An Intelligent Clinical Decision Support System for Patient-Specific Predictions to Improve Cervical Intraepithelial Neoplasia Detection

Figure 1

Schematic block diagram of the proposed decision support system. The examinations’ results of each patient are used as inputs to the CDSS. The medical information is transformed to data appropriate for processing by the PNN and the MLP subsystems. According to the value of the Pap test, the transformed data of each case is promoted to the PNN or the MLP subsystem; if Pap test is ASCUS, the data are promoted to the MLP; otherwise they are promoted to the PNN. The output of each network is properly transformed by the data interpretation block to medical information. At the end, the CDSS provides predictions regarding the actual cervical status of each woman. NASBA: nucleic acid sequence based amplification for the identification of E6/E7 mRNA of the HPV types 16, 18, 31, 33, and 45; FLOW: flow cytometric E6/E7 HPV mRNA assay; p16: p16 immunocytochemical examination; ASCUS: atypical squamous cells of unknown significance; PNN: probabilistic neural network; MLP: multilayer perceptron network.