Abstract
A panel of 14 antibodies (panepithelial antibody Lu-5, anti-keratin-18, anti-keratin-7, Ber-EP4, anti-Leu-M1, HEA-125, anti-carcinoembryonic antigen, anti-blood group-related antigens A, B, H, B72.3, antiplacental alkaline phosphatase, anti-vimentin and BMA-120), which have been evaluated for use in differentiating mesothelioma from lung adenocarcinoma, was applied to a group of 24 suspected mesotheliomas. Using the established qualitative, descriptive criteria derived from monovariate statistical analysis of the tumour control groups (definite mesotheliomas, adenocarcinomas), a definitive allocation was possible in only 25% of suspected cases. We therefore constructed two “expert systems”, based on multivariate discriminant analysis with either the ALLOC 80 program for ordinal data or a newly developed analysis program for binomial data. With these two systems diagnostic allocation of suspected mesotheliomas was improved to 75% and 79%. The use of binomial data (“positive” versus “negative”) in conjunction with the probability-based test system is of particular interest because the primary data are easy to record and the test results have a higher statistical probability.
Similar content being viewed by others
References
Bartels PH, Hiessl H (1989) Expert systems in histopathology. II. Knowledge representation and rule-based systems. Anal Quant Cytol Histol 11:147–153
Bartels PH, Thompson D (1989) Expert systems in histopathology. III. Representation of knowledge as “structured objects”. Anal Quant Cytol Histol 11:367–374
Bartels PH, Weber JE (1989) Expert systems in histopathology. I. Introduction and overview. Anal Quant Cytol Histol 11:1–7
Hermans J, Habbema JDF, Kasanmoentalib TKD, Raatgever JW (1982) A Fortran computer program for multigroup discriminant analysis, based on non-parametric density estimation. Department of Medical Statistics, University of Leiden, The Netherlands
Hufnagl P, Guski H, Wolf G, Wenzelides K, Martin H, Roth K (1989) The PARTICLE expert system for tumor grading by automated image analysis. Anal Quant Cytol Histol 11:440–446
Kolles H, Remberger K (1991) How to build a computer-assisted, diagnosis-finding system. Arch Pathol Lab Med 115:1011–1015
McCaughey WTE et al. (1991) Diagnosis of diffuse malignant mesothelioma: experience of a US/Canadian mesothelioma panel. Mod Pathol 4:342–353
Moch H, Oberholzer M, Dalquen P, Wegmann W, Gudat F (1993) Diagnostic tools for differentiating among pleural mesothelioma and lung adenocarcinoma in paraffin embedded tissue. I. Immunohistochemical findings. Virchows Arch [A] 423:19–27
Oberholzer M, Feichter G, Dalquen P, Ettlin R, Christen R, Buser M (1989) A simple “expert system” for morphometric evaluation of cells in pleural effusions. Pathol Res Pract 185:647–651
Smeulders AWM, Ginneken AM van (1989) An analysis of pathology knowledge and decision making for the development of artificial intelligence-based consulting systems. Anal Quant Cytol Histol 11:154–165
Warnock ML, Stoloff A, Thor A (1988) Differentiation of adenocarcinoma of the lung from mesothelioma. Am J Pathol 133:30–38
Wonnacott TH, Wonnacott RJ (1977) Introductory statistics, 3rd edn. Wiley, New York
Zadeh LA (1989) Knowledge representation in fuzzy logic. IEEE Trans Know Data Eng l:89–100
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Moch, H., Oberholzer, M., Christen, H. et al. Diagnostic tools for differentiating pleural mesothelioma from lung adenocarcinoma in paraffin embedded tissue. Vichows Archiv A Pathol Anat 423, 493–496 (1993). https://doi.org/10.1007/BF01606540
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF01606540