Hostname: page-component-cd9895bd7-gvvz8 Total loading time: 0 Render date: 2024-12-26T08:37:28.027Z Has data issue: false hasContentIssue false
  • English
  • Français

Natural language processing in an operational clinical information system

Published online by Cambridge University Press:  12 September 2008

C. Friedman ,
G. Hripcsak ,
W. DuMouchel ,
S. B. Johnson  and
P. D. Clayton
C. Friedman
Affiliation:
Queens College of the City University of New YorkComputer Science Department Flushing, New York 11367, USADepartment of Medical Informatics, Columbia-Presbyterian Medical Center
G. Hripcsak
Affiliation:
Department of Medical Informatics, Columbia-Presbyterian Medical Center Department of Medicine, Columbia-Presbyterian Medical Center
W. DuMouchel
Affiliation:
Department of Medical Informatics, Columbia-Presbyterian Medical Center Division of Biostatistics, Columbia-Presbyterian Medical Center
S. B. Johnson
Affiliation:
Department of Medical Informatics, Columbia-Presbyterian Medical CenterDepartment of Medicine, Columbia-Presbyterian Medical Center
P. D. Clayton
Affiliation:
Department of Medical Informatics, Columbia-Presbyterian Medical CenterDepartment of Medicine, Columbia-Presbyterian Medical Center
Get access Rights & Permissions [Opens in a new window]

Abstract

This paper describes a natural language text extraction system, called MEDLEE, that has been applied to the medical domain. The system extracts, structures, and encodes clinical information from textual patient reports. It was integrated with the Clinical Information System (CIS), which was developed at Columbia-Presbyterian Medical Center (CPMC) to help improve patient care. MEDLEE is currently used on a daily basis to routinely process radiological reports of patients at CPMC.

In order to describe how the natural language system was made compatible with the existing CIS, this paper will also discuss engineering issues which involve performance, robustness, and accessibility of the data from the end users' viewpoint.

Also described are the three evaluations that have been performed on the system. The first evaluation was useful primarily for further refinement of the system. The two other evaluations involved an actual clinical application which consisted of retrieving reports that were associated with specified diseases. Automated queries were written by a medical expert based on the structured output forms generated as a result of text processing. The retrievals obtained by the automated system were compared to the retrievals obtained by independent medical experts who read the reports manually to determine whether they were associated with the specified diseases. MEDLEE was shown to perform comparably to the experts. The technique used to perform the last two evaluations was found to be a realistic evaluation technique for a natural language processor.

Type
Articles
Information
Natural Language Engineering , Volume 1 , Issue 1 , March 1995 , pp. 83 - 108
Copyright
Copyright © Cambridge University Press 1995

