The Protege project has come a long way since Mark Musen first built the Protege meta-tool for knowledge-based systems in 1987. The original tool was a small application, aimed at building knowledge-acquisition tools for a few specialized programs in medical planning. From this initial tool, the Protege system has evolved into a durable, extensible platform for knowledge-based systems development and research. The current version, Protege-2000, can be run on a variety of platforms, supports customized user-interface extensions, incorporates the Open Knowledge-Base Connectivity (OKBC) knowledge model, interacts with standard storage formats such as relational databases, XML, and RDF, and has been used by hundreds of individuals and research groups. In this paper, we follow the evolution of the Protege project through three distinct re-implementations. We describe our overall methodology, our design decisions, and the lessons we have learned over the duration of the project. We believe that our success is one of infrastructure: Protege is a flexible, well-supported, and robust development environment. Using Protege, developers and domain experts can easily build effective knowledge-based systems, and researchers can explore ideas in a variety of knowledge-based domains.

The evolution of Protégé: an environment for knowledge-based systems development

Quality health care rests fundamentally on the achievements of biomedical research. All health outcomes are improved by sound science: health status can be turned around by transplantation when someone's life is in jeopardy due to a diseased organ; social functioning can be improved by shock wave lithotripsy that -leads to faster recovery; and satisfaction can beenhanced when children with moderate or severe asthma receive appropriate anti-inflammatory treatment. To improve the quality of health care that patients actually receive, both biomedical research production and especially its introduction into clinical practice need to be examined.

/pdf/managing-clinical-knowledge-for-health-care-improvement-5432otogqb.pdf

Managing Clinical Knowledge for Health Care Improvement

Purpose: To identify a clinically relevant and available parameter upon which to identify non-small cell lung cancer (NSCLC) patients at risk for pneumonitis when treated with three-dimensional (3D) radiation therapy. Methods and Materials: Between January 1991 and October 1995, 99 patients were treated definitively for inoperable NSCLC. Patients were selected for good performance status (96%) and absence of weight loss (82%). All patients had full 3D treatment planning (including total lung dose–volume histograms [DVHs]) prior to treatment delivery. The total lung DVH parameters were compared with the incidence and grade of pneumonitis after treatment. Results: Univariate analysis revealed the percent of the total lung volume exceeding 20 Gy ( V 20 ), the effective volume ( V eff ) and the total lung volume mean dose, and location of the tumor primary (upper versus lower lobes) to be statistically significant relative to the development of ≥ Grade 2 pneumonitis. Multivariate analysis revealed the V 20 to be the single independent predictor of pneumonitis. Conclusions: The V 20 from the total lung DVH is a useful parameter easily obtained from most 3D treatment planning systems. The V 20 may be useful in comparing competing treatment plans to evaluate the risk of pneumonitis for our individual patient treatment and may also be a useful parameter upon which to stratify patients or prospective dose escalation trials.

Clinical dose-volume histogram analysis for pneumonitis after 3D treatment for non-small cell lung cancer (NSCLC)

A simple algorithm for identifying negated findings and diseases in discharge summaries

A software environment is described, called the computational environment for radiotherapy research (CERR, pronounced "sir"). CERR partially addresses four broad needs in treatment planning research: (a) it provides a convenient and powerful software environment to develop and prototype treatment planning concepts, (b) it serves as a software integration environment to combine treatment planning software written in multiple languages (MATLAB, FORTRAN, C/C++, JAVA, etc.), together with treatment plan information (computed tomography scans, outlined structures, dose distributions, digital films, etc.), (c) it provides the ability to extract treatment plans from disparate planning systems using the widely available AAPM/RTOG archiving mechanism, and (d) it provides a convenient and powerful tool for sharing and reproducing treatment planning research results. The functional components currently being distributed, including source code, include: (1) an import program which converts the widely available AAPM/RTOG treatment planning format into a MATLAB cell-array data object, facilitating manipulation; (2) viewers which display axial, coronal, and sagittal computed tomography images, structure contours, digital films, and isodose lines or dose colorwash, (3) a suite of contouring tools to edit and/or create anatomical structures, (4) dose-volume and dose-surface histogram calculation and display tools, and (5) various predefined commands. CERR allows the user to retrieve any AAPM/RTOG key word information about the treatment plan archive. The code is relatively self-describing, because it relies on MATLAB structure field name definitions based on the AAPM/RTOG standard. New structure field names can be added dynamically or permanently. New components of arbitrary data type can be stored and accessed without disturbing system operation. CERR has been applied to aid research in dose-volume-outcome modeling, Monte Carlo dose calculation, and treatment planning optimization. In summary, CERR provides a powerful, convenient, and common framework which allows researchers to use common patient data sets, and compare and share research results.

