On mining latent treatment patterns from electronic medical records
Clinical pathway (CP) analysis plays an important role in health-care management in ensuring specialized, standardized, normalized and sophisticated therapy procedures for individual patients. Recently, with the rapid development of hospital information systems, a large volume of electronic medical records (EMRs) has been produced, which provides a comprehensive source for CP analysis. In this paper, we are concerned with the problem of utilizing the heterogeneous EMRs to assist CP analysis and improvement. More specifically, we develop a probabilistic topic model to link patient features and treatment behaviors together to mine treatment patterns hidden in EMRs. Discovered treatment patterns, as actionable knowledge representing the best practice for most patients in most time of their treatment processes, form the backbone of CPs, and can be exploited to help physicians better understand their specialty and learn from previous experiences for CP analysis and improvement. Experimental results on a real collection of 985 EMRs collected from a Chinese hospital show that the proposed approach can effectively identify meaningful treatment patterns from EMRs.
KeywordsClinical pathway analysis Probabilistic topic models Latent Dirichlet allocation Pattern discovery Electronic medical records
This work was supported by the National Nature Science Foundation of China under Grant No. 81101126, the National Hi-Tech R&D Plan of China under Grant No 2012AA02A601, and the Fundamental Research Funds for the Central Universities under Grant No 2014QNA5014. The authors would like to give special thanks to all experts who cooperated in the evaluation of the proposed method. The authors are especially thankful for the positive support received from the cooperative hospitals as well as to all medical staff involved. The authors would like to thank the anonymous reviewers for their constructive comments on an earlier draft of this paper.
- Agrawal R, Gunopulos D, Leymann F (1998) Mining process models from workflow logs. In HJ Schek, F Saltor, I Ramos, G Alonso (eds) Sixth international conference on extending database technology. Springer-Verlag, London, pp 469–483Google Scholar
- Blei DM, Ng AY, Jordan MI (March 2003) Latent Dirichlet allocation. J Mach Learn Res 3:993–1022Google Scholar
- Ghattas J, Peleg M, Soffer P, Denekamp Y (2010) Learning the context of a clinical process. In: Stefanie R-M, Shazia S, Leymann F (eds) Business process management workshops, vol 43. Lecture Notes in Business Information Processing. Springer, Berlin, pp 545–556Google Scholar
- Huang Z, Lu X, Duan H (2012) Anomaly detection in clinical processes. In AMIA Annu Symp Proc, pp 370–379Google Scholar
- Lakshmanan GT, Rozsnyai S, Wang F (2013) Investigating clinical care pathways correlated with outcomes. In: Daniel F, Wang J, Weber B (eds) Business process management, vol 8094. Lecture Notes in Computer Science.Springer, Berlin, pp 323–338Google Scholar
- Lang M, Burkle TB, Laumann S, Prokosch HU (2008) Process mining for clinical workflows: challenges and current limitations. In SK Andersen, GO Klein, S Schulz, J Aarts (eds) Proceedings of MIE2008 the XXIst international congress of the European federation for medical informatics, pp 229–234Google Scholar
- Mans R, Schonenberg H, Leonardi G, Panzarasa S, Cavallini A, Quaglini S (2008) Process mining techniques: an application to stroke care. Stud Health Technol Inform 136:573–578Google Scholar
- Peleg M, Soffer P, Ghattas J (2008) Mining process execution and outcomes—position paper. In: Arthur H, Benatallah B, Paik H-Y (eds) Business process management workshops, vol 4928. Lecture Notes in Computer Science. Springer, Berlin, pp 395–400Google Scholar
- Rosen-Zvi M, Griffiths T, Steyvers M, Smyth P (2004) The author-topic model for authors and documents. In 20th conference on uncertainty in artificial intelligence, pp 487–494Google Scholar
- Wang X, McCallum A, Wei X (2007) Topical n-grams: phrase and topic discovery, with an application to information retrieval. In IEEE international conference on data mining, pp 697–702Google Scholar
- Wang F, Zhang P, Cao N, Hu J, Sorrentino R (2014) Exploring the associations between drug side-effects and therapeutic indications. J Biomed Inform. doi: 10.1016/j.jbi.2014.03.014
- 2012 Writing Committee Members, Jneid H, Anderson JL, Wright RS, Adams CD, Bridges CR, Casey DE, Ettinger SM, Fesmire FM, Ganiats TG, Lincoff AM, Peterson ED, Philippides GJ, Theroux P, Wenger NK, Zidar JP (2012) 2012 ACCF/AHA focused update of the guideline for the management of patients with Unstable Angina/Non-ST-Elevation myocardial infarction (updating the 2007 guideline and replacing the 2011 focused update). Circulation 126(7):875–910Google Scholar