Download PDF
Appl Clin Inform 2016; 07(04): 1135-1153
DOI: 10.4338/ACI-2016-03-SOA-0035
State of the Art/Best Practice Paper
Schattauer GmbH

Preprocessing structured clinical data for predictive modeling and decision support

A roadmap to tackle the challenges
José Carlos Ferrão
1   Siemens Healthcare, Rua Irmãos Siemens 1, 2720–093 Amadora, Portugal
2   CEG-IST, Centre for Management Studies of Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais 1, 1049–001 Lisbon, Portugal
,
Mónica Duarte Oliveira
2   CEG-IST, Centre for Management Studies of Instituto Superior Técnico, Universidade de Lisboa, Av. Rovisco Pais 1, 1049–001 Lisbon, Portugal
,
Filipe Janela
1   Siemens Healthcare, Rua Irmãos Siemens 1, 2720–093 Amadora, Portugal
,
Henrique M. G. Martins
3   Centre for Research and Creativity in Informatics, Hospital Prof. Doutor Fernando Fonseca, IC-19 Venteira, 2720–276 Amadora, Portugal
› Author Affiliations Funding The authors also acknowledge the support from Fundação para a Ciência e a Tecnologia (grant SFRH/ BDE/51605/2011), Siemens Healthcare and the Centre for Management Studies of Instituto Superior Técnico (CEG-IST, University of Lisbon).
Further Information

Publication History

received: 06 March 2016

accepted: 01 October 2016

Publication Date:
18 December 2017 (online)

   Permissions and Reprints

Summary

Background EHR systems have high potential to improve healthcare delivery and management. Although structured EHR data generates information in machine-readable formats, their use for decision support still poses technical challenges for researchers due to the need to preprocess and convert data into a matrix format. During our research, we observed that clinical informatics literature does not provide guidance for researchers on how to build this matrix while avoiding potential pitfalls.

Objectives This article aims to provide researchers a roadmap of the main technical challenges of preprocessing structured EHR data and possible strategies to overcome them.

Methods Along standard data processing stages – extracting database entries, defining features, processing data, assessing feature values and integrating data elements, within an EDPAI framework –, we identified the main challenges faced by researchers and reflect on how to address those challenges based on lessons learned from our research experience and on best practices from related literature. We highlight the main potential sources of error, present strategies to approach those challenges and discuss implications of these strategies.

Results Following the EDPAI framework, researchers face five key challenges: (1) gathering and integrating data, (2) identifying and handling different feature types, (3) combining features to handle redundancy and granularity, (4) addressing data missingness, and (5) handling multiple feature values. Strategies to address these challenges include: crosschecking identifiers for robust data retrieval and integration; applying clinical knowledge in identifying feature types, in addressing redundancy and granularity, and in accommodating multiple feature values; and investigating missing patterns adequately.

Conclusions This article contributes to literature by providing a roadmap to inform structured EHR data preprocessing. It may advise researchers on potential pitfalls and implications of methodological decisions in handling structured data, so as to avoid biases and help realize the benefits of the secondary use of EHR data.

Citation: Ferrão JC, Oliveira MD, Janela F, Martins HMG. Preprocessing structured clinical data for predictive modeling and decision support – a roadmap to tackle the challenges.

Keywords

Data mining - data access - integration and analysis - electronic health records and systems - structured data - clinical decision support
 

