An expert system for the interpretation of full blood counts and blood smears in a hematology laboratory

Tolmie, Carmien; Plessis, J. P. du; Badenhorst, P. N.

doi:10.1016/0933-3657(91)90032-7

Cited by 3 publications

(2 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Along with review of the peripheral blood smear, analysis of the hemogram findings should lead to a working diagnosis in patients with hematologic disease. Several expert systems have already been designed based primarily on interpretation of hemogram data [1][2][3][4][5][6]. Although these systems have been shown to be reasonably accurate in the classification of anemia, thus demonstrating the feasibility of designing an expert system for the domain of hematology, a large-scale high-performance decision support system for hematology diagnosis has yet to be attained.…”

Section: Discussionmentioning

confidence: 99%

“…A number of computerized decision-support programs (expert systems) have been developed to aid in the interpretation of hemogram findings, with particular reference to the diagnosis of anemia [1][2][3][4][5][6]. A variety of inference processes and problemsolving strategies have been tried including Bayesian probability [1], statistical pattern recognition [2], multivariate statistical analysis [3], and rule-based production systems [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Expert System Design in Hematology Diagnosis

Nguyen

Diamond²,

Priolet³

et al. 1992

Methods Inf Med

View full text Add to dashboard Cite

Abstract:A two-part study was designed to test the hypothesis that sufficient information is available from a modern hematology analyzer (the Coulter STKS) to reach a reliable intermediate conclusion which can be used as input to the next decision-making level in the design of a high-performance expert system for hematology diagnosis. In phase one, we analyzed the performance of three probabilistic systems (using Bayes’ rule) which interpret STKS data: a control system which took the traditional approach of classifying cases into specific diagnoses, and two test systems which were designed to reach only an intermediate conclusion but not a final diagnosis. One of the test systems classified cases into “textbook categories” of disease and the other utilized defined diagnostic patterns. The systems were tested with 150 cases. The pattern approach ranked the correct choice first in 141 of 150 cases (94%). In phase two, we abandoned Bayes’ rule, reformulated the pattern approach into a heuristic classification system, and tested its reliability on 820 cases. The algorithm of the reformulated system was able to classify all 820 cases into the same predominant pattern as a panel of three experienced laboratory hematologists.

show abstract

Section: Discussionmentioning

confidence: 99%