CERR: A computational environment for radiotherapy research

The guideline interchange format: a model for representing guidelines.

There is need for encoded data for computerized clinical decision support, but most such data are unavailable as they are in free-text reports. Natural language processing offers one alternative for encoding such data. MedLEE is a natural language processing system which is in routine use for encoding chest radiograph and mammogram reports. In this paper, we study MedLEE's ability to identify mammogram findings suspicious for breast cancer by comparing MedLEE's encoding with a logbook of all suspicious findings maintained by the mammography center. While MedLEE was able to identify all the suspicious findings, it varied in the level of granularity, particularly about the location of the suspicious finding. Thus, natural language processing is a useful technique for encoding mammogram reports in order to detect suspicious findings.

Identification of findings suspicious for breast cancer based on natural language processing of mammogram reports.

Identification of eligible patients from electronically available patient data is a key difficulty in computerizing clinical practice guidelines because a large amount of the relevant data is stored as free text. We have been using MedLEE (Medical Language Extraction and Encoding System), a natural language processing system, to encode the clinical information in all chest radiograph and mammogram reports. This paper describes a retrospective study to determine if MedLEE can identify patients at risk for having tuberculosis (TB) based on their admission chest radiographs. Reports of 171 adult inpatients with culture-positive TB during 1992 and 1993 were manually coded (by a TB specialist) using seven terms suggestive of TB, and were also encoded by MedLEE. Using manual coding as the gold standard, MedLEE agreed on the classification of 152/171 (88.9%) reports--129/142 (90.8%) suspicious for TB and 23/29 (79.3%) not suspicious for TB; and 1072/1197 (89.6%) terms indicative of TB. Analysis showed that most of the discrepancies were caused by MedLEE not finding the location of the infiltrate. By ignoring the location of the infiltrate, the agreement became 157/171 (91.8%) reports and 946/1026 (92.2%) terms. Thus, natural language processing offers a practical alternative for using free-text reports to determine patient eligibility for computerized clinical practice guidelines.

Identification of suspected tuberculosis patients based on natural language processing of chest radiograph reports.

OBJECTIVE To evaluate a clinical guideline and an automated computer protocol for detection and respiratory isolation of tuberculosis (TB) patients. DESIGN An automated computer protocol was tested on a retrospective cohort of adult culture-positive TB patients admitted from 1992 to 1993 to Columbia-Presbyterian Medical Center and evaluated prospectively from July 1995 until July 1996. SETTING A large teaching hospital in New York City. PATIENTS 171 adult patients admitted from 1992 to 1993 and 43 patients admitted between July 1995 and July 1996. INTERVENTIONS The 1990 Centers for Disease Control and Prevention guidelines for preventing transmission of TB were adapted to formulate clinical guidelines to ensure early isolation of TB patients at Columbia-Presbyterian Medical Center. RESULTS Implementation of a clinical respiratory isolation protocol resulted in a significant improvement in TB patient isolation rates, from 45 (51%) of 88 in 1992 to 62 (75%) of 83 in 1993 (P<.001). In testing automated protocols, the theoretical improvement would have identified an additional 27 patients not isolated by clinicians, making the overall isolation rate 134 (78%) of 171. For the prospective evaluation, 30 (70%) of 43 TB patients were isolated by clinicians adhering to the clinical protocol. Four additional patients were identified by the automated TB protocol, making the combined isolation rate 34 (79%) of 43. CONCLUSIONS A clinical policy to isolate TB patients and suspected human immunodeficiency virus-infected patients with cough, fever, or radiographic abnormalities improved isolation of culture-documented TB patients from 1992 to 1993. Automated computer protocols were successful in identifying additional potentially infectious patients that clinicians failed to place on respiratory isolation. Clinical and automated protocols combined resulted in better isolation rates than a clinical protocol alone.

Nilesh L. Jain

Papers

The guideline interchange format: a model for representing guidelines.

Identification of findings suspicious for breast cancer based on natural language processing of mammogram reports.

Identification of suspected tuberculosis patients based on natural language processing of chest radiograph reports.

Respiratory isolation of tuberculosis patients using clinical guidelines and an automated clinical decision support system.

Automated Tuberculosis Detection