  • References

  • 1 Hripcsak G, Bloomrosen M, FlatelyBrennan P, Chute CG, Cimino J, Detmer DE. et al. Health data use, stewardship, and governance: ongoing gaps and challenges: a report from AMIA’s 2012 Health Policy Meeting. J Am Med Inform Assoc 2014; 21 (02) 204-211 doi:10.1136/amiajnl-2013-002117.
    CrossrefPubMedGoogle Scholar
  • 2 Schneeweiss S. Learning from Big Health Care Data. N Engl J Med 2014; 370: 2161-2163 doi:10.1056/NEJMp1401111.
    CrossrefPubMedGoogle Scholar
  • 3 Safran C, Bloomrosen M, Hammond WE, Labkoff S, Markel-Fox S, Tang PC. 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 (01) 1-9 doi:10.1197/jamia.M2273.
    CrossrefPubMedGoogle Scholar
  • 4 Wu J, Roy J, Stewart WF. Prediction modeling using EHR data: challenges, strategies, and a comparison of machine learning approaches. Med Care 2010; 48 (Suppl. 06) S106-S113 doi:10.1097/MLR.0b013e3181de9e17.
    CrossrefPubMedGoogle Scholar
  • 5 Berner ES. Clinical Decision Support Systems. 2nd ed. New York: Springer; 2007.
    Google Scholar
  • 6 Rowan M, Ryan T, Hegarty F, O’Hare N. The use of artificial neural networks to stratify the length of stay of cardiac patients based on preoperative and initial postoperative factors. Artif Intell Med 2007; 40 (03) 211-221 doi:10.1016/j.artmed.2007.04.005.
    CrossrefPubMedGoogle Scholar
  • 7 Carter EM, Potts HWW. Predicting length of stay from an electronic patient record system: a primary total knee replacement example. BMC Med Inform Decis Mak. 2014 14. 26 doi:10.1186/1472–6947–14–26.
    PubMedGoogle Scholar
  • 8 Chaudry B, Wang J, Wu S, Maglione M, Mojica W, Roth E. et al. Systematic Review: Impact of Health Information Technology on Quality, Efficiency, and Costs of Medical Care. Ann Intern Med 2006; 144 (10) 742-752.
    CrossrefPubMedGoogle Scholar
  • 9 Osheroff JA, Teich JM, Middleton B, Steen EB, Wright A, Detmer DE. A roadmap for national action on clinical decision support. J Am Med Inform Assoc 2007; 14 (02) 141-145 doi:10.1197/jamia.M2334.
    CrossrefPubMedGoogle Scholar
  • 10 Prokosch HU, Ganslandt T. Perspectives for medical informatics. Reusing the electronic medical record for clinical research. Methods Inf Med 2009; 48 (01) 38-44.
    Article in Thieme ConnectPubMedGoogle Scholar
  • 11 Cios KJ, Moore GW. Uniqueness of medical data mining. Artif Intell Med 2002; 26 1-2 1-24.
    CrossrefPubMedGoogle Scholar
  • 12 Lin JH, Haug PJ. Data preparation framework for preprocessing clinical data in data mining. Proceedinfs of AMIA Annu Symp. 2006. Nov 11-15; Washington DC: USA; 2006: 489-93.
    Google Scholar
  • 13 Kotsiantis SB. Supervised Machine Learning-: A Review of Classification Techniques. Informatica 2007; 31: 249-268.
    PubMedGoogle Scholar
  • 14 McDonald CJ. Computer-Stored Medical Records: Their Future Role in Medical Practice, J Am Med Assoc. 1988; 259 (23) 3433-3440 doi:10.1001/jama.1988.03720230043028.
    PubMedGoogle Scholar
  • 15 Iavindrasana J, Cohen G, Depeursinge A, Müller H, Meyer R, Geissbuhler A. Clinical data mining: a review. Yearb Med Inform; 2009. 48 (Suppl. 1): 1-13.
    Google Scholar
  • 16 Hand DJ, Mannila H, Smyth P. Principles of Data Mining. 3rd edition. Cambridge, USA: MIT Press; 2001
    Google Scholar
