An expert system for the classification of serum protein electrophoresis patterns

Background: With the improvement of capillary elec- trophoresis, much progress has been made in terms of sensitivity and automation, but the interpretation of the patterns, actually, depends totally on expert personnel. The aim of this work was to evaluate Neu- rosoft-Sebia, an expert system developed to discrim- inate between regular and anomalous serum protein electrophoresis patterns performed on Capillarys2. Methods: Neurosoft-Sebia, based on six auto-associ- ative neural networks, was trained to create the initial knowledge base. In the tuning phase, 3000 electro- phoretic patterns were performed in three different laboratories, and the discordances between human experts and Neurosoft-Sebia classifications were add- ed to the initial knowledge base. Finally, the perform- ances of Neurosoft-Sebia were evaluated using a benchmark dataset. Results: The initial knowledge base was created with 2685 fractions. In the tuning phase, 241 discordances were found: 56 as regular by Neurosoft-Sebia and anomalous by human experts, and 185 as anomalous by Neurosoft-Sebia and regular by human experts. Sensitivity values were evidenced as the ability of Neurosoft-Sebia in selecting anomalous fractions, with an increase from 66.67% using the initial knowl- edge base to 97.40% using the enriched knowledge base. Conclusions: This work demonstrated how the ability of Neurosoft-Sebia in selecting anomalous pattern was comparable to that of human experts, saving time and providing rapid and standardized interpretations.