Skip to main content
Key Specialties
Cardiology Diabetology Endocrinology Gastroenterology Geriatrics and Gerontology Gynecology and Obstetrics Hematology Infectious Disease Internal Medicine Nephrology Neurology Oncology Pediatrics Respiratory Medicine Rheumatology Surgery
Congress Coverage
2024 ACC Congress 2023 ESMO Congress 2023 EASD Congress 2023 ERS Congress 2023 ESC Congress
Clinical Collections
Advances in Alzheimer’s

At a glance: The ONWARDS insulin icodec trials

A round-up of the ONWARDS phase 3 clinical trials evaluating the novel weekly insulin icodec in people with diabetes.
ADVANCED SEARCH
Log in
Top
BMC Medical Informatics and Decision Making
Published in: BMC Medical Informatics and Decision Making 1/2019

Open Access 01-12-2019 | Research article

A classification framework for exploiting sparse multi-variate temporal features with application to adverse drug event detection in medical records

Authors: Francesco Bagattini, Isak Karlsson, Jonathan Rebane, Panagiotis Papapetrou

Published in: BMC Medical Informatics and Decision Making | Issue 1/2019

Login to get access

Abstract

Background

Adverse drug events (ADEs) as well as other preventable adverse events in the hospital setting incur a yearly monetary cost of approximately $3.5 billion, in the United States alone. Therefore, it is of paramount importance to reduce the impact and prevalence of ADEs within the healthcare sector, not only since it will result in reducing human suffering, but also as a means to substantially reduce economical strains on the healthcare system. One approach to mitigate this problem is to employ predictive models. While existing methods have been focusing on the exploitation of static features, limited attention has been given to temporal features.

Methods

In this paper, we present a novel classification framework for detecting ADEs in complex Electronic health records (EHRs) by exploiting the temporality and sparsity of the underlying features. The proposed framework consists of three phases for transforming sparse and multi-variate time series features into a single-valued feature representation, which can then be used by any classifier. Moreover, we propose and evaluate three different strategies for leveraging feature sparsity by incorporating it into the new representation.

Results

A large-scale evaluation on 15 ADE datasets extracted from a real-world EHR system shows that the proposed framework achieves significantly improved predictive performance compared to state-of-the-art. Moreover, our framework can reveal features that are clinically consistent with medical findings on ADE detection.

