research-article

Experiences with mining temporal event sequences from electronic medical records: initial successes and some challenges

Authors:

Debprakash Patnaik,

Patrick Butler,

Naren Ramakrishnan,

Benjamin J. Keller,

David A. HanauerAuthors Info & Claims

KDD '11: Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining

Pages 360 - 368

https://doi.org/10.1145/2020408.2020468

Published: 21 August 2011 Publication History

Abstract

The standardization and wider use of electronic medical records (EMR) creates opportunities for better understanding patterns of illness and care within and across medical systems. Our interest is in the temporal history of event codes embedded in patients' records, specifically investigating frequently occurring sequences of event codes across patients. In studying data from more than 1.6 million patient histories at the University of Michigan Health system we quickly realized that frequent sequences, while providing one level of data reduction, still constitute a serious analytical challenge as many involve alternate serializations of the same sets of codes. To further analyze these sequences, we designed an approach where a partial order is mined from frequent sequences of codes. We demonstrate an EMR mining system called EMRView that enables exploration of the precedence relationships to quickly identify and visualize partial order information encoded in key classes of patients. We demonstrate some important nuggets learned through our approach and also outline key challenges for future research based on our experiences.

References

[1]

R. Agrawal and R. Srikant. Mining sequential patterns. In 11th ICDE, pages 3--14, Taipei, Taiwan, 1995.

Digital Library

[2]

R. Bellazzi et al. Methods and tools for mining multivariate temporal data in clinical and biomedical applications. In Conf Proc IEEE Eng Med Biol Soc., pages 5629--32, 2009.

[3]

K. Booth and G. Lueker. Testing for the Consecutive Ones Property, Interval Graphs, and Graph Planarity using PQ-tree Algorithms. JCSS, 13(3):335--379, 1976.

Digital Library

[4]

K. C. Chen, S. W. Hung, V. K. Seow, C. F. Chong, T. L. Wang, Y. C. Li, and H. Chang. The role of emergency ultrasound for evaluating acute pyelonephritis in the ed. Am J Emerg Med, Apr 2010.

[5]

S. Concaro et al. Temporal data mining for the assessment of the costs related to diabetes mellitus pharmacological treatment. In AMIA Annu Symp Proc., pages 119--123, 2009.

[6]

S. Concaro et al. Mining health care administrative data with temporal association rules on hybrid events. Methods Inf Med, 50(2), Dec 2010.

[7]

C. De Coster et al. Identifying priorities in methodological research using ICD-9-CM and ICD-10 administrative data: report from an international consortium. BMC Health Serv Res., 6:77, Jun 2006.

[8]

J. Denny et al. Extracting timing and status descriptors for colonoscopy testing from electronic medical records. J Am Med Inform Assoc., 17(4):383--8, Jul-Aug 2010.

[9]

W. L. Healy and R. Iorio. Total hip arthroplasty: optimal treatment for displaced femoral neck fractures in elderly patients. Clin Orthop Relat Res, (429):43--48, Dec 2004.

[10]

S. Heber and J. Stoye. Finding all common intervals of k permutations. In Proc. of the 12th CPM'01, pages 207--218, London, UK, UK, 2001. Springer-Verlag.

Digital Library

[11]

A. W. Howard, C. Macarthur, L. Rothman, A. Willan, and A. K. Macpherson. School playground surfacing and arm fractures in children: a cluster randomized trial comparing sand to wood chip surfaces. PLoS Med, 6(12), Dec 2009.

[12]

E. Jamrozik, N. de Klerk, and A. Musk. Clinical review: Asbestos-related disease. Intern Med J, Feb 2011.

[13]

E. T. Jaynes. Information theory and statistical mechanics. Phys. Rev., 106(4):620--630, May 1957.

[14]

W. Kormos. Primary Care Medicine, chapter Approach to the Patient With Sinusitis, pages 1402--1407. Lippincot WIlliams and WIlkins, 2009.

[15]

R. Kukafka et al. Redesigning electronic health record systems to support public health. J. of Biomedical Informatics, 40:398--409, August 2007.

