Title: An online decision support system for diagnosing hematologic malignancies by flow cytometry immunophenotyping

Authors: You-Wen Qian, Dinesh P. Mital, Stephen Lee

Addresses: Department of Pathology and Laboratory Medicine, Division of Hematopathology, UMDNJ-Robert Wood Johnson Medical School, One Robert Wood Johnson Place, New Brunswick, NJ 08903, USA. ' Department of Health Informatics, University of Medicine and Dentistry in New Jersey-SHRP, 65 Bergen Street, Newark, NJ 07107, USA. ' Department of Pathology and Laboratory Medicine, Section of Hematopathology, Cedars-Sinai Medical Center, 8700 Beverly Blvd, Room 4711, Los Angeles, CA 90048, USA

Abstract: A knowledge-based decision support system to interpret online flow cytometry results for hematologic malignacies has been developed in this study as a complete client-server application. The list mode data files are loaded to the system where gating, dot plot, histogram and contour plot have been performed. Upon gating, the CD marker results are generated as a percentage with associated positive or negative designation. Differential diagnosis with different confidence levels is generated based on a semantic network of knowledge base embedded in an extensible mark up language (XML). Java programming is used to implement the inference engine where tree structure and search algorithm are employed. A set of 273 flow cytometry list mode data files are fed into the system and diagnosis was correctly included in top three differential diagnoses in 94% of all cases tested.

Keywords: clinical DSS; decision support systems; online DSS; flow cytometry; CD markers; hematologic disease; client-server technology; list mode; knowledge base; immunophenotyping; hematologic malignancies; semantic networks; XML; medical informatics.

DOI: 10.1504/IJMEI.2008.019474

International Journal of Medical Engineering and Informatics, 2008 Vol.1 No.1, pp.109 - 124

Published online: 13 Jul 2008 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article