Conclusions

Our study and experimental findings demonstrate that temporal multi-variate features of variable length and with high sparsity can be effectively utilized to predict ADEs from EHRs. Two key advantages of our framework are that it is method agnostic, i.e., versatile, and of low computational cost, i.e., fast; hence providing an important building block for future exploitation within the domain of machine learning from EHRs.
Appendix
Available only for authorised users
Literature
1.
Dalianis H, Hassel M, Henriksson A, Skeppstedt M. Stockholm EPR Corpus: a clinical database used to improve health care. In: Swedish Language Technology Conference.2012. p. 17–8.
2.
Karlsson I, Boström H. Predicting adverse drug events using heterogeneous event sequences. In: Healthcare Informatics (ICHI), 2016 IEEE International Conference On. IEEE: 2016. p. 356–62.
3.
Aspden P BJ, Wolcott J LRC. Generalized random shapelet forests. In: Committee on Identifying and Preventing Medication Errors.2007.
4.
Freeman R, Moore L, García Álvarez L, Charlett A, Holmes A. Advances in electronic surveillance for healthcare-associated infections in the 21st century: a systematic review. J Hosp Infect. 2013; 84(2):106–19.PubMedCrossRef
5.
Henriksson A, Zhao J, Boström H, Dalianis H. Modeling electronic health records in ensembles of semantic spaces for adverse drug event detection. In: IEEE International Conference on Bioinformatics and Biomedicine.2015. p. 343–50.
6.
Cao H, Markatou M, Melton GB, Chiang MF, Hripcsak G. Handling temporality of clinical events for drug safety surveillance. In: AMIA Annual Symposium Proceedings, vol. 2005. American Medical Informatics Association: 2005. p. 106–110.
7.
8.
Hersh WR. Adding value to the electronic health record through secondary use of data for quality assurance, research, and surveillance. Clin Pharmacol Ther. 2007; 81:126–8.CrossRef
9.
Weiskopf NG, Hripcsak G, Swaminathan S, Weng C. Defining and measuring completeness of electronic health records for secondary use. J Biomed Inform. 2013; 46(5):830–6.PubMedCrossRef
10.
Safran C, Bloomrosen M, Hammond WE, Labkoff S, Markel-Fox S, Tang PC, Detmer DE, et al.Toward a national framework for the secondary use of health data: an american medical informatics association white paper. J Am Med Inform Assoc. 2007; 14(1):1–9.PubMedPubMedCentralCrossRef
11.
Jensen PB, Jensen LJ, Brunak S. Mining electronic health records: towards better research applications and clinical care. Nat Rev Genet. 2012; 13(6):395–405.PubMedCrossRef
12.
Uzuner Ö, Goldstein I, Luo Y, Kohane I. Identifying patient smoking status from medical discharge records. J Am Med Inform Assoc. 2008; 15(1):14–24.PubMedPubMedCentralCrossRef
13.
Honigman B, Lee J, Rothschild J, Light P, Pulling R, Yu T, Bates D. Using computerized data to identify adverse drug events in outpatients. J Am Med Inform Assoc. 2001; 8(3):254–66.PubMedPubMedCentralCrossRef
14.
Henriksson A, Kvist M, Dalianis H, Duneld M. Identifying adverse drug event information in clinical notes with distributional semantic representations of context. J Biomed Inform. 2015; 57:333–49.PubMedCrossRef
15.
Pakhomov SV, Buntrock J, Chute CG. Prospective recruitment of patients with congestive heart failure using an ad-hoc binary classifier. J Biomed Inform. 2005; 38(2):145–53.PubMedCrossRef
16.
Norén GN, Bergvall T, Ryan PB, Juhlin K, Schuemie MJ, Madigan D. Empirical performance of the calibrated self-controlled cohort analysis within temporal pattern discovery: Lessons for developing a risk identification and analysis system. Drug Saf. 2013; 36(1):107–21. https://​doi.​org/​10.​1007/​s40264-013-0095-x.CrossRef
17.
Singh A, Nadkarni G, Gottesman O, Ellis SB, Bottinger EP, Guttag JV. Incorporating temporal ehr data in predictive models for risk stratification of renal function deterioration. J Biomed Inform. 2015; 53:220–8.PubMedCrossRef
18.
Zhao J, Henriksson A, Kvist M, Asker L, Boström H. Handling temporality of clinical events for drug safety surveillance. In: AMIA Annual Symposium Proceedings. American Medical Informatics Association: 2015. p. 1371.
19.
Zhao J. Temporal weighting of clinical events in electronic health records for pharmacovigilance. In: IEEE International Conference on Bioinformatics and Biomedicine.2015. p. 375–81.
20.