  • 17 International Organization For Standardization. ISO/TR 20514 Electronic health record – Definition, scope and context. 2005 doi:ISO/TR 20514:2005(E).
    PubMedGoogle Scholar
  • 18 International Organization For Standardization. ISO 18308 – Health informatics – Requirements for an electronic health record architecture. 2011
    PubMedGoogle Scholar
  • 19 International Organization For Standardization. ISO 21090 – Health informatics – Harmonized data types for information interchange. 2011
    PubMedGoogle Scholar
  • 20 International Organization For Standardization. ISO/EN 13606 – Health Informatics – Electronic Health Record Communication. 2010
    PubMedGoogle Scholar
  • 21 Santos MR, Bax MP, Kalra D. Building a logical EHR architecture based on ISO 13606 standard and semantic web technologies. Stud Health Technol Inform 2010; 160 (Pt 1): 161-165.
    PubMedGoogle Scholar
  • 22 Dolin RH, Alschuler L, Boyer S, Beebe C, Behlen FM, Biron PV. et al. HL7 Clinical Document Architecture, Release 2. J Am Med Inform Assoc 2006; 13 (01) 30-39 doi:10.1197/jamia.M1888.
    CrossrefPubMedGoogle Scholar
  • 23 Beale T, Heard S. OpenEHR Architecture Overview. 2006
    PubMedGoogle Scholar
  • 24 Atzeni P, De Antonellis V. Relational database theory. Redwood City, USA: Benjamin-Cummings Publishing; 1993
    Google Scholar
  • 25 Lee KK, Tang WC, Choi KS. Alternatives to relational database: comparison of NoSQL and XML approaches for clinical data storage. Comput Methods Programs Biomed 2013; 110 (01) 99-109 doi:10.1016/j.cmpb.2012.10.018.
    CrossrefPubMedGoogle Scholar
  • 26 Cattell R. Scalable SQL and NoSQL data stores. ACM SIGMOD Rec 2011; 39 (04) 12-27 doi:10.1145/1978915.1978919.
    CrossrefPubMedGoogle Scholar
  • 27 Stalidis G, Prentza A, Vlachos IN, Maglavera S, Koutsouris D. Medical support system for continuation of care based on XML web technology. Int J Med Inform 2001; 64 2-3 385-400 doi:10.1016/S1386–5056(01)00195–2.
    CrossrefPubMedGoogle Scholar
  • 28 Catley C, Frize M. A prototype XML-based implementation of an integrated “intelligent” neonatal intensive care unit. Proceedings of the 4th Int IEEE EMBS Spec Top Conf Inf Technol Appl Biomed. Apr 24-26 2003; Birmingham, UK: 2003: 322-325 doi:10.1109/ITAB.2003.1222543.
    Google Scholar
  • 29 Gainer V, Hackett K, Mendis M, Kuttan R, Pan W, Phillips LC. et al. Using the i2b2 hive for clinical discovery: an example. Proceedings of AMIA Annu Symp. 2007. Nov 10-14; Chicago, USA: 2007: 959.
    Google Scholar
  • 30 Murphy SN, Weber G, Mendis M, Gainer V, Chueh HC, Churchill S. et al. Serving the enterprise and beyond with informatics for integrating biology and the bedside (i2b2). J Am Med Inform Assoc 2010; 17 (02) 124-130 doi:10.1136/jamia.2009.000893.
    CrossrefPubMedGoogle Scholar
  • 31 Rea S, Pathak J, Savova G, Oniki TA, Westberg L, Beebe CE. et al. Building a robust, scalable and standards-driven infrastructure for secondary use of EHR data: the SHARPn project. J Biomed Inform 2012; 45 (04) 763-771 doi:10.1016/j.jbi.2012.01.009.
    CrossrefPubMedGoogle Scholar
  • 32 Chute CG, Pathak J, Savova GK, Bailey KR, Schor MI, Hart LA. et al. The SHARPn project on secondary use of Electronic Medical Record data: progress, plans, and possibilities. Proceedings of AMIA Annu Symp. 2011. Oct 22-26; Washington DC, USA: 2011: 248-56.
    Google Scholar