Digital Library

[16]

G. Landau, L. Parida, and O. Weimann. Using PQ Trees for Comparative Genomics. In Proc. CPM, pages 128--143, 2005.

Digital Library

[17]

R. T. Loder. The demographics of playground equipment injuries in children. J Pediatr Surg, 43(4):691--699, Apr 2008.

[18]

J. A. Lowe, B. D. Crist, M. Bhandari, and T. A. Ferguson. Optimal treatment of femoral neck fractures according to patient's physiologic age: an evidence-based review. Orthop Clin North Am, 41(2):157--166, Apr 2010.

[19]

T. M and L. PL. Nasal Polyps: Origin, Etiology, Pathenogensis, and Structure, chapter Diseases of the sinuses: diagnosis and management, pages 57--68. 2001.

[20]

H. Mannila et al. Discovery of frequent episodes in event sequences. DMKD, 1:259--289, 1997.

Digital Library

[21]

H. Mannila and C. Meek. Global Partial Orders from Sequential Data. In Proc. KDD'00, pages 161--168, 2000.

Digital Library

[22]

L. Martino and S. Ahuja. Privacy policies of personal health records: an evaluation of their effectiveness in protecting patient information. In Proc. of 1st ACM Intl. Health Informatics Symp., pages 191--200, New York, NY, USA, 2010. ACM.

Digital Library

[23]

R. Moskovitch and Y. Shahar. Medical temporal-knowledge discovery via temporal abstraction. In AMIA Annu Symp Proc., pages 452--456, 2009.

[24]

A. Perotte. Using the entropy of icd9 documentation across patients to characterize using the entropy of ICD9 documentation across patients to characterize disease chronicity. AMIA Annual Symp., Nov 2010.

[25]

C. Plaisant et al. Searching electronic health records for temporal patterns in patient histories: a case study with microsoft amalgaa. In AMIA Annu Symp Proc. 2008, pages 601--605, 2008.

[26]

B. Reis et al. Longitudinal histories as predictors of future diagnoses of domestic abuse: modelling study. BMJ, 2009.

[27]

G. Savova et al. Towards temporal relation discovery from the clinical narrative. In AMIA Annu Symp Proc., pages 569--572, 2009.

[28]

E. Sendtner, T. Renkawitz, P. Kramny, M. Wenzl, and J. Grifka. Fractured neck of femur--internal fixation versus arthroplasty. Dtsch Arztebl Int, 107(23):401--407, Jun 2010.

[29]

H. Svanstrom et al. Temporal data mining for adverse events following immunization in nationwide danish healthcare databases. Drug Saf., 33(11):1015--25, Nov 2010.

[30]

N. Tatti. Maximum entropy based significance of itemsets. In Proc. 7th ICDM'07, pages 312--321, 2007.

Digital Library

[31]

Y. Yan, G. Fung, J. G. Dy, and R. Rosales. Medical coding classification by leveraging inter-code relationships. In Proc. 16th KDD'10, pages 193--202, New York, NY, USA, 2010. ACM.

Digital Library

Cited By

Poongodi KKumar D(2022)Natural Exponent Inertia Weight based Particle Swarm Optimization for Mining Serial Episode Rules from Event SequencesIETE Journal of Research10.1080/03772063.2021.202181569:8(5425-5439)Online publication date: 18-Jan-2022
https://doi.org/10.1080/03772063.2021.2021815
Kannan RPathuri SKumar D(2021)Device Interaction Graph: Directed Decision Graph for Settings Auto-CompletionIEEE Access10.1109/ACCESS.2020.30484239(4726-4737)Online publication date: 2021
https://doi.org/10.1109/ACCESS.2020.3048423
Salvatore MBeesley LFritsche LHanauer DShi XMondul APearce CMukherjee B(2021)Phenotype risk scores (PheRS) for pancreatic cancer using time-stamped electronic health record data: Discovery and validation in two large biobanksJournal of Biomedical Informatics10.1016/j.jbi.2020.103652113(103652)Online publication date: Jan-2021
https://doi.org/10.1016/j.jbi.2020.103652
Show More Cited By

