Data processing: speech signal processing – linguistics – language – Linguistics – Natural language
Reexamination Certificate
1999-08-06
2001-01-30
Thomas, Joseph (Department: 2747)
Data processing: speech signal processing, linguistics, language
Linguistics
Natural language
C707S793000, C707S793000
Reexamination Certificate
active
06182029
ABSTRACT:
STATEMENT REGARDING MATERIAL SUBJECT TO COPYRIGHT
A portion of the disclosure of this patent document contains material which is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of any portion of the patent document, as it appears in any patent granted from the present application or in the Patent and Trademark Office file or records available to the public, but otherwise reserves all copyright rights whatsoever.
A microfiche appendix containing source code utilized in practicing an exemplary embodiment of the invention is included as part of the Specification and is hereinafter referred to as Appendix A. Appendix A includes a total of 5 microfiche and a total of 465 frames.
1. Field of the Invention
This invention relates to the computerized processing of natural-language phrases used in specialized areas of expertise such as medicine, clinical sciences, genomics, etc. More particularly, the present invention is related to the extraction and encoding of information from natural-language text sources such as physician reports and technical and scientific literature.
2. Background of the Invention
Conventional automated methods and systems, in particular in the area of clinical medicine, have been developed for producing standardized, encoded representations of extracted “natural-language” textual data. Such systems are useful for extracting clinical information from examination reports, medical histories, progress notes, and discharge summaries. Further, specialized techniques have been developed for use with different types of pathology, radiology and surgery reports.
Although textual patient documents often provide valuable clinical data, most conventional systems provide textual information that cannot be reliably accessed by automated applications. To enable access to the information, however, medical language processing (MLP) systems have been developed that extract and structure information in patient reports in order to organize and encode the pertinent information appropriately for subsequent clinical applications. See, e.g., N. Sager, M. Lyman, C. Buchnall, N. Nhan and L. Tick, “Natural Language Processing and the Representation of Clinical Data,”
JAMIA,
vol. 1 (2), pp. 142-160 (1994); C. Friedman, P. O. Alderson, J. Austin, J. J. Cimino and S. B. Johnson, “A General Natural Language Text Processor for Clinical Radiology,”
JAMIA,
vol. 1 (2), pp. 161-174 (1994); G. Hripcsak, C. Friedman, P. Alderson, W. DuMouchel, S. Johnson, P. Clayton, “Unlocking Clinical Data From Narrative Reports,” Ann. of Int. Med., vol. 122 (9), pp. 681-688 (1995); P. Haug, D. Ranum, P. Frederick, “Computerized Extraction of Coded Findings from Free-Text Radiologic Report,”
Radiology,
vol. 174, pp. 543-548 (1990); P. Zweigenbaum, B. Bachimont, J. Bouaud, J. Charlet and J. A. Boisvieux, “A Multi-lingual Architecture for Building a Normalized Conceptual Representation from Medical Language,”
Proceedings of the
19
th Annual SCAMC;
pp. 357-361 (1995); R. Baud, A. Rassinoux, J. Scherrer, “Natural Language Processing and Semantical Representation of Medical Texts,” Meth. of Info. Med., vol. 31 (2), pp. 117-125 (1993); and L. Lenert and M. Tovar, “Automated Linkage of Free-Text Descriptions of Patients with a Practice Guideline,”
Proceedings of the
17
th Annual SCAMC
, pp. 274-278 (Ozbolt ed. 1993).
Of particular further interest is a general approach which is based on concepts and techniques described in the following papers: C. Friedman et al., “A Conceptual Model for Clinical Radiology Reports,” In: C. Safran, ed.,
Seventeenth Symposium for Computer Applications in Medical Care,
New York, McGraw-Hill, March 1994, pp. 829-833; C. Friedman et al., “A General Natural-Language Text Processor for Clinical Radiology,”
Journal of the American Medical Informatics Association, Vol.
1 (April 1994), pp. 161-174; C. Friedman et al., “A Schema for Representing Medical Language Applied to Clinical Radiology,”
Journal of the American Medical Informatics Association, Vol.