  • 33 De Moor G, Sundgren M, Kalra D, Schmidt A, Dugas M, Claerhout B. et al. Using electronic health records for clinical research: the case of the EHR4CR project. J Biomed Inform 2015; 53: 162-173 doi:10.1016/j.jbi.2014.10.006.
    CrossrefPubMedGoogle Scholar
  • 34 El Fadly A, Rance B, Lucas N, Mead C, Chatellier G, Lastic PY. et al. Integrating clinical research with the Healthcare Enterprise: from the RE-USE project to the EHR4CR platform. J Biomed Inform 2011; 44 su1 S94-S102 doi:10.1016/j.jbi.2011.07.007.
    CrossrefPubMedGoogle Scholar
  • 35 Danciu I, Cowan JD, Basford M, Wang X, Saip A, Osgood S. et al. Secondary use of clinical data: the Vanderbilt approach. J Biomed Inform 2014; 52: 28-35 doi:10.1016/j.jbi.2014.02.003.
    CrossrefPubMedGoogle Scholar
  • 36 Oster S, Langella S, Hastings S, Ervin S, Madduri R, Phillips J. et al. caGrid 1.0: an enterprise Grid infrastructure for biomedical research. J Am Med Inform Assoc 2008; 15 (02) 138-149 doi:10.1197/jamia.M2522.
    CrossrefPubMedGoogle Scholar
  • 37 Bradshaw RL, Matney S, Livne OE. et al. Architecture of a federated query engine for heterogeneous resources. Proceedings of AMIA Annu Symp. 2009. Nov 14-18; San Francisco, USA: 2009: 70-4.
    Google Scholar
  • 38 Tsoumakas G, Katakis I, Vlahavas I. Mining Multi-label Data. In: Mainon O, Rokach L. editors. Data Mining and Knowledge Discovery Handbook. New York: Springer; 2010: 667-685.
    Google Scholar
  • 39 Wu L, Barash G, Bartolini C. A Service-oriented Architecture for Business Intelligence. Proceedings of the IEEE Int Conf Serv Comput Appl (SOCA). 2007. Jun 19-20; Newport Beach, USA; 2007: 279-285 doi:10.1109/SOCA.2007.6.
    Google Scholar
  • 40 Ng K, Ghoting A, Steinhubl SR, Stewart WF, Malin B, Sun J. PARAMO: a PARAllel predictive MOdeling platform for healthcare analytic research using electronic health records. J Biomed Inform 2014; 48: 160-170 doi:10.1016/j.jbi.2013.12.012.
    CrossrefPubMedGoogle Scholar
  • 41 Pietka E. Large-Scale Hospital Information System in clinical practice. Int Congr Ser 2003; 1256: 843-848 doi:10.1016/S0531–5131(03)00458–8.
    CrossrefPubMedGoogle Scholar
  • 42 AHIMA Work Group. Problem List Guidance in the EHR. J AHIMA 2008; 82 (09) 73-77.
    PubMedGoogle Scholar
  • 43 Holmes C. The Problem List beyond Meaningful Use Part I: The Problems with problem Lists. J AHIMA 2011; 82: 30-35.
    PubMedGoogle Scholar
  • 44 Moshkovich H. Rule induction in data mining: effect of ordinal scales. Expert Syst Appl 2001; 22 (04) 303-311 doi:10.1016/S0957–4174(02)00018–0.
    PubMedGoogle Scholar
  • 45 Cimino JJ. Review paper: coding systems in health care. Methods Inf Med 1996; 35 (4-5): 273-284.
    Article in Thieme ConnectPubMedGoogle Scholar
  • 46 Liu S, Moore R, Ganesan V, Nelson S. RxNorm: prescription for electronic drug information exchange. IT Prof 2005; 07 (05) 17-23 doi:10.1109/MITP.2005.122.
    PubMedGoogle Scholar
  • 47 Bennett CC. Utilizing RxNorm to support practical computing applications: capturing medication history in live electronic health records. J Biomed Inform 2012; 45 (04) 634-641 doi:10.1016/j.jbi.2012.02.011.
    CrossrefPubMedGoogle Scholar
  • 48 Huff SM, Rocha RA, McDonald CJ, De Moor GJE, Fiers T, Bidgood WD. et al. Development of the Logical Observation Identifier Names and Codes (LOINC) Vocabulary. J Am Med Inform Assoc 1998; 05 (03) 276-292 doi:10.1136/jamia.1998.0050276.
