Medical language processing applied to extract clinical information from Dutch medical documents.

In this paper, we want to show how an existing morpho-syntactic analyser for Dutch (Dutch Medical Language Processor--DMLP) has been extended in order to produce output that is compatible with the language independent modules of the LSP-MLP system (Linguistic String Project--Medical Language Processor) of the New York University. The former can focus on idiosyncrasies for Dutch and take advantage of the language independent developments of the latter. This general strategy will be illustrated by a practical application, namely the extraction of clinical information from Dutch patient discharge summaries. Such an application can be of use for education, research and quality control purposes in a hospital environment.

Medical language processing with SGML display.

The paper demonstrates several ways that medical language processing can be combined with emerging display technologies to facilitate the extraction of data from free-text patient documents. The techniques allow rapid review via highlighting of the results of processing. Coupling of text markup with further procedures is envisioned.

Medical language processing: applications to patient data representation and automatic encoding.

A linguistic approach is presented to develop a representation of patient data. Semantic categories developed for computer processing of narrative clinical reports are shown to be similar to the Medical Concepts used manually to extract data from narrative in Exercises of the Computer-based Patient Record Institute. Clinical statement types composed of these categories are used in the Linguistic String Project (LSP) medical language processing (MLP) system to convert narrative information into relational database tables of patient information. A procedure for mapping the output of the LSP MLP system into SNOMED International codes was developed. Preliminary results and further requirements are discussed.

Natural language processing and the representation of clinical data.

OBJECTIVE: Develop a representation of clinical observations and actions and a method of processing free-text patient documents to facilitate applications such as quality assurance. DESIGN: The Linguistic String Project (LSP) system of New York University utilizes syntactic analysis, augmented by a sublanguage grammar and an information structure that are specific to the clinical narrative, to map free-text documents into a database for querying. MEASUREMENTS: Information precision (I-P) and information recall (I-R) were measured for queries for the presence of 13 asthma-health-care quality assurance criteria in a database generated from 59 discharge letters. RESULTS: I-P, using counts of major errors only, was 95.7% for the 28-letter training set and 98.6% for the 31-letter test set. I-R, using counts of major omissions only, was 93.9% for the training set and 92.5% for the test set.

Automatic encoding into SNOMED III: a preliminary investigation.

The Linguistic String Project (LSP) medical language processing (MLP) system converts narrative clinical reports into database tables of patient data. A procedure for mapping the output of the LSP MLP system into SNOMED III codes was developed. Preliminary results and further requirements are discussed.

Natural language processing of asthma discharge summaries for the monitoring of patient care.

A technique for monitoring healthcare via the processing of routinely collected narrative documentation is presented. A checklist of important details of asthma management in use in the Glasgow Royal Infirmary (GRI) was translated into SQL queries and applied to a database of 59 GRI discharge summaries analyzed by the New York University Linguistic String Project medical language processor. Tables of retrieved information obtained for each query were compared with the text of the original documents by physician reviewers. Categories (unit = document) were: (1) information present, retrieved correctly; (2) information not present; (3) information present, retrieved with minor or major error; (4) information present, retrieved with minor or major omissions. Category 2 (physician "documentation score") could be used to prioritize manual review and guide feedback to physicians to improve documentation. The semantic structuring and relative completeness of retrieved data suggest their potential use as input to further quality assurance procedures.

House dust mite-specific T cells in the skin of subjects with atopic dermatitis: frequency and lymphokine profile in the allergen patch test.

The mechanism underlying positive patch tests with house dust mite-allergen, Dermatophagoides pteronyssinus (Der p), in patients with atopic dermatitis was investigated by isolating T cells from the test sites of two patients. Eighty-five T cell clones (TCC) were established from the epidermis and dermis of lesional skin by the limiting-dilution method with Der p and interleukin (IL)-2. With restimulation assays, 29 of 60 TCCs tested demonstrated specific proliferation; 85% were of the CD3+, CD2+, and CD4+ phenotype. Der p-specific T cells constituted 0.4% to 2.7% of lesional T cells, and they were more frequent in the skin than in the blood of the patients by one order of magnitude. The mitogen-stimulated lymphokine profile of 55 TCCs was assessed; 42% (11/26) of the allergen-specific TCCs secreted IL-4 but almost no interferon-gamma, as described for the Th2 subset of the mouse. Also, six selected TCCs supported IgE secretion by autologous lymphocytes. Only three of 26 allergen-specific, skin-derived TCCs demonstrated a Th1-like lymphokine profile. These results support the specific nature of Der p-induced patch test lesions in patients with atopic dermatitis, and the results demonstrate also that a considerable proportion of lesional T cells are allergen-specific, IL-4-producing T cells that are capable of enhancing IgE production.

The application of natural-language processing to healthcare quality assessment.

This paper describes the automatic extraction of information from hospital discharge letters. The computer analysis and extraction process, designed to eliminate much of the manual effort required to review patient documents, are presented.

TEXTINFO: a tool for automatic determination of patient clinical profiles using text analysis.

The clinical data contained in narrative patient documents is made available via grammatical and semantic processing. Retrievals from the resulting relational database tables are matched against a set of clinical descriptors to obtain clinical profiles of the patients in terms of the descriptors present in the documents. Discharge summaries of 57 Dept. of Digestive Surgery patients were processed in this manner. Factor analysis and discriminant analysis procedures were then applied, showing the profiles to be useful for diagnosis definitions (by establishing relations between diagnoses and clinical findings), for diagnosis assessment (by viewing the match between a definition and observed events recorded in a patient text), and potentially for outcome evaluation based on the classification abilities of clinical signs.

Automatic encoding of clinical narrative.

An experiment in the automatic encoding of English-language medical data is described. The encoding program has two stages. First, the free-text input is parsed and the information is arranged in a tabular format by a general-purpose natural language processor developed at New York University. Then a simple code-dependent subprogram assigns numerical values to the entries on the basis of the positions the input words occupy in the information format. Results of a blind test of the encoding program using the code employed at Roswell Park Memorial Institute for earliest symptoms of head-neck cancer are presented.

Quantitative determination endogenous acid phosphatase activity in vaginal washings.

Vaginal washings obtained in 98 patients were analyzed for acid phosphatase activity. A history of recent sexual intercourse was also obtained. Acid phosphatase values of less than 50 IU (obtained by the alpha naphthol phosphate method) correlated with abstinence from sexual intercourse for more than 30 hours, whereas values greater than 50 IU correlated with sexual intercourse in a period up to and including 30 hours (P less than 0.05). The presence or absence of sperm was found to correlate poorly with the time since intercourse.