1 (June 1994), pp. 233-248; C. Friedman et al., “Natural Language Processing in an Operational Clinical Information System,”
Natural Language Engineering, Vol.
1 (March 1995), pp. 83-106.
Despite the advancement of medical and natural language processing systems, conventional systems remain limited to specific areas of expertise (i.e., domains) and can only be used on a limited number of dedicated computing platforms. Examples of such conventional systems include those used for decision support and quality assurance tasks. See, e.g., N. Sager, M. Lyman, C. Buchnall, N. Nhan and L. Tick, “Natural Language Processing and the Representation of Clinical Data,”
JAMIA,
vol. 1 (2), pp. 142-160 (1994); G. Hripcsak, C. Friedman, P. Alderson, W. DuMouchel, S. Johnson, P. Clayton, “Unlocking Clinical Data From Narrative Reports,” Ann. of Int. Med., vol. 122 (9), pp. 681-688 (1995); P. Haug, D. Ranum, P. Frederick, “Computerized Extraction of Coded Findings from Free-Text Radiologic Report,”
Radiology,
vol. 174, pp. 543-548 (1990); and L. Lenert and M. Tovar, “Automated Linkage of Free-text Descriptions of Patients with a Practice Guideline,” Proceedings of the 17th Annual SCAMC, pp. 274-278 (Ozbolt ed. 1993). Other systems automatically generate ICD codes from text to assist in generating billing codes. See, e.g., M. Gundersen, P. Haug, T. Pryor, R. van Bree, S. Koehler, K. Bauer, B. Clemons, “Development and Evaluation of a Computerized Admission Diagnoses Encoding System,”
Computers and Biomedical Research,
vol. 29, pp. 351-372 (1996); and C. Lovis, J. Gaspoz, R. Baud, P. Michel and J. Scherrer, “Natural Language Processing and Clinical Support to Improve the Quality of Reimbursement Claim Databases,”
Proceedings of the
1996
AMIA Fall Annual Symposium,
p. 899 (Henley & Belfus 1996). Although output generated by these systems are structured so that it may be used by different automated applications, conventional systems remain unable to map the structured output directly to corresponding text in the original report. Other systems use comprehensive syntactic and semantic knowledge, and include knowledge about the structure of complete sentences.
Still other systems rely more heavily on semantic and local phrasal information. RECIT, for example, uses syntactical information to recognize the structure of local phrases and interleaves phrase recognition with semantic knowledge in order to assemble semantically relevant groupings and representations. See Zweigenbaum et al., “A Multi-Lingual Architecture for Building a Normalized Conceptual Representation from Medical Language,”
Proceedings of the
19
th Annual SCAMC
, pp. 357-361 (1995). SPRUS, which was initially purely semantically driven, uses semantic information relating to words in a sentence along with expectations about findings, locations and conditions associated with the words. See, e.g., G. Hripcsak et al., Unlocking Clinical Data from Narrative Reports,”
Ann. of Int. Med.,
vol. 122 (9), pp. 681-688 (1995); N. Sager et al., “Medical Language Processing With SGML Display,”
Proceedings of the
1996
AMIA Fall Annual Symposium,
pp. 547-551 (1996). More recent versions of SPRUS have integrated some syntax into the processing. Other MLP systems use methods that are based on pattern matching and keyword searching.
Other conventional systems enrich patient reports by using predefined tags for the purpose of facilitating highlighting, manual review and limited automated retrieval of information. See, e.g., N. Sager et al., “Medical Language Processing With SGML Display,”
Proceedings of the
1996
AMIA Fall Annual Symposium,
pp. 547-551 (1996); P. Zweigenbaum et al., “From Text to Knowledge: A Unifying Document-Oriented View of Analyzed Medical Language,” Workshop on Medical Concept Representation and Natural Language Processing,”
IMIA WG
6, pp. 21-29 (1997). The problem with these approaches, however, is that automated retrieval of documents containing the desired information cannot be performed with sufficient
Baker & Botts LLP
The Trustees of Columbia University in the City of New York
Thomas Joseph
LandOfFree
System and method for language extraction and encoding... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with System and method for language extraction and encoding..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and System and method for language extraction and encoding... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2525480