Index Terms

Experiences with mining temporal event sequences from electronic medical records: initial successes and some challenges
1. Applied computing
  1. Life and medical sciences
    1. Health care information systems
2. Information systems
  1. Information systems applications
    1. Data mining

Recommendations

Temporal electronic phenotyping by mining careflows of breast cancer patients

Display Omitted A careflow mining approach designed to analyze heterogeneous longitudinal data is proposed.Temporal electronic phenotyping of EHR and billing data is performed.Better insights on the health care processes of breast cancer patients are ...
Building a National Electronic Medical Record Exchange System - Experiences in Taiwan

Electronic medical record (EMR) can support a secure, real-time, point-of-care, patient centric information resource for clinical care.Taiwan's government has been promoting the EMR adoption since 2000.We describe the EMR adoption strategies, current ...
Medical Informatics: A Model Developed for Diabetes Education Via Telemedicine

Fast developments in information and communication technology (ICT) have made it possible to develop new services for people. One of the most interesting areas is health care. Medical informatics is the discipline concerned with the systematic ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

KDD '11: Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining

August 2011

1446 pages

ISBN:9781450308137

DOI:10.1145/2020408

General Chair:
Chid Apte
IBM Research
,
Program Chairs:
Joydeep Ghosh
UT Austin
,
Padhraic Smyth
UC Irvine

Copyright © 2011 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 21 August 2011

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Conference

KDD '11

Sponsor:

KDD '11: The 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

August 21 - 24, 2011

California, San Diego, USA

Acceptance Rates

Overall Acceptance Rate 1,133 of 8,635 submissions, 13%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

41
Total Citations
View Citations
920
Total Downloads

Downloads (Last 12 months)9
Downloads (Last 6 weeks)2

Reflects downloads up to 16 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Poongodi KKumar D(2022)Natural Exponent Inertia Weight based Particle Swarm Optimization for Mining Serial Episode Rules from Event SequencesIETE Journal of Research10.1080/03772063.2021.202181569:8(5425-5439)Online publication date: 18-Jan-2022
Kannan RPathuri SKumar D(2021)Device Interaction Graph: Directed Decision Graph for Settings Auto-CompletionIEEE Access10.1109/ACCESS.2020.30484239(4726-4737)Online publication date: 2021
Salvatore MBeesley LFritsche LHanauer DShi XMondul APearce CMukherjee B(2021)Phenotype risk scores (PheRS) for pancreatic cancer using time-stamped electronic health record data: Discovery and validation in two large biobanksJournal of Biomedical Informatics10.1016/j.jbi.2020.103652113(103652)Online publication date: Jan-2021
Jalali LJain R(2021)Event Mining for Explanatory ModelingundefinedOnline publication date: 11-May-2021
Ao XShi HWang JZuo LLi HHe Q(2019)Large-Scale Frequent Episode Mining from Complex Event Sequences with HierarchiesACM Transactions on Intelligent Systems and Technology10.1145/332616310:4(1-26)Online publication date: 20-Jul-2019
Jentner WKeim D(2019)Visualization and Visual Analytic Techniques for PatternsHigh-Utility Pattern Mining10.1007/978-3-030-04921-8_12(303-337)Online publication date: 19-Jan-2019
Pimus IPeleg MSchertz M(2018)Sequence Mining of Comorbid Neurodevelopmental Disorders Using the SPADE AlgorithmMethods of Information in Medicine10.3414/ME15-01-014255:03(223-233)Online publication date: 8-Jan-2018
Yadav PSteinbach MKumar VSimon G(2018)Mining Electronic Health Records (EHRs)ACM Computing Surveys10.1145/312788150:6(1-40)Online publication date: 3-Jan-2018
Boytcheva S(2018)Clinical Text Mining for Context Sequences IdentificationMachine Learning and Knowledge Extraction10.1007/978-3-319-99740-7_15(223-236)Online publication date: 24-Aug-2018
Zhang JGong JBarnes LBonato PWang H(2017)HCNNProceedings of the Second IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies10.1109/CHASE.2017.80(214-221)Online publication date: 17-Jul-2017
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents