No abstract

Asthmaexpert, an expert system (ES), was produced at the special request of several clinicians in order to better understand the medical decisions made clinical experts in managing an asthmatic patient. We describe and evaluate this knowledge base, focusing mainly on assessment of the severity of asthma. After compiling data from a patient, Asthmaexpert assesses the severity of the disease and identifies the trigger factors involved, suggests any further investigations that may be required, and offers a treatment strategy. Implemented with Nexpert and Hypercard, it runs on a MacIntosh personal computer. The validation stage involved eight clinical experts who provided 20 case report forms (CRF) with their conclusions about management of asthma. The CRF were then programmed into the ES, which provided its own conclusions about the same subjects. Afterward, all the experts evaluated the conclusions given by ES or by their colleagues in a double-blind manner. One hundred twenty-seven CRF were available. The reliability of the experts' opinions was good, with a substantial consensus between them when assessing severity scores (kappa = 0.27 to 0.54). There was no difference in concordance of opinions on severity scores either between the experts who designed the system and ES or between the other experts and ES (weighted kappa = 0.72 and 0.69, respectively). Experts judged that the severity scores given by ES were as good as those proposed by their colleagues, and that the overall conclusions given by ES were as good as or better than those given by their colleagues. The conclusions drawn by ES were given a good rating.(ABSTRACT TRUNCATED AT 250 WORDS)

"Asthmaexpert" was produced at the special request of several clinicians in order to obtain a better understanding of the medical decisions taken by clinical experts in the management of asthmatic patients. In order to assess the severity of asthma, a new score called Artificial Intelligence score (AI score), produced by Asthmaexpert, was compared with three other scores (Aas, Hargreave and Brooks).One hundred patients were enrolled prospectively in the study during their first consultation in the out-patient clinic. Distribution of severity level according to the different scores was studied, and the reliability between AI and other scores was evaluated by Kappa and MacNemar tests. Correlations with functional parameters were performed.The AI score assessed higher levels of severity than the other scores (Kappa=18, 28 and 10% for Aas, Hargreave and Brooks, respectively) with significant MacNemar test in all cases. There was a significant correlation between AI score and forced expiratory volume in one second (FEV1) (r=0.73).These data indicate that the AI score is a severity score which defines higher levels of severity than the chosen scores. Correlations for functional parameters are good. This score appears easy to use for the first consultation of an asthmatic patient.

The characteristics of the group studied here are consistent with the literature. This could be considered as an indirect validation of the expert system. Moreover, patients with possible atopy show intermediate findings for these variables and it is possible to suggest a 'dose-effect' relationship.

No abstract