Abstract
Drug use is an important part of patient treatment process to cure and prevent disease, following the strict application guidelines of clinical drugs. The availability of free and massive patient electronic medical records (EMRs) provides a new chance to mine drug use patterns by designing automatic discovery methods. In this paper, we propose a data-driven method to mine typical drug use patterns from EMRs. Firstly, we use a set of quintuple to define drug use distribution feature (DUDF) for each drug and represent patient treatment record with DUDF vector (DUDFV). Then we design a similarity measure method to compute the similarity between pairwise patient treatment records. Next we adopt affinity propagation (AP) clustering algorithm to cluster all patient treatment records, extract typical drug use patterns including typical drug use set, typical drug use day set, and the DUDF of each typical drug, and further evaluate and label typical drug use patterns with demographic and diagnostic information. Finally, experimental results on a real-world EMR data of sepsis patients show that our approach can effectively extract typical drug use patterns and develop standard treatments for patients based on their demographic and diagnostic information.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
The first code is the exemplar of a cluster, the last is the smallest similarity with the exemplar.
- 3.
The 3 denotes that the drug code 3 in Fig. 4(3) is Potassium Chloride.
References
Desalegn, A.A.: Assessment of drug use pattern using WHO prescribing indicators at Hawassa University teaching and referral hospital, south Ethiopia: a cross-sectional study. BMC Health Serv. Res. 13(1), 170 (2013)
WHO: The Rational Use of Drugs. Report of a conference of experts, Nairobi, 25–29 November 1985. World Health Organization, Geneva (1987)
Khan, S.U., Zomaya, A.Y., Abbas, A.: Handbook of Large-Scale Distributed Computing in Smart Healthcare. Springer, New York (2017). https://doi.org/10.1007/978-3-319-58280-1
Jensen, P.B., Jensen, L.J., Brunak, S.: Mining electronic health records: towards better research applications and clinical care. Nat. Rev. Genet. 13(6), 395–405 (2012)
Yadav, P., Steinbach, M., Kumar, V., Simon, G.: Mining electronic health records (EHR): a survey. ACM Comput. Surv. 50(6), 1–40 (2018)
Huang, Z., Dong, W., Bath, P., Ji, L., Duan, H.: On mining latent treatment patterns from electronic medical record. Data Min. Knowl. Discov. 29(4), 914–949 (2015)
Perer, A., Wang, F., Hu, J.: Mining and exploring care pathways from electronic medical records with visual analytics. J. Biomed. Inf. 56, 369–378 (2015)
Sun, L., Liu, C., Guo, C., Xie, Y., Xiong, H.: Data-driven automatic treatment regimen development and recommendation. In: Proceedings of the 22rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1865–1874. ACM (2016)
Yang, S., Dong, X., Sun, L., Zhou, Y., Farneth, R.A., Xiong, H.: A data-driven process recommender framework. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2111–2120. ACM (2017)
Hirano, S., Tsumoto, S.: Mining typical order sequences from EHR for building clinical pathways. In: Peng, W.C., et al. (eds.) PAKDD 2014. LNCS, vol. 8643, pp. 39–49. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-13186-3_5
Chen, J., Sun, L., Guo, C., Wei, W., Xie, Y.: A data-driven framework of typical treatment process extraction and evaluation. J. Biomed. Inf. 83, 178–195 (2018)
Liu, C., Wang, F., Hu, J., Xiong, H.: Temporal phenotyping from longitudinal electronic health records: a graph based framework. In: Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 705–714. ACM (2015)
Riccardo, M., Li, L., Kidd, B.A., Dudley, J.T.: Deep patient: an unsupervised representation to predict the future of patients from the electronic health records. Sci. Rep. 6, 26094 (2016)
Li, L., et al.: Identification of type 2 diabetes subgroups through topological analysis of patient similarity. Sci. Transl. Med. 7(311), 311ra174–311ra174 (2015)
Data, M.I.T.C.: Secondary Analysis of Electronic Health Records. Springer, New York (2016). https://doi.org/10.1007/978-3-319-43742-2
Sun, J., Wang, F., Hu, J., Ebadollahi, S.: Supervised patient similarity measure of heterogeneous patient records. ACM SIGKDD Explor. Newsl. 14(1), 16–24 (2012)
Wang, F., Sun, J., Ebadollahi, S.: Integrating distance metrics learned from multiple experts and its application in patient similarity assessment. In: Proceedings of the 2011 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics, pp. 59–70 (2011)
Garcelon, N., et al.: Finding patients using similarity measures in a rare diseases-oriented clinical data warehouse: Dr. warehouse and the needle in the needle stack. J. Biomed. I. 73, 51–61(2017)
Yang, S., et al.: Duration-aware alignment of process traces. In: Perner, P. (ed.) ICDM 2016. LNCS (LNAI), vol. 9728, pp. 379–393. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-41561-1_28
Forestier, G., Lalys, F., Riffaud, L., Trelhu, B., Jannin, P.: Classification of surgical processes using dynamic time warping. J. Biomed. Inf. 45, 255–264 (2012)
Han, J., Kamber, M., Pei, J.: Data Mining: Concepts and Techniques, 3rd edn. Morgan Kaufmann Publishers Inc., Burlington (2011)
Frey, B.J., Dueck, D.: Clustering by passing messages between data points. Science 315(5814), 972–976 (2007)
Sun, L., Guo, C., Liu, C., Xiong, H.: Fast affinity propagation clustering based on incomplete similarity matrix. Knowl. Inf. Syst. 51(3), 1–23 (2016)
Johnson, A.E.W., Pollard, T.J., Shen, L., Lehman, L.W.H., Feng, M., Ghassemi, M., et al.: MIMIC-III, a freely accessible critical care database. Sci. Data 3, 160035 (2016)
Wang, S., Li, X., Chang, X., Yao, L., Sheng, Q.Z., Long, G.: Learning multiple diagnosis codes for ICU patients with local disease correlation mining. ACM Trans. Knowl. Discov. Data 11(3), 31 (2017)
Johnson, A., Stone, D.J., Celi, L.A., Pollard, T.J.: The MIMIC code repository: enabling reproducibility in critical care research. J. Am. Med. Inf. Assoc. 25(1), 32–39 (2017)
Martin, G.S.: Sepsis, severe sepsis and septic shock: changes in incidence, pathogens and outcomes. Expert Rev. Anti-Infect. Ther. 10(6), 701–706 (2012)
Singer, M., et al.: The third international consensus definitions for sepsis and septic shock (Sepsis-3). J. Am. Med. Assoc. 315(8), 775–787 (2016)
Acknowledgements
This work was supported in part by the Natural Science Foundation of China [Grant Numbers 71771034, 71421001] and China Postdoctoral Science Foundation [Grant Number 2017M620054].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, J., Guo, C., Sun, L., Lu, M. (2018). Mining Typical Drug Use Patterns Based on Patient Similarity from Electronic Medical Records. In: Chen, J., Yamada, Y., Ryoke, M., Tang, X. (eds) Knowledge and Systems Sciences. KSS 2018. Communications in Computer and Information Science, vol 949. Springer, Singapore. https://doi.org/10.1007/978-981-13-3149-7_6
Download citation
DOI: https://doi.org/10.1007/978-981-13-3149-7_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-3148-0
Online ISBN: 978-981-13-3149-7
eBook Packages: Computer ScienceComputer Science (R0)