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Baud, R.H., Rassinoux, A-M., and Scherrer, J-R. (1991) Knowledge representation of discharge summaries. In Proceedings of The Third Conference of Artificial Intelligence in Medicine, Mastricht, the Netherlands. Berlin, Heidelberg: Springer-Verlag. Pp. 173–182.Google Scholar
Baud, R.H., Rassinoux, A-M., and Scherrer, J-R. (1992) Natural language processing and medical records. In Lun, K.C. et al. , (eds), Proceedings of MEDINF092. Amsterdam: Elsevier Science Publishers (North-Holland). Pp. 1362–1367.Google Scholar
Bell, D.S., Pattison-Gordon, E. and Greenes, R.A., (1994) Experiments in concept modeling for radiographic image reports. Journal of Medical Informatics Association l(3):249–62.CrossRefGoogle Scholar
Canfield, K., Bray, B., and Huff, S., (1990) Representation and database design for clinical information. In Proceedings of the Fourteenth Annual Symposium on Computer Applications in Medical Care. Los Alamitos, CA: IEEE Computer Society Press. Pp. 350–3.Google Scholar
Campbell, K.E., Das, A.K., and Musen, M.A., (1994) A logical foundation for representation of clinical data. Journal of Medical Informatics Assocation 1(3):218–32.CrossRefGoogle ScholarPubMed
Campbell, K., and Musen, M., (1992) Respresentation of clinical data using SNOMED III and conceptual graphs. In Frisse, M.E. (eds). Proceedings of the Sixteenth Annual Symposium on Computer Applications in Medical Care. New York: McGraw-Hill. Pp. 354–358.Google Scholar
Cimino, J.J., Clayton, P.D., Hripcsak, G., and Johnson, S.B., (1994) Knowledge-based approaches to the maintenance of a large controlled medical terminology. Journal of the American Medical Informatics Association l(l):35–50.CrossRefGoogle Scholar
Evans, D., Chute, C, Cimino, J.J. et al. , (1993) CANON: towards a medical concept representation language for electronic medical records (abstr.). In Kahn, M.G. (ed). Proceedings of the 1993 Spring Congress of the American Medical Informatics Association. Bethesda, MD: American Medical Informatics Association.Google Scholar
Friedman, C, Hripcsak, G., Johnson, S.B., Cimino, J.J., and Clayton, PD., (1990) A generalized relational schema for an integrated clinical patient database. In Proceedings of the Fourteenth Annual Symposium on Computer Applications in Medical Care. Los Alamitos, CA: IEEE Computer Society Press. Pp. 335–9.Google Scholar
Friedman, C, Alderson, P.O., Austin, J., Cimino, J.J., and Johnson, S.B., (1994a) A general natural language text processor for clinical radiology. Journal of American Medical Informatics Association 1(2):161–74.CrossRefGoogle ScholarPubMed
Friedman, C, Cimino, J.J., and Johnson, S.B., (1994b) A schema for representing medical language. Journal of American Medical Informatics Association l(3):233–48.CrossRefGoogle Scholar
Gabrieli, E., and Speth, D., (1987) Computer processing of discharge summaries. In Proceedings of the Eleventh Annual Symposium on Computer Applications in Medical Care. Washington D.C.: IEEE Computer Society Press. Pp. 137–40.Google Scholar
Gell, G., (1982) Free text processing in clinical documentation. Clincal Computing 10(5):170–79.Google ScholarPubMed
Grams, R., and Jin, Z., (1989) The natural language processing of medical databases. Medical Systems 13(2):79–87.CrossRefGoogle ScholarPubMed
Health Level Seven. (1990) Version 2.1.Google Scholar
Hendrickson, G., Anderson, R.K., Clayton, P.D., Cimino, J.J., Hripcsak, G., Johnson, S.B., McCormack, M., Sengupta, S., Shea, S., Sideli, R.V., and Roderer, N., (1992) The integrated academic information system at Columbia-Presbyterian Medical Center. MD Computing 9(l):35–42.Google Scholar
Hobbs, J., (1993) The generic information extraction system. In Sundheim, B. (ed.), Proceedings of the Fifth Message Understanding Conference (MUC-5). San Mateo CA.: Morgan Kaufmann Inc. Pp. 87–91.Google Scholar
Hripcsak, G., Cimino, J.J., Johnson, S.B., and Clayton, P.D., (1992) The Columbia-Presbyterian Medical Center decision-support system as a model for implementing the Arden Syntax. In Clayton, P.D. (ed.), Fifteenth Annual Symposium on Computer Applications in Medical Care. New York: McGraw-Hill, Pp. 248–52.Google Scholar
Hripscak, G., Clayton, P.D., Cimino, J.J., Johnson, S.B., and Friedman, C., (1990) Medical decision support at Columbia-Presbyterian Medical Center. In IMIA Working Conference on Software Engineering in Medical Informatics. Amsterdam, The Netherlands. Pp. 8–10.Google Scholar