    CrossrefPubMedGoogle Scholar
  • 49 Doan A, Halevy A, Ives Z. Principles of Data Integration. 1st ed. Morgan Kaufmann; 2012
    Google Scholar
  • 50 Brazhnik O, Jones JF. Anatomy of data integration. J Biomed Inform 2007; 40 (03) 252-269 doi:10.1016/j.jbi.2006.09.001.
    CrossrefPubMedGoogle Scholar
  • 51 Burgun A, Bodenreider O. Accessing and integrating data and knowledge for biomedical research. Yearb Med Inform. 2008: 91-101.
    PubMedGoogle Scholar
  • 52 Giuse D. Health information systems challenges: the Heidelberg conference and the future. Int J Med Inform 2003; 69 2-3 105-114 doi:10.1016/S1386–5056(02)00182-X.
    CrossrefPubMedGoogle Scholar
  • 53 Donnelly WJ. Viewpoint: patient-centered medical care requires a patient-centered medical record. Acad Med 2005; 80 (01) 33-38.
    CrossrefPubMedGoogle Scholar
  • 54 Bellazzi R, Zupan B. Predictive data mining in clinical medicine: current issues and guidelines. Int J Med Inform 2008; 77 (02) 81-97 doi:10.1016/j.ijmedinf.2006.11.006.
    CrossrefPubMedGoogle Scholar
  • 55 Guyon I, Elisseeff A. An Introduction to Variable and Feature Selection. J Mach Learn Res 2003; 03: 1157-1182.
    PubMedGoogle Scholar
  • 56 Liu H, Motoda H, Setiono R, Zhao Z. Feature Selection: An Ever Evolving Frontier in Data Mining. in: JMLR Work Conf Proc 2010; 10: 4-13.
    PubMedGoogle Scholar
  • 57 Dash M, Liu H. Feature selection for classification. Intell Data Anal 1997; 01: 131-156 doi:10.1016/S1088–467X(97)00008–5.
    CrossrefPubMedGoogle Scholar
  • 58 Cimino JJ. Desiderata for controlled medical vocabularies in the twenty-first century. Methods Inf Med 1998; 37 4-5 394-403.
    Article in Thieme ConnectPubMedGoogle Scholar
  • 59 Lippmann R. An introduction to computing with neural nets. IEEE ASSP Mag 1987; 04 (02) 4-22 doi:10.1109/MASSP.1987.1165576.
    CrossrefPubMedGoogle Scholar
  • 60 Quinlan JR. Decision trees and decision-making. IEEE Trans Syst Man Cybern 1990; 20 (02) 339-346 doi:10.1109/21.52545.
    CrossrefPubMedGoogle Scholar
  • 61 Saeys Y, Inza I, Larrañaga P. A review of feature selection techniques in bioinformatics. Bioinformatics 2007; 23 (19) 2507-2517.
    CrossrefPubMedGoogle Scholar
  • 62 Lazar C, Taminau J, Meganck S, Steenhoff D, Coletta A, Molter C. et al. A survey on filter techniques for feature selection in gene expression microarray analysis. IEEE/ACM Trans Comput Biol Bioinform 2012; 09 (04) 1106-1119 doi:10.1109/TCBB.2012.33.
    CrossrefPubMedGoogle Scholar
  • 63 Suits DB. Use of Dummy Variables in Regression Equations. J Am Stat Assoc 1957; 52: 548-551 doi:10.1080/01621459.1957.10501412.
    CrossrefPubMedGoogle Scholar
  • 64 Liu H, Hussain F, Tan CL, Dash M. Discretization: An Enabling Technique. Data Min Knowl Discov 2002; 06: 393-423.
    CrossrefPubMedGoogle Scholar
  • 65 Chen C, Garrido T, Chock D, Okawa G, Liang L. The Kaiser Permanente Electronic Health Record: transforming and streamlining modalities of care. Health Aff (Millwood) 2009; 28 (02) 323-333 doi:10.1377/hlthaff.28.2.323.
    CrossrefPubMedGoogle Scholar
  • 66 Mäenpää T, Suominen T, Asikainen P, Maass M, Rostila I. The outcomes of regional healthcare information systems in health care: a review of the research literature. Int J Med Inform 2009; 78 (11) 757-771 doi:10.1016/j.ijmedinf.2009.07.001.
