Biomedical subjects

A H Seal

Publications and source records attributed to A H Seal.

4 recordsLinked to original sources

PubMed1994

A clinical database as a component of a diagnostic hematology workstation.

A clinical database was designed as part of a comprehensive workstation for diagnostic laboratory hematology. The database stores coded findings pertinent to hematologic disorders including inherited abnormalities, previous surgery, malignancies, current therapy, and laboratory test results. The workstation includes knowledge-based systems for peripheral blood analysis, flow cytometry studies, and bone marrow morphology. The peripheral blood system renders an interpretive report based on data from a complete blood count with manual review of a blood smear by a technologist. The flow cytometry module interprets the immunophenotyping and DNA content results, and correlates them with the clinical findings and the peripheral blood data. The bone marrow system bases its report on all of the available information including the morphologic review of the bone marrow specimen by a physician, the peripheral blood data, immunophenotype, and clinical/laboratory findings. Before generating an interpretive report, each of the knowledge-based systems automatically searches the clinical database for specific information pertinent to the findings in the case. Since the workstation must function in situations where access to distributed databases is not feasible or not yet practical, a data entry module with a graphical user interface has been created.

Artificial Intelligence↗

PubMedDate not supplied

Multiparameter interpretative reporting in diagnostic laboratory hematology.

Accurate diagnosis and classification of hematologic malignancies (acute leukemias and chronic lymphoproliferative disorders) requires a multiparameter approach including peripheral blood analysis, bone marrow examination, and immunophenotyping. We have designed knowledge-based computer systems for interpretation of the hemogram and peripheral blood smears, analysis of flow cytometric immunophenotyping panels, and morphologic assessment of bone marrow specimens. The 3 modules share a relational database which includes pertinent clinical history in addition to the laboratory results. The bone marrow module automatically writes a complete interpretative report with a final diagnosis by searching all of the databases for appropriate clinical, peripheral blood, and immunophenotyping information. The ability of the 3 modules to interact, and the quality of the interpretative reports were tested on 100 consecutive patients with leukemia. The final diagnosis made by the bone marrow system agreed with the hospital diagnosis in 94 cases and the authors' interpretation in 99 of 100 cases.

Artificial Intelligence↗

PubMedDate not supplied

Multiparameter case studies using knowledge-based systems in hematology.

Knowledge-based systems in diagnostic medicine are often used for teaching medical decision making. We have extended the educational value of our suite of hematology decision support systems (peripheral blood analysis, flow cytometry immunophenotyping and DNA analysis, and bone marrow morphology) by creating case studies in a hypertext format. The case studies use the knowledge-based system screens as a background. Digitized images of blood and bone marrow smears from the teaching cases can be accessed on-line. The case studies, which are designed primarily for technologists and physicians, emphasize the proper multiparameter approach to hematopathology diagnosis.

Decision Support Techniques↗

PubMedDate not supplied

Are normative expert systems appropriate for diagnostic pathology?

Conceptual models for diagnostic reasoning proposed in the medical literature are presented to stimulate discussion about the issue of the appropriateness of probabilistic knowledge-based systems for medical diagnosis. Evidence is presented to corroborate the authors' view that diagnosis is a problem-solving task, rather than a decision-making task. In the authors' opinion, probabilistic reasoning is better suited to situations dealing with choices for clinical intervention, rather than to those dealing with determining the correct diagnosis. A critique is given of a diagnostic Bayesian expert system for lymph node pathology. In empirical studies, diagnostic Bayesian systems have been shown to typically list the correct diagnosis as the program's first choice 60% to 70% of the time. One reason for this undistinguished level of diagnostic performance is that Bayesian systems are not designed to represent and use knowledge the same way that an expert does.

Bayes Theorem↗