ABSTRACT
Traditional Chinese medicine (TCM), a style of medicine widely used in China for thousands of years, can complement modern western medicine by taking personalization as the core principle of clinical practice. A fundamental task in TCM, particularly important for achieving effective precision medicine, is to subcategorize patients with a general disease into groups corresponding to variations of that disease. In this paper, we conduct the first study of the problem of subcategorizing electronic patient records in TCM. While the general problem of subcategorization can be solved using basic clustering algorithms, accommodating variations in symptoms and herb prescriptions of TCM patient records when computing patient similarity is a major technical challenge that has yet to be addressed. To tackle this problem, we propose to learn inexact matchings of both symptoms and herbs from a TCM dictionary of herb functions by using an embedding algorithm. Our hypothesis is that the prior knowledge of herb-symptom associations in the TCM dictionary can be used to discover latent relationships among comorbid symptoms and functionally similar herbs, thereby improving the quality of subcategorization. We performed extensive experiments on large-scale real-world datasets. As expected, our approach leads to more accurate matchings between patient records than baseline approaches, and thus better subcategorization results.
We also show that the proposed algorithm can be used immediately in multiple clinical applications, such as retrieving similar patients as well as discovering two special TCM cases: similar symptoms treated by different herbs and different symptoms treated by similar herbs.
- Website. "TraditionalChineseMedicine: InDepth|NCCIH."2009.NCCIH.April1.https://nccih.nih.gov/health/whatiscam/chinesemed.htm. Accessed: 2016-5-29.Google Scholar
- Preparation process for yinianjin capsule, June 25 2014. CN Patent App. CN 201,210,561,504.Google Scholar
- D. Bertsimas, B. Dimitris, M. V. Bjarnadóttir, M. A. Kane, J. Christian Kryder, P. Rudra, V. Santosh, and W. Grant. Algorithmic prediction of Health-Care costs. Oper. Res., 56(6):1382--1392, 2008. Google ScholarDigital Library
- H. Cho, B. Berger, and J. Peng. Diffusion component analysis: unraveling functional topology in biological networks. In Research in Computational Molecular Biology, pages 62--64. Springer, 2015.Google ScholarCross Ref
- Committee on a Framework for Development a New Taxonomy of Disease, Board on Life Sciences, Division on Earth and Life Studies, and National Research Council. Toward Precision Medicine:: Building a Knowledge Network for Biomedical Research and a New Taxonomy of Disease. National Academies Press, 16 Dec. 2011.Google Scholar
- C. N. F. Committees. Chinese Pharmacopoeia 2015, June 2015.Google Scholar
- S. Dharmananda. Treatment of Gallstones with Chinese Herbs and Acupuncture. ITM, 2001.Google Scholar
- Z. Gao, J. Shao, H. Sun, W. Zhong, W. Zhuang, and Z. Zhang. Evaluation of different kinds of organic acids and their antibacterial activity in japanese apricot fruits. African Journal of Agricultural Research, 7(35):4911--4918, 2012.Google ScholarCross Ref
- Q. He, X. Zhou, Z. Zhou, M. Cui, and Z. Wu. Efficacy-based clustering analysis of traditional chinese medicinal herbs. Chin J Inf TCM, 11(7):561--562, 2004.Google Scholar
- L. Hubert and P. Arabie. Comparing partitions. Journal of classification, 2(1):193--218, 1985.Google ScholarCross Ref
- T. Lahans. Integrating chinese and conventional medicine in colorectal cancer treatment. Integr. Cancer Ther., 6(1):89--94, Mar. 2007.Google ScholarCross Ref
- D. L. McKay and J. B. Blumberg. A review of the bioactivity and potential health benefits of peppermint tea (mentha piperita l.). Phytotherapy Research, 20(8):619--633, 2006.Google ScholarCross Ref
- J. S. Nimitz. Antiviral supplement compositions and methods of use, Jan. 21 2016. US Patent 20,160,015,762.Google Scholar
- P. N. Robinson. Deep phenotyping for precision medicine. Hum. Mutat., 33(5):777--780, May 2012.Google ScholarCross Ref
- F. S. Roque, P. B. Jensen, H. Schmock, M. Dalgaard, M. Andreatta, T. Hansen, K. Søeby, S. Bredkjær, A. Juul, T. Werge, L. J. Jensen, and S. Brunak. Using electronic patient records to discover disease correlations and stratify patient cohorts. PLoS Comput. Biol., 7(8):e1002141, Aug. 2011.Google ScholarCross Ref
- Q. Shi, S. Qi, Z. Huihui, C. Jianxin, M. Xueling, Y. Yi, Z. Chenglong, and W. Wei. Study on TCM syndrome identification modes of coronary heart disease based on data mining. Evid. Based. Complement. Alternat. Med., 2012:1--11, 2012.Google ScholarCross Ref
- M. Smith, R. Saunders, L. Stuckhardt, and J. M. McGinnis, editors. Best Care at Lower Cost: The Path to Continuously Learning Health Care in America. National Academies Press (US), Washington (DC), 6 June 2014.Google Scholar
- N. X. Vinh, E. Julien, and B. James. Information theoretic measures for clusterings comparison. In Proceedings of the 26th Annual International Conference on Machine Learning - ICML '09, 2009. Google ScholarDigital Library
- M. Wang, W. Mingfeng, G. Zhi, W. Miqu, C. Feng, D. Weijun, and L. Ming. Combination of network construction and cluster analysis and its application to traditional chinese medicine. In Lecture Notes in Computer Science, pages 777--785. 2006. Google ScholarDigital Library
- S. Wang, H. Cho, C. Zhai, B. Berger, and J. Peng. Exploiting ontology graph for predicting sparsely annotated gene function. Bioinformatics, 31(12):i357--64, 15 June 2015.Google ScholarCross Ref
- N. Wiseman. Fundamentals of Chinese Medicine. Paradigm Publications, 1995.Google Scholar
- F. Xie, M. Zhang, C.-F. Zhang, Z.-T. Wang, B.-Y. Yu, and J.-P. Kou. Anti-inflammatory and analgesic activities of ethanolic extract and two limonoids from melia toosendan fruit. Journal of ethnopharmacology, 117(3):463--466, 2008.Google ScholarCross Ref
- Y. K. Zhao, Q. E. Cao, H. T. Liu, K. T. Wang, A. X. Yan, and Z. D. Hu. Determination of baicalin, chlorogenic acid and caffeic acid in traditional chinese medicinal preparations by capillary zone electrophoresis. Chromatographia, 51(7):483--486, 2000.Google ScholarCross Ref
Recommendations
Mining patterns of Chinese medicinal prescription for diabetes mellitus based on therapeutic effect
AbstractTraditional Chinese medicine (TCM) prescription comprises groups of Chinese herbs that embody thousands of years of history with respect to the treatment of diabetes mellitus (DM), a condition for which there are numerous prescriptions with ...
Study on Traditional Chinese Medicine for Treating COVID-19
ICBBE '20: Proceedings of the 2020 7th International Conference on Biomedical and Bioinformatics EngineeringCOVID-19, new coronavirus pneumonia, refers to viral pneumonia caused by new coronavirus (named as 2019-nCoV), with fever, cough, headache, fatigue, difficulty breathing and other symptoms as the main clinical manifestations. The earliest COVID-19 ...
Interactions between traditional Chinese medicine and western drugs in Taiwan
Most commonly interacting Chinese herbs were Ephedrae Herba and Angelicae Sinensis Radix/Angelicae Dahuricae Radix.Unique cultural factors that have resulted in widespread acceptance of both western and traditional Chinese medicine.Taiwan stands well ...
Comments