Hripcsak, G., Friedman, C, Alderson, P.O., DuMouchel, W, Johnson, S.B., and Clayton, P.D., (1995) Unlocking clinical data from narrative reports. Annals of Internal Medicine 122(9):681–8.CrossRefGoogle Scholar
Huff, S.M., Rocha, R.A., Haug, P.J., Bray, B.E., and Warner, H.R., (1994) An Event Model of Model Information Representation. Technical Report, Latter Day Saints Hospital, Salt Lake City Utah.Google Scholar
Johnson, S.B., Hripcsak, G., Chen, J., and Clayton, P.D., (1994) Accessing the Columbia clinical repository. In Ozbold, J.G. (ed.), Proceedings of the Eighteenth Annual Symposium on Computer Applications in Medical Care. Philadelphia: Hanley and Belfus Inc. Pp. 281–5.Google Scholar
Johnson, S.B., Friedman, C, Cimino, J.J., Clark, A.S., Hripcsak, G., and Clayton, P.D., (1991) A conceptual schema for a central patient database. In Clayton, P.D. (ed.), Proceedings of the Fifteenth Annual Symposium on Computer Applications in Medical Care. Washington D.C., Pp. 381–7.Google Scholar
Lin, R., Lenert, L.A., Middleton, B., and Shiffman, S., (1991) A free-text processing system to capture physical findings: canonical phrase identification system (CAPIS). In Clayton, P.D. (ed.), Proceedings of the Fifteenth Annual Symposium on Computer Applications in Medical Care. New York: McGraw-Hill. Pp. 843–7.Google Scholar
Masarie, F., Miller, R., Bouhaddou, O., Giuse, N., and Warner, H., (1991) An interlingua for electronic interchange of medical information. Computers and Biomedical Research 24:379–400.CrossRefGoogle Scholar
Moore, G.W., Miller, R.E., and Hutchins, G.M., (1989) Indexing by MeSH titles of natural language pathology phrases identified on first encounter using the barrier word method. In Scherrerr, J-R., Cote, R.A., and Mandil, S. (eds.), Computerized Natural Medical Language Processing for Knowledge Representation. Amsterdam, The Netherlands: Elsevier Science. Pp. 29–39.Google Scholar
Pereira, F.C.N., and Warren, D., (1980) Definite clause grammars for language analysis - a survey of the formalism and a comparison with augmented transition networks. Artificial Intelligence 13: 231–278.CrossRefGoogle Scholar
Reprinted in Grosz, B.J., Jones, K. Sparc, and Webber, B.L. (eds.), Readings in Natural Language Processing. Los Altos: Morgan Kaufmann. Pp. 101–124.Google Scholar
Ranum, D., (1988) Knowledge based understanding of radiology text. In Proceedings of the Twelfth Annual Symposium on Computer Applications in Medical Care. Washington, D.C.: IEEE Computer Society Press. Pp. 141–145.Google Scholar
Rector, A.L., Nowlan, W.A., and Kay, S., (1992) Conceptual knowledge: the core of medical information systems. In Lun, K.C., P, DegouletPlemme, T.E., and Rienhoff, O. (eds.), Proceedings of MEDINFO 92. Amsterdam, The Netherlands: North-Holland. Pp. 1420–1426.Google Scholar
Sager, N., Friedman, C., and Lyman, M.S. et al. , (1987) Medical Language Processing: Computer Management of Narrative Data. Reading, MA: Addison-Wesley.Google Scholar
Sager, N., Lyman, M., Bucknall, C., Nhan, N., and Tick, L.J., (1994) Natural language processing and the representation of clinical data. Journal of the American Medical Informatics Association 1(2): 142–160.CrossRefGoogle ScholarPubMed
Sideli, R.V., Johnson, S.B., Weschler, M., Clark, A., Chen, J., Simpson, R., and Chen, C., (1990) Adopting H17 as a standard for the exchange of clinical text reports. In Miller, R.A. (ed.), Proceedings of the 14th Symposium of Computer Applications in Medical Care. Pp. 226–229.Google Scholar
Sowa, J.F., (1984) Conceptual Structures. Reading, MA: Addison-Wesley.Google Scholar
Sundheim, B., (ed.) (1991) Proceedings of the Third Message Understanding Conference (MUC-3). San Mateo, CA: Morgan Kaufmann Inc.Google Scholar
Sundheim, B., (ed.) (1992) Proceedings of the Fourth Message Understanding Conference (MUC-4). San Mateo, CA: Morgan Kaufmann Inc.Google Scholar
Sundheim, B., (ed.) (1993a) Proceedings of the Fifth Message Understanding Conference (MUC-5). San Mateo, CA: Morgan Kaufmann Inc.Google Scholar
Sundheim, B., (1993b) Tipster/MUC-5 information extraction system evaluation. In Sundheim, B. (ed.), Proceedings of the Fifth Message Understanding Conference (MUC-5). San Mateo, CA: Morgan Kaufmann Inc. Pp. 27–44.Google Scholar
Will, C., (1994) Comparing human and machine performance for natural language information evaluation. In Sundheim, B. (ed.), Proceedings of the Fifth Message Understanding Conference (MUC-5). San Mateo, CA: Morgan Kaufmann Inc. Pp. 53–68.Google Scholar
Zingmond, D., and Lenert, L.A., (1993) Monitoring free-text data using medical language processing. Computers and Biomedical Research 26:467–81.CrossRefGoogle ScholarPubMed