Detecting anomalous sequences in electronic health records using higher-order tensor networks

Niu, Haoran; Omitaomu, Olufemi A.; Langston, Michael A.; Olama, Mohammad; Ozmen, Ozgur; Klasky, Hilda B.; Laurio, Angela; Sauer, Brian; Ward, Merry; Nebeker, Jonathan

doi:10.1016/j.jbi.2022.104219

Title: Detecting anomalous sequences in electronic health records using higher-order tensor networks

Journal Article · Thu Oct 13 00:00:00 EDT 2022 · Journal of Biomedical Informatics

DOI:https://doi.org/10.1016/j.jbi.2022.104219· OSTI ID:1895227

^[1];

^[2];

^[1]; Olama, Mohammad ^[3];

^[3]; Klasky, Hilda B. ^[3];

^[4]; Sauer, Brian ^[4]; Ward, Merry ^[4];

^[4]

Univ. of Tennessee, Knoxville, TN (United States)
Univ. of Tennessee, Knoxville, TN (United States); Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
US Department of Veterans Affairs, Washington, DC (United States)

Detecting anomalous sequences is an integral part of building and protecting modern large-scale health information technology (HIT) systems. These HIT systems generate a large volume of records of patients’ state and significant events, which provide a valuable resource to help improve clinical decisions, patient care processes, and other issues. However, detecting anomalous sequences in electronic health records (EHR) remains a challenge in healthcare applications for several reasons, including imbalances in the data, complexity of relationships between events in the sequence, and the curse of dimensionality. Conventional anomaly detection methods use the finite sequence of events to discriminate sequences. They fail to incorporate salient event details under variable higher-order dependencies (e.g., duration between events) that can provide better discrimination of sequences in their models. To address this problem, we propose event sequence and subsequence anomaly detection algorithms that (1) use network-based representations of interactions in the data, (2) account for variable higher-order dependencies in the data, and (3) incorporate events duration for adequate discrimination of the data. The proposed approach identifies anomalies by monitoring the change in the graph after the test sequence is removed from the network. The change is quantified using graph distance metrics so that dramatic changes in the network can be attributed to the removed sequence. Furthermore, the proposed subsequence algorithm recommends plausible paths and salient information for the detected anomalous subsequences. Our results show that the proposed event sequence anomaly detection algorithm outperforms the baseline methods for both synthetic data and real-world EHR data.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE; US Department of Veterans Affairs

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 1895227

Journal Information:: Journal of Biomedical Informatics, Vol. 135; ISSN 1532-0464

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (27)

