This research focused on the design of a decision-support system to assist blood bankers in identifying alloantibodies in patients' blood. It was hypothesized that critiquing, a technique in which a computer monitors human performance for errors, would be an effective role for such a decision-support system if the error monitoring was unobtrusive and if the critiquing was in response to both intermediate and final conclusions made by the user. A prototype critiquing system monitored medical technologists for (a) errors of commission and errors of omission, b) failure to follow a complete protocol, (c) answers inconsistent with the data collected, and (d) answers inconsistent with prior probability information. Participants using the critiquing system had significantly better performance (completely eliminating misdiagnosis rates for 3 out of 4 test cases) than a comparable control group. Detailed analysis of the behavioral protocols provided insights into how specific design features influenced performance. Practical applications of this research include its use (after refinements) as a tool for routine antibody identification in blood banks.
We describe a software module in an expert system RED, which interprets data related to red cell antibody identification. There are three portions to this module: the problem-solving component, which incorporates the knowledge required for antibody identification as a hierarchy of programs. The programs in the hierarchy organize within themselves small pieces of knowledge represented in the form of production rules, which are capable of making judgments concerning a specific hypothesis; an intelligent data base for storage of patient data, red cell attributes, and test results; the "overview critic" portion, which combines the atomic hypotheses judged favorably by the antibody programs into a unified judgment concerning the case. Overview makes the decision to terminate processing with a conclusion about which antibodies are actually present and what specific further tests need to be performed to resolve any remaining ambiguities.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.