Search

The expert system for platelet request evaluation (ESPRE) is being developed to support independent learning and decision making regarding the use of platelet transfusions while physicians are actively engaged in clinical practice. The knowledge of transfusion medicine incorporated in ESPRE has been largely gathered from blood bank physicians responsible for determining the appropriateness of blood product administration. Knowledge acquisition methods have included structured and unstructured interviews with protocol analysis using real and fabricated transfusion cases and critiques of an expert system prototype's conclusions. For knowledge representation, ESPRE uses frames with embedded production rules to provide processing efficiency and facilitate knowledge base development. ESPRE automatically acquires key laboratory findings from a laboratory information system. Systems such as ESPRE require careful evaluation and, if proven effective and accurate, present to laboratorians a new tool for delivering high-quality and individually adapted health care.

The authors investigated the potential of various time series models to aid in the prediction of platelet utilization patterns at the authors' institution. During a seven-week feasibility study, prediction accuracy of time series models was slightly inferior to that of an experienced platelet transfusion coordinator. The models that adjusted for day-of-the-week variability were superior to simpler models in a prospective evaluation over a three-month period. Conversion to a time series model for platelet utilization prediction has resulted in significant savings in personnel costs for management of platelet concentrate inventory in the blood bank. Outdate rates have been lower than those achieved by the platelet transfusion coordinator, with no sacrifice in availability occurring during the evaluation period.

The large cell lymphoma (LCL) that occurs in patients with chronic lymphocytic leukemia (Richter's syndrome) has generally been shown to be of the same light chain type as the original chronic lymphocytic leukemia (CLL). The authors now report on a patient with diffuse well-differentiated lymphocytic lymphoma (WDL) of the kappa light chain type who in the course of his illness first had the blood picture of CLL and then developed malignant lymphoma of large cell ("histiocytic") type, which expressed lambda light chains. Despite an extensive multiparameter investigation, we could not determine with certainty whether the presence of two morphologically and immunologically different lymphomas represented proliferation of two distinctly separate clones or whether it represented clonal evolution of the disease with an alteration in immunoglobulin light chain associated genes. The results of the study, however, suggest that the development of lymphoma with expression of a different immunoglobulin light chain may not necessarily indicate the occurrence of a second primary. This study also illustrates the necessity for sequential lymph node biopsies to document progression of disease in patients with low-grade lymphoproliferative disorders and indicates that the immunologic phenotype of a B-cell neoplasm in a given patient should not be assumed to remain constant.