Abstract
Electronic Health Records (EHRs) are typically stored as time-stamped encounter records. Judicious interpretation of temporal relationship between medical records is an integral part of assessing clinical information. Analogously, data analyzed by statistical or data mining methods need to contain time-interdependent analysis variables (TIAVs), whose values represent the clinical embodiment to be investigated. Unlike directly measured data, TIAV formulation is an iterative collaboration between programmer and investigator. This is because clinical TIAVs are context specific and often not absolute, and a custom program is needed to create and assess TIAVs. With rapidly growing interest in mining EHRs, there is a need for scalable solutions to optimize TIAV generation. We describe a framework of using sequences of time-referenced entities as building blocks. Scripts of simple functions are used with these entities to create TIAVs that incorporates multiple interdependencies, hence reducing the need for custom programs. We provide three examples to illustrate the principles of this method using the Veterans Health Administration’s EHR data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Jensen, P., Jensen, L., Brunak, S.: Mining electronic health records: towards better research applications and clinical care. Nat. Rev. Genet. 13(6), 395–405 (2012)
Coorevits, P., Sundgren, M., Klein, G., et al.: Electronic health records: new opportunities for clinical research. J. Intern. Med. 274(6), 547–560 (2013)
Murdoch, T., Detsky, A.: The inevitable application of big data to health care. J. Am. Med. Assoc. 309(13), 1351–1352 (2013)
Yadav, P., Steinbach, M., Kumar, V., et al.: Mining electronic health records (EHR): a survey. ACM Comput. Surv. 1(1), Article 1 (2016)
Myers, L., Stevens, J.: Using EHR to conduct outcome and health services research. In: Secondary Analysis of Electronic Health Records, pp. 61–70. Springer, Cham (2016)
Casey, J., Schwartz, B., Stewart, W., et al.: Using electronic health records for population health research: a review of methods and applications. Annu. Rev. Public Health 37, 61–81 (2016)
Cowie, M., Blomster, J., Curtis, L., et al.: Electronic health records to facilitate clinical research. Int. J. Clin. Cardiovasc. Res. 106(1), 1–9 (2017)
Hripcsak, G., Knirsch, C., Zhou, L.: Bias associated with mining electronic health records. J. Biomed. Discov. Collab. 6, 48–52 (2011)
Rusanov, A., Weiskopf, N., Wang, S., et al.: Hidden in plain sight: bias towards sick patients when sampling patients with sufficient electronic health record data for research. BMC Med. Inform. Decis. Mak. 14, 51 (2014)
Agniel, D., Kohane, I., Weber, H.: Biases in electronic health record data due to processes within the healthcare system: retrospective observational study. The BMJ 361, k1479 (2018)
Hruby, G., Matsoukas, K., Cimino, J., et al.: Facilitating biomedical researchers’ interrogation of electronic health record data: ideas from outside of biomedical informatics. J. Biomed. Inform. 60, 376–384 (2016)
Hand, D., Mannila, H., Smyth, P.: Principles of Data Mining. The MIT Press, Cambridge (2001)
Kriegel, H., Borgwardt, K., Kroger, P., et al.: Future trends in data mining. Data Min. Knowl. Disc. 15, 87–97 (2007)
Maimon, O., Rokach, L.: Data Mining and Knowledge Discovery Handbook. Springer, Boston (2010)
Han, J., Kamber, M., Pei, J.: Data preprocessing. In: Data Mining: Concepts and Techniques, pp. 83–124. Morgan Kaufmann, Burlington (2012)
Garca, S., Luengo, J., Herrera, F.: Data preprocessing. In: Data Mining. Springer, Heidelberg (2014)
Wickham, H.: Tidy data. J. Stat. Softw. 59(1), 1–23 (2014)
Shahar, Y.: A framework for knowledge-based temporal abstraction. Artif. Intell. 90(1), 79–133 (1997)
Nigrin, D., Kohane, I.: Temporal expressiveness in querying a time-stamp—based clinical database. J. Am. Med. Inform. Assoc. 7(2), 152–163 (2000)
Post, A., Harrison, J.: PROTEMPA: a method for specifying and identifying temporal sequences in retrospective data for patient selection. J. Am. Med. Inform. Assoc. 14(5), 674–683 (2007)
Moskovitch, R., Shahar, Y.: Medical temporal-knowledge discovery via temporal abstraction. In: AMIA Annual Symposium Proceedings, American Medical Informatics Association, p. 452 (2009)
Combi, C., Pozzi, G., Rossato, R.: Querying temporal clinical databases on granular trends. J. Biomed. Inform. 45(2), 273–291 (2012)
Lan, R., Lee, H., Monroe, M., et al.: Temporal search and replace: an interactive tool for the analysis of temporal event sequences. In: Human-Computer Interaction Lab Technical Report (2013)
Moskovitch, R., Walsh, C., Wang, F., et al.: Outcomes prediction via time intervals related patterns. In: IEEE International Conference on Data Mining, pp. 919–924 (2015)
Zhao, J., Papapetrou, P., Asker, L., et al.: Learning from heterogeneous temporal data in electronic health records. J. Biomed. Inform. 65, 105–119 (2017)
Fihn, S., Francis, J., Clancy, C., et al.: Insights from advanced analytics at the veterans health administration. Health Aff. 33(7), 1203–1211 (2014)
SAS Institute Inc., Cary, NC, USA
Quan, H., Sundararajan, V., Fong, A., et al.: Coding algorithms for defining comorbidities in ICD-9-CM and ICD-10 administrative data. Med. Care 43(11), 1130–1139 (2005)
Overhage, J., Ryan, P., Reich, C., et al.: Validation of a common data model for active safety surveillance research. J. Am. Med. Inform. Assoc. 19(1), 54–60 (2012)
Plaisant, C., Mushlin, R., Snyder, A., et al.: Lifelines: using visualization to enhance navigation and analysis of patient records. In: Proceeding of the annual American Medical Informatics Association Fall Symposium 1998, pp. 76–80 (1998)
Hirsch, J., Tanenbaum, J., Gorman, S., et al.: HARVEST, a longitudinal patient record summarizer. J. Am. Med. Inform. Assoc. 22(2), 263–274 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Woods, A., Meyer, C., Sauer, B., Cohen, B. (2021). Mining Time-Stamped Electronic Health Records with Referenced Sequences. In: Arai, K. (eds) Advances in Information and Communication. FICC 2021. Advances in Intelligent Systems and Computing, vol 1364. Springer, Cham. https://doi.org/10.1007/978-3-030-73103-8_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-73103-8_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73102-1
Online ISBN: 978-3-030-73103-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)