Anomaly Detection for Discrete Sequences: A Survey Chandola, V.; Banerjee, A.; Kumar, V. IEEE Transactions on Knowledge and Data Engineering, Vol. 24, Issue 5 https://doi.org/10.1109/TKDE.2010.235	journal	May 2012
Detection of Abnormal Change in a time Series of Graphs Shoubridge, Peter; Kraetzl, Miro; Wallis, Wal Journal of Interconnection Networks, Vol. 03, Issue 01n02 https://doi.org/10.1142/S0219265902000562	journal	March 2002
Investigating hidden Markov models capabilities in anomaly detection Joshi, Shrijit S.; Phoha, Vir V. Proceedings of the 43rd annual southeast regional conference on - ACM-SE 43 https://doi.org/10.1145/1167350.1167387	conference	January 2005
A metabolomics-based approach for non-invasive screening of fetal central nervous system anomalies Troisi, Jacopo; Landolfi, Annamaria; Sarno, Laura Metabolomics, Vol. 14, Issue 6 https://doi.org/10.1007/s11306-018-1370-8	journal	May 2018
Problems with health information technology and their effects on care delivery and patient outcomes: a systematic review Kim, Mi Ok; Coiera, Enrico; Magrabi, Farah Journal of the American Medical Informatics Association, Vol. 24, Issue 2 https://doi.org/10.1093/jamia/ocw154	journal	February 2017
Efficient algorithms for mining outliers from large data sets Ramaswamy, Sridhar; Rastogi, Rajeev; Shim, Kyuseok ACM SIGMOD Record, Vol. 29, Issue 2 https://doi.org/10.1145/335191.335437	journal	June 2000
Building Usability Knowledge for Health Information Technology: A Usability-Oriented Analysis of Incident Reports Marcilly, Romaric; Schiro, Jessica; Beuscart-Zéphir, Marie Catherine Applied Clinical Informatics, Vol. 10, Issue 03 https://doi.org/10.1055/s-0039-1691841	journal	May 2019
Computing label-constraint reachability in graph databases Jin, Ruoming; Hong, Hui; Wang, Haixun Proceedings of the 2010 ACM SIGMOD International Conference on Management of data https://doi.org/10.1145/1807167.1807183	conference	June 2010
Detection of Behavioral Anomalies in Medication Adherence Patterns Among Patients With Serious Mental Illness Engaged With a Digital Medicine System Knights, Jonathan; Heidary, Zahra; Cochran, Jeffrey M. JMIR Mental Health, Vol. 7, Issue 9 https://doi.org/10.2196/21378	journal	September 2020
Video Anomaly Identification Saligrama, Venkatesh; Konrad, Janusz; Jodoin, Pierre-marc IEEE Signal Processing Magazine, Vol. 27, Issue 5 https://doi.org/10.1109/MSP.2010.937393	journal	September 2010
Efficient anomaly detection by modeling privilege flows using hidden Markov model Cho, Sung-Bae; Park, Hyuk-Jang Computers & Security, Vol. 22, Issue 1 https://doi.org/10.1016/S0167-4048(03)00112-3	journal	January 2003
DeepLog: Anomaly Detection and Diagnosis from System Logs through Deep Learning Du, Min; Li, Feifei; Zheng, Guineng Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security - CCS '17 https://doi.org/10.1145/3133956.3134015	conference	January 2017
Word2Vec Church, Kenneth Ward Natural Language Engineering, Vol. 23, Issue 1 https://doi.org/10.1017/S1351324916000334	journal	December 2016
Algorithms on Stings, Trees, and Sequences Gusfield, Dan ACM SIGACT News, Vol. 28, Issue 4 https://doi.org/10.1145/270563.571472	journal	December 1997
A review of PHR, EMR and EHR integration: A more personalized healthcare and public health policy Heart, Tsipi; Ben-Assuli, Ofir; Shabtai, Itamar Health Policy and Technology, Vol. 6, Issue 1 https://doi.org/10.1016/j.hlpt.2016.08.002	journal	March 2017
A clustering approach for detecting implausible observation values in electronic health records data Estiri, Hossein; Klann, Jeffrey G.; Murphy, Shawn N. BMC Medical Informatics and Decision Making, Vol. 19, Issue 1 https://doi.org/10.1186/s12911-019-0852-6	journal	July 2019
The effects and preventability of 2627 patient safety incidents related to health information technology failures: a retrospective analysis of 10 years of incident reporting in England and Wales Martin, Guy; Ghafur, Saira; Cingolani, Isabella The Lancet Digital Health, Vol. 1, Issue 3 https://doi.org/10.1016/S2589-7500(19)30057-3	journal	July 2019
Effects of health information technology on patient outcomes: a systematic review Brenner, Samantha K.; Kaushal, Rainu; Grinspan, Zachary Journal of the American Medical Informatics Association, Vol. 23, Issue 5 https://doi.org/10.1093/jamia/ocv138	journal	November 2015
Detecting, Categorizing, and Correcting Coverage Anomalies of RNA-Seq Quantification Ma, Cong; Kingsford, Carl Cell Systems, Vol. 9, Issue 6 https://doi.org/10.1016/j.cels.2019.10.005	journal	December 2019
Anomaly Detection and Diagnosis Algorithms for Discrete Symbol Sequences with Applications to Airline Safety Budalakoti, S.; Srivastava, A. N.; Otey, M. E. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), Vol. 39, Issue 1 https://doi.org/10.1109/TSMCC.2008.2007248	journal	January 2009
Improved$hboxK$-Means Clustering Algorithm for Exploring Local Protein Sequence Motifs Representing Common Structural Property Zhong, W.; Altun, G.; Harrison, R. IEEE Transactions on Nanobioscience, Vol. 4, Issue 3 https://doi.org/10.1109/TNB.2005.853667	journal	September 2005
Characterizing the behavior of a program using multiple-length N-grams Marceau, Carla NSPW '00 Proceedings of the 2000 workshop on New security paradigms, p. 101-110 https://doi.org/10.1145/366173.366197	conference	January 2000
Apache Spark: a unified engine for big data processing Zaharia, Matei; Franklin, Michael J.; Ghodsi, Ali Communications of the ACM, Vol. 59, Issue 11 https://doi.org/10.1145/2934664	journal	October 2016
Anomaly detection of event sequences using multiple temporal resolutions and Markov chains Boldt, Martin; Borg, Anton; Ickin, Selim Knowledge and Information Systems, Vol. 62, Issue 2 https://doi.org/10.1007/s10115-019-01365-y	journal	May 2019
Recurrent Neural Network Attention Mechanisms for Interpretable System Log Anomaly Detection Brown, Andy; Tuor, Aaron; Hutchinson, Brian Proceedings of the First Workshop on Machine Learning for Computing Systems - MLCS'18 https://doi.org/10.1145/3217871.3217872	conference	January 2018
Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding Hundman, Kyle; Constantinou, Valentino; Laporte, Christopher Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining https://doi.org/10.1145/3219819.3219845	conference	July 2018
Representing higher-order dependencies in networks Xu, Jian; Wickramarathne, Thanuka L.; Chawla, Nitesh V. Science Advances, Vol. 2, Issue 5 https://doi.org/10.1126/sciadv.1600028	journal	May 2016

Similar Records

EHR-BERT: A BERT-based model for effective anomaly detection in electronic health records

Journal Article · Tue Feb 06 00:00:00 EST 2024 · Journal of Biomedical Informatics · OSTI ID:1895227

Niu, Haoran; Omitaomu, Olufemi A.; Langston, Michael A.; +6 more

Adaptive Anomaly Detection for Dynamic Clinical Event Sequences

Conference · Tue Dec 01 00:00:00 EST 2020 · OSTI ID:1895227

Niu, Haoran; Omitaomu, Femi; Cao, Qing; +12 more

Detection of Anomalous Events in Electronic Health Records

Conference · Fri May 01 00:00:00 EDT 2020 · OSTI ID:1895227

Pellett, Jordan J.; Omitaomu, Femi; Olama, Mohammed M.; +9 more

Related Subjects

96 KNOWLEDGE MANAGEMENT AND PRESERVATION
Event sequence
Anomaly detection
Higher-order tensor network
Electronic health records

Title: Detecting anomalous sequences in electronic health records using higher-order tensor networks

Citation Formats

References (27)

Similar Records

Related Subjects