This paper proposes a novel unsupervised document embedding based clustering algorithm to generate clinical note templates. We adapted Charikar’s SimHash to embed each clinical document into a vector representation. We modified the traditional K-means algorithm to merge any two clusters with centroids when they are very close. Under the K-means paradigm, our algorithm designates the cluster representative corresponding to the document vector closest to the centroid as the prototype template. On a corpus of clinical notes, we evaluated the feasibility of utilizing our algorithm at the individual author level. The corpus contains 1,063,893 clinical notes corresponding to 19,146 unique providers between January 2011 and July 2016. Our algorithm achieved more than 80% precision and runs in O(n) time complexity. We further validated our algorithm using human annotators who reported it is able to efficiently detect a real clinical document that can represent the other documents in the same cluster at both the department level and the individual clinician level.
This is a preview of subscription content, access via your institution.
Buy single article
Instant access to the full article PDF.
Tax calculation will be finalised during checkout.
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
Tax calculation will be finalised during checkout.
Electronic health record
Dubois S, Romano N, Kale DC, Shah N, Jung K (2017) Effective representations of clinical notes. arXiv preprint arXiv:1705.07025
Tan P, Steinbach M, Karpatne A, Kumar V (2019) Introduction to data mining, 2nd edn. Pearson Education India, London
Naming clusters (2017) Dataiku.com. https://academy.dataiku.com/cluster-models/513439. Accessed 5 June 2020
Doing-Harris K, Patterson O, Igo S, Hurdle J (2013) Document sublanguage clustering to detect medical specialty in cross-institutional clinical texts. In: Proceedings of the 7th international workshop on data and text mining in biomedical informatics. ACM, pp 9–12
Patterson O, Hurdle JF (2011) Document clustering of clinical narratives: a systematic study of clinical sublanguages. In: AMIA annual symposium proceedings. American Medical Informatics Association, p 1099
Zhang R, Pakhomov S, Melton GB (2014) Longitudinal analysis of new information types in clinical notes. In: AMIA joint summits on translational science proceedings. American Medical Informatics Association, pp 232–237
Cohen R, Elhadad M, Elhadad N (2013) Redundancy in electronic health record corpora: analysis, impact on text mining performance and mitigation strategies. BMC Bioinform 14:10
Downey D, Etzioni O, Soderland S (2010) Analysis of a probabilistic model of redundancy in unsupervised information extraction. Artif Intell 174(11):726
Zhang R, Pakhomov S, McInnes BT, Melton GB (2011) Evaluating measures of redundancy in clinical texts. In: AMIA annual symposium proceedings, pp 1612–1620
Steinbach M, Karypis G, Kumar V (2000) A comparison of document clustering techniques. In: KDD workshop on text mining, vol 400, no 1, pp 525–526
Keogh E, Mueen A (2017) Curse of dimensionality. In: Sammut C, Webb GI (eds) Encyclopedia of machine learning and data mining. Springer, Boston, MA. https://doi.org/10.1007/978-1-4899-7687-1
Charikar MS (2002) Similarity estimation techniques from rounding algorithms. In: Proceedings of the thirty-fourth annual ACM symposium on theory of computing. ACM, pp 380–388
Sadowski C, Levin G (2007) Simhash: hash-based similarity detection. Technical report, Google
Boley D, Gini M, Gross R, Han E, Hastings K, Karpis G, Kumar V, Mobasher B, Moore J (1999) Partitioning-based clustering for web document categorization. Decis Support Syst 27(3):329–341
Zhao Y, Karypis G, Fayyad U (2005) Hierarchical clustering algorithms for document datasets. Data Min Knowl Discov 10(2):141–168
Ester M, Kriegel H, Sander J, Xu X (1996) A density-based algorithm for discovering clusters a density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the second international conference on knowledge discovery and data mining. AAAI, pp 226–231
Liao W, Liu Y, Choudhary A (2004) A grid-based clustering algorithm using adaptive mesh refinement. In: 7th workshop on mining scientific and engineering datasets of SIAM international conference on data mining, vol 22. SIAM, pp 61–69
Zhong S, Ghosh J (2003) A unified framework for model-based clustering. J Mach Learn Res 4:1001–1037
Wu H, Luk R, Wong K, Kwok K (2008) Interpreting TF-IDF term weights as making relevance decisions. ACM Trans Inf Syst 26(3):13
Hui S, Dechao Z (2016) A weighted topical document embedding based clustering method for news text. In: 2016 IEEE information technology, networking, electronic and automation control conference. IEEE, pp 1060–1065
Sood S (2011) Probabilistic simhash matching. Doctoral dissertation. Texas A&M University
Indyk P, Motwani R (1998) Approximate nearest neighbors: towards removing the curse of dimensionality. In: Proceedings of ACM STOC, pp 604–613
Svenstrup DT, Hansen J, Winther O (2017) Hash embeddings for efficient word representations. In: Advances in neural information processing systems, pp 4928–4936
Sim J, Wright CC (2005) The kappa statistic in reliability studies: use, interpretation, and sample size requirements. Phys Ther 85(3):257–268
McHugh ML (2012) Interrater reliability: the kappa statistic. Biochem Med 22(3):276–282
Institute of Medicine Committee on Quality of Health Care in America (2001) Crossing the quality chasm: a new health system for the 21st century. National Academies Press, Washington
Clark A (1998) Being there: putting brain, body, and world together again. MIT Press, Cambridge
Kashyap V, Turchin A, Morin L, Chang F, Li Q, Hongsermeier T (2006) Creation of structured documentation templates using natural language processing techniques. In: AMIA annual symposium proceedings. American Medical Informatics Association, p 977
Ferrández O, South BR, Shen S, Friedlin FJ, Samore MH, Meystre SM (2013) BoB, a best-of-breed automated text de-identification system for VHA clinical documents. J Am Med Inform Assoc 20(1):77–83
This work was partially funded by the Partners Innovation Fund, the National Natural Science Foundation of China Projects No. U1636207, No. U1936213, and the Shanghai Science and Technology Development Fund No. 19511121204, No.19DZ1200802. The authors would like to thank Wenxuan Shen, Hai Cao, and Siyuan Cheng, for their helpful comments on an early draft of the manuscript; and Lynn A. Volk, and Frank Y. Chang for help with the annotation.
Conflict of interest
The authors declare that they have no competing interests.
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Tang, C., Plasek, J.M., Xiong, Y. et al. A Clustering Algorithm Based on Document Embedding to Identify Clinical Note Templates. Ann. Data. Sci. (2020). https://doi.org/10.1007/s40745-020-00296-8
- Cluster analysis
- Medical informatics applications
- Electronic health records
- Embedding methods