinese medicine. , 2012, Journal of ethnopharmacology.

[26]  Zhaohui Wu,et al.  Integrative mining of traditional Chinese medicine literature and MEDLINE for functional gene networks , 2007, Artif. Intell. Medicine.

[27]  Wei Wang,et al.  Discovering treatment pattern in Traditional Chinese Medicine clinical cases by exploiting supervised topic model and domain knowledge , 2015, J. Biomed. Informatics.

[28]  Li Tian,et al.  The ontology-based knowledge representation modeling of the traditional-Chinese-medicine symptom , 2017, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).