PubMed HealthSearch

Biomedical subjects

S Quaglini

Publications and source records attributed to S Quaglini.

8 recordsLinked to original sources

GAMEES: a probabilistic environment for expert systems.

This paper describes GAMEES (Graphical Modelling Environment for Expert Systems), an interactive graphical environment for building and processing Belief Networks and Influence Diagrams. We review the existing systems designed for analogous purposes, and, after a brief introduction to Belief Networks and Influence Diagrams, we describe the graphical interface, discuss algorithms for probabilistic inference on these networks and illustrate the current implementation of GAMEES. The system has been designed for being integrated within wider expert systems and actually it is part of the Therapy Advisor module within an expert system for the management of anemic patients.

Algorithms

Relevance of class, molecular weight and isoelectric point in predicting human light chain amyloidogenicity.

The ability to predict the amyloidogenicity of certain light chains may facilitate an earlier diagnosis of AL amyloidosis and, possibly, lead to more effective treatment. Using current methods, available in clinical chemistry laboratories, we assessed the class, the relative molecular mass (Mr) and the isoelectric point of urinary monoclonal light chains from 35 patients with AL amyloidosis (A+) and 51 without amyloidosis (A-). The light chain class (LCC) was lambda in 77% and 45% of A+ and A- patients, respectively. Light chain fragments (LCF) with low Mr (12-18 x 10(3) were detected in the urine of 30/35 A+ patients and in 15/51 A- ones. The mean (SD) isoelectric point (pI) of A+ light chains was 4.8 (1.1) while in A- patients it was 6.2 (1.6). Univariate analysis showed significant differences between the two groups for the three parameters. Discriminant analysis gave a function which allowed a correct allocation of 81% of the cases between the two groups.

Amyloidosis

Relative iron deficiency in hereditary spherocytosis.

Seventy-three patients with hereditary spherocytosis (HS) (58 nonsplenectomized, 15 splenectomized) were studied to evaluate iron status and the adequacy of iron availability for erythropoiesis. Splenectomized patients, who had hemoglobin levels in the normal or upper normal range, had higher levels of serum iron, transferrin saturation, and serum ferritin than normal matched controls and normal zinc protoporphyrin (ZnPP) levels. On the contrary, nonsplenectomized patients presenting with mild to severe anemia had higher red cell ZnPP concentrations than both splenectomized subjects and matched normal controls. ZnPP in nonsplenectomized patients correlated inversely with Hb concentration, mean corpuscular volume (MCV), mean red cell hemoglobin concentration (MCHC), transferrin saturation, and serum iron, and directly with reticulocyte count. At multiple regression analysis only Hb concentration was a significant explanatory variable for high ZnPP. The authors conclude that a number of nonsplenectomized HS patients have relative iron deficiency primarily because of expansion of erythropoiesis caused by anemia.

Adolescent

A performance evaluation of the expert system ANEMIA.

This paper reports the results of an evaluation study of the current level of performance given by ANEMIA, a knowledge-based consultation system addressing the clinical problem of managing anemic patients. ANEMIA was developed on a mainframe using the AI programming scheme EXPERT and then translated into a version running on a personal computer. At present the system is able to provide assistance in the diagnosis and management of 65 disease entities. After extensive local testing of accuracy, completeness, and consistency of the knowledge base included into ANEMIA, we designed a study to evaluate whether the system is able to appropriately mirror also the reasoning of well-known hematologists other than those who provided the knowledge. We were also interested in testing whether there were conflicting opinions among hematologists. Thus, we designed a validation study in which ANEMIA's performance could be compared with that of six hematologists and the interexpert consensus evaluated. ANEMIA's overall performance was judged acceptable in 87% (26/30) of the cases, while expert evaluators agreed with their colleagues in 90% (27/30) of them. A low interexpert consensus was found: considering the ratings given by different hematologists to the same ANEMIA performance, complete agreement occurred only 47% of the time.

Adult

ANEMIA: an expert consultation system.

Anemia is a knowledge-based consultation program for anemic states. It has been built using an artificial intelligence programming scheme, called EXPERT, which was developed at Rutgers University. At present, ANEMIA is able to provide assistance in the diagnosis and management of 64 disease entities. They include iron deficiency anemias, anemias due to chronic disorders, thalassemias, hemolytic anemias, arigenerative anemias, and a few other miscellaneous conditions. ANEMIA was tested against a data base of 220 retrospective and 100 new cases and the overall accuracy in the diagnostic performance was pretty good. Our intent is that ANEMIA ultimately will be able to serve as surrogate for the hematologist with the nonhematologist physician-user.

Anemia

Classification of anaemia on the basis of ferrokinetic parameters.

Quantitative information on abnormalities of erythropoiesis and mechanisms of anaemia has been obtained in 136 anaemic patients by means of ferrokinetic studies. To derive a functional classification of anaemia based on ferrokinetic parameters, agglomerative hierarchical cluster analysis and principal coordinate analysis were utilized as techniques for unsupervised classification. Two main clusters were found and named anaemia with low potential erythropoiesis and with high potential erythropoiesis, since the most discriminant parameter between them was total erythroid iron turnover, a measure of total erythropoietic activity. A value of total erythropoiesis equal to 4 times the normal was found to discriminate these two types of anaemia in 94% of cases. Within the group with low potential erythropoiesis, three clusters showing different qualitative disturbances of erythropoiesis were singled out. Among patients with high potential erythropoiesis, two clusters were found. A value of effective erythropoiesis equal to 2.5 times the normal was shown to have a high discriminant power between these clusters. This threshold level distinguished between patients having ineffective erythropoiesis or peripheral haemolysis as the major mechanism of anaemia. The present functional classification of anaemia provides a complete picture of the different pathogenetic mechanisms and may represent the basis for a more rational diagnostic approach to erythroid disorders.

Adolescent