Abstract
Pattern mining has been applied to classification problems. However, detection and analysis of frequently occurring patterns in clinical data is less studied. Instead, data-driven measures of the quality of clinical care are based on abstractions from clinical guidelines, and often are not validated on the basis of outcomes. We hypothesize that by using outcomes as a training signal, we can discover patterns of treatment that lead to better or worse than expected outcomes. Because clinical data is often censored, traditional classification algorithms are inappropriate. In addition, it is difficult to infer the latent meanings of patterns in clinical data if frequency is the only explanation. In this paper, we present a framework for discovering critical patterns in censored data. We evaluate this framework by comparing the patterns we detect with guidelines. Our framework can improve the accuracy in survival analysis and facilitate discovery of patterns of care that improve outcomes.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Mant, J.: Process versus outcome indicators in the assessment of quality of health care. Int. J. Qual. Heal. Care 13, 475–480 (2001)
Delen, D., Walker, G., Kadam, A.: Predicting breast cancer survivability: A comparison of three data mining methods. Artif. Intell. Med. 34(2), 113–127 (2005)
D’Agostinio, R.S., D’Agostinio, R.J.: Estimating treatment effects using observational data. J. Am. Med. Assoc. 297(3), 314–316 (2007)
Shetty, K.D., Dalal, S.R.: Using information mining of the medical literature to improve drug safety. J. Am. Med. Inform. Assoc. 18(5), 668–674 (2011)
Nor, G.N., Bate, A., Hopstadius, J., Star, K., Edwards, I.R.: Temporal Pattern Discovery for Trends and Transient Effects: Its Application to Patient Records, pp. 963–971. ACM, New York (2008)
Norén, G.N., Hopstadius, J., Bate, A., Star, K., Edwards, I.R.: Temporal pattern discovery in longitudinal electronic patient records. Data Min. Knowl. Disc. 20, 361–387 (2010)
Malhotra, K., Chau, D.H., Sun, J., Hadjipanayis, C., Navathe, S.B.: Temporal event sequence mining for glioblastoma survival prediction. In: KDD 2014 Workshop on Health Informatics (HI-KDD 2014) (2014)
Silva, A., Meira Jr., W., Queiroz, O., Cherchiglia, M.: Sequential medical treatment mining for survival analysis. In: SBBD 2009, pp. 166–180 (2009)
Bellazzi, R., Zupan, B.: Predictive data mining in clinical medicine: Current issues and guidelines. Int. J. Med. Inform. 77(2), 81–97 (2008)
Fisher, E.S., Wennberg, D.E., Alter, D.A., Vermeulen, M.J.: Analysis of observational studies in the presences of treatment selection bias: Effects of invasive cardiac management on AMI survival using propensity score and instrumental variable methods. J. Am. Med. Assoc. 297(3), 278–285 (2007)
Lee, J.G., Han, J., Li, X., Cheng, H.: Mining discriminative patterns for classifying trajectories on road networks. IEEE Trans. Knowl. Data Eng. 23(5), 712–726 (2011)
Lo, D., Cheng, H., Han, J., Khoo, S.C., Sun, C.: Classification of software behaviors for failure detection: A discriminative pattern mining approach. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol. 73, no. 2, pp. 557–565 (2009)
Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20, 273–297 (1995)
Cox, D.R.: Regression models and life tables. J. R. Stat. Soc. Ser. B 34(2), 187–220 (1972)
Liu, M., Matheny, M.E., Hu, Y., Xu, H.: Data mining methodologies for pharmacovigilance. SIGKDD Explor. Newsl. 14, 35–42 (2012)
Schneeweiss, S., Rassen, J.A., Glynn, R.J., Avorn, J., Mogun, H., Brookhart, M.A.: High-dimensional propensity score adjustment in studies of treatment effects using health care claims data. Epidemiology 20(4), 512–522 (2009)
Tatonetti, N.P., Denny, J.C., Murphy, S.N., Fernald, G.H., Krishnan, G., Castro, V., Yue, P., Tsau, P.S., Kohane, I., Roden, D.M., Altman, R.B.: Detecting drug interactions from adverse-event reports: interaction between paroxetine and pravastatin increases blood glucose levels. Clin. Pharmacol. Ther. 90(1), 133–142 (2011)
Jin, H., Chen, J., He, H., Williams, G.J., Kelman, C., O’Keefe, C.M.: Mining unexpected temporal associations: Applications in detecting adverse drug reactions. IEEE Trans. Inf Technol. Biomed. 12(4), 488–500 (2008)
Mazlack, L.J.: Using association rules without understanding their underlying causality reduces their decision value, pp. 312–319 (2004)
Esfandiari, N., Babavalian, M.R., Moghadam, A.-M.E., Tabar, V.K.: Knowledge discovery in medicine: Current issue and future trend. Expert Syst. Appl. 41(9), 4434–4463 (2014)
Kleinbaum, G.D., Klein, M.: Survival Analysis: A Self-Learning Text. Statistics for Biology and Health, 3rd edn. Springer, New York (2011)
Deyo, R.A., Cherkin, D.C., Ciol, M.A.: Adapting a clinical comorbidity index for use with ICD-9-CM administrative databases. J. Clin. Epidemiol. 45(6), 613–619 (1992)
Zaki, M.: SPADE: An efficient algorithm for mining frequent sequences. Mach. Learn. 42(1), 31–60 (2001)
Fournier-Viger, P., Wu, C.-W., Gomariz, A., Tseng, V.S.: VMSP: Efficient vertical mining of maximal sequential patterns. In: Sokolova, M., van Beek, P. (eds.) Canadian AI. LNCS, vol. 8436, pp. 83–94. Springer, Heidelberg (2014)
Zhu, L.-P., Li, L., Li, R., Zhu, L.-X.: Model-free feature screening for ultrahigh-dimensional data. J. Am. Stat. Assoc. 106(496), 1464–1475 (2011)
Heagerty, P.J., Zheng, Y.: Survival model predictive accuracy and ROC curves 1. Biometrics 61(March), 92–105 (2005)
spmf. An Open-Source Data Mining Library. http://www.philippe-fournier-viger.com/spmf
Healthline. http://www.healthline.com/druginteractions
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Chiu, H., Meeker, D. (2015). Reverse Engineering Measures of Clinical Care Quality: Sequential Pattern Mining. In: Ashish, N., Ambite, JL. (eds) Data Integration in the Life Sciences. DILS 2015. Lecture Notes in Computer Science(), vol 9162. Springer, Cham. https://doi.org/10.1007/978-3-319-21843-4_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-21843-4_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-21842-7
Online ISBN: 978-3-319-21843-4
eBook Packages: Computer ScienceComputer Science (R0)