2006 Scientific Session Abstracts
E-Poster Presentations
Submission Compliance and Guidelines
Copyright Transfer Form (PDF)
Abstract Archive
Automated Annotation of a Novel Virtual Neuropathology Report Database- A Paradigm for Creating Patient-Friendly Reports
Bei Hu1, Tomer Schehori1, Steven S. Silver B.Sc.1,2, Alberto Marchevsky M.D.2, X. Fan M.D.2, William H. Yong M.D.1,2 (wyong@mednet.ucla.edu); 1Department of Pathology, UCLA Medical Center and 2Department of Pathology, Cedars-Sinai Medical Center; UCLA School of Medicine, Los Angeles, CA
Context: Current pathology reports contain diagnostic and descriptive elements that are complex and often unique to the pathology field. Clinicians and patients may not grasp these diagnostic reports. Yet a clear understanding of the diagnoses in the pathology report is crucial in determining the correct choice of therapy. We propose that the standard pathology report can be automatically converted into a second report with annotations appropriate to the reader.
Technology: We have constructed a Visual Basic for Applications (VBA) software program that generates virtual oncologic neuropathology reports. Data elements such as virtual patient names and tumor characteristics pertinent to the standard report are maintained within Microsoft Access and results are output as Microsoft Word files. Annotation of the standard reports is also mediated by VBA routines. Tables containing the desired annotation are linked to data elements of the original standard pathology report.
Design: The virtual database includes the CNS tumor types in the current WHO classification with common tumors proportionate to their incidence as reported by the Central Brain Tumor Registry of the United States 2005-2006 statistical report. Parameters including median age, age range, and locations of each tumor type are delimited and reports are generated in a normal distribution respecting these parameters. The reports are formatted using the College of American Pathologists (CAP) brain and spinal cord cancer protocol. Explanatory comments are linked to the standard data elements of the CAP protocol. A routine adds these comments adjacent to the original data element in an automated fashion.
Results: A database of 11,000 virtual oncologic neuropathology reports has been generated. Standard reports with corresponding annotated reports giving explanations in layman terms are created.
Conclusion: This virtual oncologic neuropathology database is a novel and suitable substrate for experimentation with pathology report formats. The conversion of data elements in the standard pathology report to a reader-appropriate version is technically feasible. While the succinct, standard report may be desirable for experts in the field, expanded or annotated versions of the standard pathology report has potential for improving the clarity of these documents