Zhao J, Henriksson A, Asker L, Boström H. Detecting adverse drug events with multiple representations of clinical measurements. In: IEEE International Conference on Bioinformatics and Biomedicine.2014. p. 536–43.
21.
Augusto JC. Temporal reasoning for decision support in medicine. Artif Intell Med. 2005; 33(1):1–24.PubMedCrossRef
22.
Chakrabarti K, Keogh E, Mehrotra S, Pazzani M. Locally adaptive dimensionality reduction for indexing large time series databases. ACM Trans Database Syst. 2002; 27(2):188–228.CrossRef
23.
Lin J, Keogh E, Lonardi S, Chiu B. A symbolic representation of time series, with implications for streaming algorithms. In: Proceedings of the 8th ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery. ACM: 2003. p. 2–11.
24.
Lin J, Keogh E, Wei L, Lonardi S. Experiencing sax: a novel symbolic representation of time series. Data Min Knowl Disc. 2007; 15(2):107–44.CrossRef
25.
Agrawal R, Faloutsos C, Swami A. Efficient Similarity Search in Sequence Databases. In: Foundations of Data Organization and Algorithms. Berlin Heidelberg: Springer: 1993.
26.
Chan K-P, Fu AW-C. Efficient time series matching by wavelets. In: Proceedings of 15th International Conference on Data Engineering. IEEE: 1999. p. 126–33.
27.
Ye L, Keogh E. Time series shapelets: a new primitive for data mining. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM: 2009. p. 947–56.
28.
Hills J, Lines J, Baranauskas E, Mapp J, Bagnall A. Classification of time series by shapelet transformation. Data Min Knowl Disc. 2014; 28(4):851–81.CrossRef
29.
Karlsson I, Papapetrou P, Boström H. Generalized random shapelet forests. Data Min Knowl Disc. 2016; 30(5):1053–85.CrossRef
30.
Hielscher T, Spiliopoulou M, Völzke H, Kühn J. Mining longitudinal epidemiological data to understand a reversible disorder. In: International Symposium on Intelligent Data Analysis.2014. p. 120–30.
31.
Hielscher T, Spiliopoulou M, Völzke H, Papapetrou P. Discovering, selecting and exploiting feature sequence records of study participants for the classification of epidemiological data on hepatic steatosis.2017.
32.
Zhao J, Papapetrou P, Asker L, Boström H. Learning from heterogeneous temporal data in electronic health records. J Biomed Inform. 2017; 65:105–19.PubMedCrossRef
33.
Eriksson R, Werge TM, Jensen LJ, Brunak S. Dose-specific adverse drug reaction identification in electronic patient records: Temporal data mining in an inpatient psychiatric population. In: Drug Safety.2014.
34.
Melton GB, Hripcsak G. Automated detection of adverse events using natural language processing of discharge summaries. J Am Med Inform Assoc. 2005; 12(4):448–57.PubMedPubMedCentralCrossRef
35.
Eriksson R, Jensen PB, Frankild S, Jensen LJ, Brunak S. Dictionary construction and identification of possible adverse drug events in danish clinical narrative text. J Am Med Inform Assoc. 2013; 20(5):947–53.PubMedPubMedCentralCrossRef
36.
Harpaz R, Haerian K, Chase HS, Friedman C. Mining electronic health records for adverse drug effects using regression based methods. In: the 1st ACM International Health Informatics Symposium. ACM: 2010. p. 100–107.
37.
Zhao J, Henriksson A, Asker L, Boström H. Predictive modeling of structured electronic health records for adverse drug event detection. BMC Med Informat Decis Making. 2015; 15(Suppl 4):1.
38.
39.
Larrañaga P, Calvo B, Santana R, Bielza C, Galdiano J, Inza I, Lozano JA, Armañanzas R, Santafé G, Pérez A, et al.Machine learning in bioinformatics. Brief Bioinform. 2006; 7(1):86–112.PubMedCrossRef
40.
Haneuse S, Daniels M. A general framework for considering selection bias in ehr-based studies: what data are observed and why?. eGEMs. 2016; 4(1):1–17.CrossRef
41.
Johnson SG, Speedie S, Simon G, Kumar V, Westra BL. A data quality ontology for the secondary use of ehr data. In: AMIA Annual Symposium Proceedings, vol. 2015. American Medical Informatics Association.2015. p. 1937.
42.
Li X, Shen C, Li L. Effectiveness research using electronic health records (ehrs). In: Wiley StatsRef: Statistics Reference Online: 2016.
43.
Chakrabarti K, Keogh E, Mehrotra S, Pazzani M. Locally adaptive dimensionality reduction for indexing large time series databases. ACM Trans Database Syst. 2002; 27(2):188–228.CrossRef
44.
