Combining glass box and black box evaluations in the identification of heart disease risk factors and their temporal relations from clinical records

Journal of Biomedical Informatics

Volumn 58, Issue , 2015, Pages S133-S142

  Grouin, Cyril ^a   Moriceau, Véronique ^a,b   Zweigenbaum, Pierre ^a  

^a CNRS   (France)

^b UNIVERSITÉ PARIS SACLAY   (France)

Author keywords

Electronic health records; Natural language processing; Program evaluation; Risk factors

Indexed keywords

BUILDING COMPONENTS; COMPUTATIONAL LINGUISTICS; GLASS; NATURAL LANGUAGE PROCESSING SYSTEMS; RISKS; SYNTACTICS;

ELECTRONIC HEALTH RECORD; EVALUATION FRAMEWORK; INDIVIDUAL COMPONENTS; NATURAL LANGUAGE PROCESSING; PROGRAM EVALUATION; RELATIVE PERFORMANCE; RISK FACTORS; TEMPORAL EXPRESSIONS;

HEALTH RISKS;

ARTICLE; CLINICAL EVALUATION; COMPONENT LEVEL EVALUATION; CONCEPTUAL FRAMEWORK; CORONARY ARTERY DISEASE; DIABETES MELLITUS; ELECTRONIC HEALTH RECORD; FAMILY HISTORY; HEART DISEASE; HUMAN; HYPERLIPIDEMIA; HYPERTENSION; NATURAL LANGUAGE PROCESSING; OBESITY; PRIORITY JOURNAL; PROGRAM EVALUATION; RISK ASSESSMENT; RISK FACTOR; SMOKING; SUPPORT VECTOR MACHINE; TASK LEVEL EVALUATION; AGED; ALGORITHM; AUTOMATED PATTERN RECOGNITION; CARDIOVASCULAR DISEASES; COHORT ANALYSIS; COMORBIDITY; COMPUTER SECURITY; CONFIDENTIALITY; CONTROLLED VOCABULARY; DATA MINING; DIABETES COMPLICATIONS; FEMALE; FRANCE; INCIDENCE; LONGITUDINAL STUDY; MALE; MIDDLE AGED; ORGANIZATION AND MANAGEMENT; PROCEDURES; VERBAL COMMUNICATION;

AGED; ALGORITHMS; CARDIOVASCULAR DISEASES; COHORT STUDIES; COMORBIDITY; COMPUTER SECURITY; CONFIDENTIALITY; DATA MINING; DIABETES COMPLICATIONS; ELECTRONIC HEALTH RECORDS; FEMALE; FRANCE; HUMANS; INCIDENCE; LONGITUDINAL STUDIES; MALE; MIDDLE AGED; NARRATION; NATURAL LANGUAGE PROCESSING; PATTERN RECOGNITION, AUTOMATED; RISK ASSESSMENT; VOCABULARY, CONTROLLED;

EID: 84936816696     PISSN: 15320464     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.jbi.2015.06.014     Document Type: Article

References (18)

1. A. Stubbs, Ö. Uzuner, V. Kumar, S. Shaw, Annotation guidelines: risk factors for heart disease in diabetic patients, in: i2b2/UTHealth NLP Challenge, 2014. J. Biomed. Inform. 58S (2015) S78-S91.
2. A. Stubbs, C. Kotfila, H. Xu, Ö. Uzuner, Practical applications for NLP in clinical research: the 2014 i2b2/UTHealth shared tasks, in: Proc of i2b2/UTHealth NLP Challenge, 2014. J. Biomed. Inform. 58S (2015) S1-S5.
3. Uzuner Ö., South B.R., Shen S., DuVall S.L. 2010 i2b2/VA challenge on concepts, assertions, and relations in clinical text. J. Am. Med. Inform. Assoc. 2011, 18:552-556.
4. Sun W., Rumshisky A., Uzuner Ö. Evaluating temporal relations in clinical text: 2012 i2b2 Challenge. J. Am. Med. Inform. Assoc. 2013, 20(5):806-813.
5. Tannier X., Muller P. Evaluating temporal graphs built from texts via transitive reduction. J. Artif. Intell. Res. 2011, 40:375-413.
6. Cai J., Strube M. Evaluation metrics for end-to-end coreference resolution systems. Proceedings of the SIGDIAL 2010 Conference 2010, 28-36. Association for Computational Linguistics, Tokyo, Japan.
7. Uzuner Ö., Bodnari A., Shen S., Forbush T., Pestian J., South B.R. Evaluating the state of the art in coreference resolution for electronic medical records. J. Am. Med. Inform. Assoc. 2012, 19:786-791.
8. Kelly L., Goeuriot L., Leroy G., Suominen H., Schreck T., Mowery D.L., Velupillai S., Chapman W.W., Zuccon G., Palotti J. Overview of the ShARe/CLEF eHealth evaluation lab 2014. Proceedings of the ShARe/CLEF eHealth Evaluation Lab 2014, Springer-Verlag.
9. Stubbs A., Kotfila C., Xu H., Uzuner Ö. Identifying risk factors for heart disease over time: overview of 2014 i2b2/UTHealth shared task Track 2. J. Biomed. Inform. 2015, 58S:S67-S77.
10. J.D. Lafferty, A. McCallum, F.C.N. Pereira, Conditional random fields: probabilistic models for segmenting and labeling sequence data, in: Proc of ICML, Williamstown, MA, 2001, pp. 282-289.
11. T. Lavergne, O. Cappé, F. Yvon, Practical very large scale CRFs, in: Proc of ACL, Uppsala, Sweden, 2010, pp. 504-513.
12. H. Schmid, Probabilistic part-of-speech tagging using decision trees, in: Proc of International Conference on New Methods in Language Processing, Manchester, UK, 1994, pp. 44-49.
13. Strötgen J., Gertz M. Multilingual and cross-domain temporal tagging. Lang. Resour. Eval. 2013, 47(2):269-298. 10.1007/s10579-012-9179-y.
14. T. Hamon, C. Grouin, P. Zweigenbaum, Disease and disorder template filling using rule-based and statistical approaches, in: Working Notes of the ShARe/CLEF eHealth Evaluation Lab, 2014.
15. Q. Chen, H. Li, B. Tang, X. Liu, Z. Liu, S. Liu, W. Wang, Identifying risk factors for heart disease over time-HITSZ's system for track 2 of the 2014 i2b2 NLP challenge, in: Proc of i2b2/UTHealth NLP Challenge, 2014. J. Biomed. Inform. 58S (2015) S158-S163.
16. H. Yang, J. Garibaldi, Automatic extraction of risk factors for heart disease in clinical texts, in: Proc of i2b2/UTHealth NLP Challenge, 2014. J. Biomed. Inform. 58S (2015) S171-S182.
17. M. Torii, J. wei Fan, W. li Yang, T. Lee, M.T. Wiley, D. Zisook, Y. Huang, De-identification and risk factor detection in medical records, in: Proc of i2b2/UTHealth NLP Challenge, 2014. J. Biomed. Inform. 58S (2015) S164-S170.
18. Xu H., Stenner S., Doan S., Johnson K., Waitman L., Denny J. MedEx: a medication information extraction system for clinical narratives. J. Am. Med. Inform. Assoc. 2010, 17(1):19-24.