    CrossrefPubMedGoogle Scholar
  • 67 Heitjan DF. Annotation: what can be done about missing data? Approaches to imputation. Am J Public Health 1997; 87 (04) 548-550.
    CrossrefPubMedGoogle Scholar
  • 68 Sterne JA, White IR, Carlin JB, Spratt M, Royston P, Kenward MG. et al. Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls. BMJ 2009; 338: b2393 doi:10.1136/bmj.b2393.
    CrossrefPubMedGoogle Scholar
  • 69 Gorelick MH. Bias arising from missing data in predictive models. J Clin Epidemiol 2006; 59 (10) 1115-1123 doi:10.1016/j.jclinepi.2004.11.029.
    CrossrefPubMedGoogle Scholar
  • 70 Wells BJ, Chagin KM, Nowacki AS, Kattan MW. Strategies for handling missing data in electronic health record derived data. EGEMS (Wash DC) 2013; 01 (03) 1035 doi:10.13063/2327–9214.1035.
    PubMedGoogle Scholar
  • 71 Allison PD. Missing Data. SAGE Publications, Inc; 2001
    Google Scholar
  • 72 Donders ART, van der Heijden GJMG, Stijnen T, Moons KGM. Review: a gentle introduction to imputation of missing values. J Clin Epidemiol 2006; 59: 1087-1091 doi:10.1016/j.jclinepi.2006.01.014.
    CrossrefPubMedGoogle Scholar
  • 73 Cismondi F, Fialho AS, Vieira SM, Reti SR, Sousa JM, Finkelstein SN. Missing data in medical databases: impute, delete or classify?. Artif Intell Med 2013; 58 (01) 63-72 doi:10.1016/j.artmed.2013.01.003.
    CrossrefPubMedGoogle Scholar
  • 74 Jerez JM, Molina I, García-Laencina PJ, Alba E, Ribelles N, Martín M. et al. Missing data imputation using statistical and machine learning methods in a real breast cancer problem. Artif Intell Med 2010; 50 (02) 105-115 doi:10.1016/j.artmed.2010.05.002.
    CrossrefPubMedGoogle Scholar
  • 75 Windle T, McClay JC, Windle JR. The impact of domain knowledge on structured data collection and templated note design. Appl Clin Inform 2013; 04 (03) 317-330 doi:10.4338/ACI-2013–02-CR-0008.
    Article in Thieme ConnectPubMedGoogle Scholar
  • 76 Rosenbloom ST, Stead WW, Denny JC, Giuse D, Lorenzi NM, Brown SH. et al. Generating Clinical Notes for Electronic Health Record Systems. Appl Clin Inform 2010; 01 (03) 232-243 doi:10.4338/ACI-2010–03-RA-0019.
    Article in Thieme ConnectPubMedGoogle Scholar
  • 77 Hoerbst A, Ammenwerth E. Electronic Health Records. A Systematic Review on Quality Requirements. Methods Inf Med 2010; 49 (04) 320-336 doi:10.3414/ME10–01–0038.
    Article in Thieme ConnectPubMedGoogle Scholar
  • 78 Cresswell KM, Bates DW, Sheikh A. Ten key considerations for the successful implementation and adoption of large-scale health information technology. J Am Med Inform Assoc 2013; 20 e1 e9-e13 doi:10.1136/amiajnl-2013–001684.
    CrossrefPubMedGoogle Scholar
  • 79 Walji MF, Kalenderian E, Piotrowski M, Tran D, Kookal KK, Tokede O. et al. Are three methods better than one? A comparative assessment of usability evaluation methods in an EHR. Int J Med Inform 2014; 83 (05) 361-367 doi:10.1016/j.ijmedinf.2014.01.010.
    CrossrefPubMedGoogle Scholar
  • 80 Walji MF, Kalenderian E, Tran D, Kookal KK, Nguyen V, Tokede O. et al. Detection and characterization of usability problems in structured data entry interfaces in dentistry. Int J Med Inform 2013; 82 (02) 128-138.
    CrossrefPubMedGoogle Scholar