Sant’Anna A, Wickström N. Symbolization of time-series: An evaluation of sax, persist, and aca. In: 4th International Congress on Image and Signal Processing, vol. 4. IEEE: 2011. p. 2223–8.
45.
Levenshtein V. Binary codes capable of correcting spurious insertions and deletions of ones. Probl Inf Transm. 1965; 1(1):8–17.
46.
Ye L, Keogh E. Time series shapelets: a new primitive for data mining. In: Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM: 2009. p. 947–56.
47.
Rakthanmanon T, Keogh E. Fast shapelets: A scalable algorithm for discovering time series shapelets. In: Proceedings of the 2013 SIAM International Conference on Data Mining. SIAM: 2013. p. 668–76.
48.
Dalianis H, Henriksson A, Kvist M, Velupillai S, Weegar R. Health bank - a workbench for data science applications in healthcare. CAiSE-2015 Industry Track co-located with 27th Conference on Advanced Information Systems Engineering (CAiSE - CEUR), International Conference on Advanced Information Systems. 2015; 1381:1–18.
49.
Stausberg J, Hasford J. Drug-related admissions and hospital-acquired adverse drug events in germany: a longitudinal analysis from 2003 to 2007 of icd-10-coded routine data. BMC Health Serv Res. 2011; 11(1):134.PubMedPubMedCentralCrossRef
50.
Pontet F, Petersen UM, Fuentes-Arderiu X, Nordin G, Bruunshuus I, Ihalainen J, Karlsson D, Forsum U, Dybkaer R, Schadow G, Kuelpmann W, Férard G, Kang D, McDonald CJ, Hill G. Clinical laboratory sciences data transmission: The npu coding system. Stud Health Technol Inform. 2009; 150:265–9.PubMedPubMedCentral
51.
52.
Hanley JA, McNeil BJ. The meaning and use of the area under a receiver operating characteristic (roc) curve. Radiology. 1982; 143(1):29–36.PubMedCrossRef
53.
Bradley AP. The use of the area under the roc curve in the evaluation of machine learning algorithms. Pattern Recognit. 1997; 30(7):1145–59.CrossRef
54.
Ferri IC, Flach P, Orallo J, Lachice N. ECAI’2004 First Workshop on ROC Analysis in AI. In: European Conference on Artificial Intelligence: 2004.
55.
Fawcett T. An introduction to roc analysis. Pattern Recogn Lett. 2006; 27(8):861–74.CrossRef
56.
Demšar J. Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res. 2006; 7:1–30.
57.
Wilcoxon F. Individual comparisons by ranking methods. Biom Bull. 1945; 1(6):80–3.CrossRef
58.
Bornstein S, Allolio B, Arlt W, et al.Diagnosis and treatment of primary adrenal insufficiency: An endocrine society clinical practice guideline. J Clin Endocrinol Metab. 2016; 101(2):364–89.PubMedCrossRef
59.
Verma R, Vasudevan B, Pragasam V. Severe cutaneous adverse drug reactions. Med J Armed Forces. 2013; 69(4):375–83.CrossRef
60.
Fernyhough P, Nigel A C. Abnormal calcium homeostasis in peripheral neuropathies. Cell calcium 47.2. 2010; 47(2):130–9.CrossRef
61.
Sim M, Kim D, Yoon J, Park D, Kim Y. Assessment of peripheral neuropathy in patients with rheumatoid arthritis who complain of neurologic symptoms. Ann Rehabil Med. 2014; 38(2):249–55.PubMedPubMedCentralCrossRef
Metadata
Title
A classification framework for exploiting sparse multi-variate temporal features with application to adverse drug event detection in medical records
Authors
Francesco Bagattini
Isak Karlsson
Jonathan Rebane
Panagiotis Papapetrou
Publication date
01-12-2019
Publisher
BioMed Central
Published in
BMC Medical Informatics and Decision Making / Issue 1/2019
Electronic ISSN: 1472-6947
DOI
https://doi.org/10.1186/s12911-018-0717-4

Other articles of this Issue 1/2019

BMC Medical Informatics and Decision Making 1/2019 Go to the issue

Research article

A Bayesian decision support sequential model for severity of illness predictors and intensive care admissions in pneumonia

Research article

Readiness to use telemonitoring in diabetes care: a cross-sectional study among Austrian practitioners

Research article

Multi-part quality evaluation of a customized mobile application for monitoring elderly patients with functional loss and helping caregivers

Research article

Talking about treatment benefits, harms, and what matters to patients in radiation oncology: an observational study

Research article

Epileptic patients’ willingness to receive cell-phone based medication reminder in Northwest Ethiopia

Research article

The use of technology in the context of frailty screening and management interventions: a study of stakeholders’ perspectives