Use of artificial intelligence in analytical systems for the clinical laboratory

Abstract

Glostrup/Copehagen, Denmark. segmented flow system started with the auto-analysers of Skeggs [2], that were made commercially available at the end of the 1950s. This process has continued through many phases with the most recent advances being in the area of robotics [3]. Mechanization figure) and the open or stand-alone system (total figure). Metarules are part of the procedural knowledge of expert systems. They are used to evoke programs and to guide the inference process and thus define how to use the rules in the system. They are basic blocks of (usually) IF_THEN rules for exhaustive mapping.The inference engine may make use of one or a number of these problem-solving mechanisms. Problems with expert systemsSince the expert system is built using knowledge from the expert, it may perform more or less like an expert.However, as an expert system does not get tired, it will give more consistent results than its human counterparts. A good expert system may even give better results than human experts performing at their best.

Automated Prozone Effect Detection in Ferritin Homogeneous Immunoassays Using Neural Network Classifiers

“…They were used as an alternative to the traditional multivariate statistical techniques for the analysis of feature extracted parameters (16,18). They were used as an alternative to the traditional multivariate statistical techniques for the analysis of feature extracted parameters (16,18).…”

“…Nowadays, new algorithms are being suggested for medical pattern recognition tasks (14)(15)(16). Beside the algorithm based expert systems, we can now evaluate biological signals with non-linear techniques simulating biological pattern recognition procedures.…”

“…Beside the algorithm based expert systems, we can now evaluate biological signals with non-linear techniques simulating biological pattern recognition procedures. Neural networks have already been used in medical decision support systems in the field of microscopic image analysis (15,18) and also in clinical chemistry (16,19,20). The cardinal advantage of neural networks com-pared to traditional procedures is derived from their operation.…”

Intelligent computer reporting `lack of experience': a confidence measure for decision support systems

“…It has been demonstrated that the best of these interpretation programs perform almost as well as human experts (Willems et al, 1991). Computer-aided decision making has been used in many other applications, for example image interpretation (Scott, 1993;Kahn, 1994), and in the clinical laboratory (Place et al, 1994). The standard methods for classifying clinical data have been knowledge-based systems and statistical methods such as linear discriminant analysis.…”