Medical reports contain a great deal of information that characterizes a patient's medical condition. A large percent of this information, however, is unstructured in the form of free text. In this form, the information is difficult to search, sort, analyze, summarize and present. We present a new method of natural language processing which attempts to automatically extract the important concepts from medical free text reports. The sentence parsing algorithm is based on a """"""""field theory"""""""" that is motivated by how a multi-particle system forms attachments as explained in physics. This view of natural language processing attempts to view words as active entities rather than passive data elements. A model for how and why word attachments occur is presented. The model presents explanations in terms of both energy fields that characterize the stability of a word at a given state of the sentence parse and in terms of a signal processing model involving a resonance phenomenon. Our hypotheses are that: 1) the system can extract information from medical reports; 2) the results can be represented in a canonical form with respect to meaning; 3) the system is extendable to many domains of medicine. The testing and evaluation of our system will be performed on reports from the specific domains of radiology. We will explore the adaptability of the NLP system to the domains of pediatric pathology and urology. In addition to technical measures, NLP will be evaluated from the end-user perspective including the selection of appropriate imaging protocols, SNOMED coding, and information retrieval from radiology teaching cases.

Agency
National Institute of Health (NIH)
Institute
National Cancer Institute (NCI)
Type
Research Program Projects (P01)
Project #
5P01CA051198-10
Application #
6430473
Study Section
Subcommittee G - Education (NCI)
Project Start
2001-04-01
Project End
2002-03-31
Budget Start
Budget End
Support Year
10
Fiscal Year
2001
Total Cost
$231,603
Indirect Cost
Name
University of California Los Angeles
Department
Type
DUNS #
119132785
City
Los Angeles
State
CA
Country
United States
Zip Code
90095
Morioka, Craig; Dionisio, John David N; Bui, Alex et al. (2007) StructConsult: structured real-time wet read consultation infrastructure to support patient care. Stud Health Technol Inform 129:429-33
Sinha, Usha; Kangarloo, Hooshang (2002) Image study summarization of MR brain images by automated localization of relevant structures. Ann N Y Acad Sci 980:278-86
Bui, Alex A T; Taira, Ricky K; Dionisio, John David N et al. (2002) Evidence-based radiology: requirements for electronic access. Acad Radiol 9:662-9
Morioka, Craig A; Sinha, Usha; Taira, Ricky et al. (2002) Structured reporting in neuroradiology. Ann N Y Acad Sci 980:259-66
Bui, Aleex A T; Taira, Ricky K; Churchill, Bernard et al. (2002) Integrated visualization of problemcentric urologic patient records. Ann N Y Acad Sci 980:267-77
Dionisio, John David N; Bui, Alexander A T; Johnson, David et al. (2002) Designing a patient education framework via use case analysis. Ann N Y Acad Sci 980:225-35
Son, Roderick Y; Taira, Ricky K; Bui, Alex A T et al. (2002) A context-sensitive methodology for automatic episode creation. Proc AMIA Symp :707-11
Goldin, Jonathan G (2002) Quantitative CT of the lung. Radiol Clin North Am 40:145-62
Bui, Alex A T; Weinger, Gregory S; Barretta, Susan J et al. (2002) An XML Gateway to Patient Data for Medical Research Applications. Ann N Y Acad Sci 980:236-46
Bui, Alex A T; Dionisio, John David N; Morioka, Craig A et al. (2002) DataServer: an infrastructure to support evidence-based radiology. Acad Radiol 9:670-8

Showing the most recent 10 out of 58 publications