POLARS: A pathology on-line logging and reporting system

The errors studied are misspellings and typographical errors made by the physician house staff, surgical pathologists, and secretary/typists of a large teaching hospital. The 6,019 errors studies were encountered in the compilation of a LEXICON now containing 24,135 medical and non-medical terms (including errors) from Tissue Examination Request Forms and Surgical Pathology Reports. An automated error correction algorithm was sought to reduce the tedious task of manual encoding of errors, and eliminate the need for storing errors occupying 24.9% of the LEXICON storage space. The errors were classified into 23 types, and it was found that 84.2% of the errors were in the 11 first order categories.Existing error correction algorithms were analyzed with respect to possible application to our medical sample. Two were selected for experimentation, the Baskin-Selfridge algorithm and SOUNDEX. Results showed that Baskin-Selfridge worked quite well, but was too slow to be applied singularly. SOUNDEX was reasonable in speed, but had too many mismatches to be applied singularly in a non-interactive application. SOUNDEX was modified phonologically and with respect to code length in various ways and some experimental data showed improvements.The optimal design for the medical LEXICON sample appears to be a two-step process. The modified version of SOUNDEX will quickly select the most likely corrections for the error (experimental average is 2.38 choices/error). Then the Baskin-Selfridge will decide which, if any, is the actual correct form of the error. By only considering a very small number of choices, the time required for the Baskin-Selfridge algorithm becomes trivial.On the basis of experimental results, it is estimated that this combination will reduce manual encoding of errors by 60—70% and reduce the storage required for the LEXICON by approximately 15%.

Section: Methodsmentioning

confidence: 99%

“…This paper reports our experience in scanning over one million words from a database constructed for a surgical pathology library. The language processing and retrieval techniques have been reported previously [11,25]. The structure and profile of the LEXICON from which the error words were obtained will be reported separately.…”

Section: Introductionmentioning

confidence: 99%

Correction of Misspellings and Typographical Errors in a Free-Text Medical English Information Storage and Retrieval System

Joseph¹,

Wong²

1979

“…This system is referred to by the acronym of PAIRS (PAthology Information Retrieval System) and the algorithms have been described in a previous publication [8]. For capturing free text and fixed length data without major change of the hospital tissue examination requesting and reporting procedures, PO-LARS (Pathology Online Logging And Reporting System) was implemented in 1973 and is serving a routine patient care function in the University of Illinois Hospital [18]. This paper reports the results of utilization of 12,653 Surgical Pathology Reports from a free text database processed by POLARS-PAIRS.…”

Section: Schlilssel-tvii1•ter: Automatische Verschliisselung Klartexmentioning

confidence: 99%

“…Each segment is divided into sentences, and each sentence generates a single record to be entered into the database. All free text and fixed length information is entered via WYLBUR**), processed by POLARS [18], to output various logs for the pathology department, the official chart copy of the SlU'gical Pathology Report, and disk files suitable for input to PAIRS. PAIRS consists *) The •words )fl'ee text« are synonYlllous with )cI8 [11' text(l divides the text into words and sentences and looks up each work in LEXICON, a computer dictionary; LEXI-CON contains coding to indicate whether a word is »Key«, i. e., a word of meclical interest, and also has the capability of correcting misspellings, replacing a word by its synonym, or adding a related word to the sentence.…”

Section: Explanation Of the Database And Processing Of Datamentioning

confidence: 99%

A Numerically Coded File of Operative Procedures Derived from a Free Text Data Collection System : A Measure of the Accuracy

Scudiero¹,

Wong²

1976

A free text data collection system has been developed at the University of Illinois utilizing single word, syntax free dictionary lookup to process data for retrieval. The source document for the system is the Surgical Pathology Request and Report form. To date 12,653 documents have been entered into the system.The free text data was used to create an IRS (Information Retrieval System) database. A program to interrogate this database has been developed to numerically coded operative procedures. A total of 16,519 procedures records were generated. One and nine tenths percent of the procedures could not be fitted into any procedures category; 6.1% could not be specifically coded, while 92% were coded into specific categories. A system of PL/1 programs has been developed to facilitate manual editing of these records, which can be performed in a reasonable length of time (1 week). This manual check reveals that these 92% were coded with precision = 0.931 and recall = 0.924. Correction of the readily correctable errors could improve these figures to precision = 0.977 and recall = 0.987. Syntax errors were relatively unimportant in the overall coding process, but did introduce significant error in some categories, such as when right-left-bilateral distinction was attempted.The coded file that has been constructed will be used as an input file to a gynecological disease/PAP smear correlation system. The outputs of this system will include retrospective information on the natural history of selected diseases and a patient log providing information to the clinician on patient follow-up.Thus a free text data collection system can be utilized to produce numerically coded files of reasonable accuracy. Further, these files can be used as a source of useful information both for the clinician and for the medical researcher.

“…A sequence of the processes that is flexible enough to meet users' demands also is an important fea• ture. Other factors that lower the threshold of man• machine interface and thus encourage pathologists would include (I) immediate accessibility of the data base [2,4,5,19,20,29], (2) interactive dialogue that permits machine•assisted operation [6,10,14,15,19,20], (3) storage of the essential minimum information, resorting to hand•written documents for details, (4) ease of cor• rection and updating of data, (5) automatic coding capability which eliminates need for coding by hand of diagnostic terms [S,10,16,IS,20,21,2S,30], and (6) workability frOIn the very begiruling without prelinlinary construction of a thesaurus for coding. The speed of data acquisition and the number of records that can be stored are of secondary importance.…”

mentioning

confidence: 99%

Computer-Linked Memorandum of Pathology System (CLIMPS 7909) for Interactive Storage and Analysis of Surgical Pathology Data

Takahashi¹,

Masuda²,

Isiglo³

et al. 1980

A new interactive data base management system for surgical pathology is described which was developed by modification of the previously reported system for autopsy records [23]. As the name implies, it serves as a personal memorandum. Always led by the computer, it is easy to write and read, whenever necessary, without knowledge of programming or data format. The outstanding features are its flexibility of operation and the on-line availability of simple statistical data on some items (diagnoses, topography, histology, age and sex) in response to the specification of search condition so that it provides an opportunity to expand association of ideas during the process of diagnosis and serves as a diagnostic support system. The CLIMPS has been successfully tested with over 770 surgical pathology records. Some problems to be expected in the future are discussed.