An artificial intelligent network model to monitor the condition of a patient with a breast tumor based on fuzzy logic.

Purpose: This article introduces an intelligent network for monitoring breast cancer patients. The increase in the network's speed for monitoring the patient depends on the extracted information from the nodes, information rate, network topology, type of data, and the analysis method used for processing this information. The extracted information from the network determines the patient monitoring rate, and the network infrastructure is designed in a way that reports the patient's information in real-time, moment by moment. The decision-making model is based on the OODA cycle, which includes the stages of "Observe," where information is extracted from the network, "Orient," "Decide," and "Act." The stages of "Analyze," "Decide," and "Act" are based on the Fuzzy Analytic Hierarchy Process (FAHP) model. Methods: In this paper, three algorithms, namely, Fuzzy Analytic Hierarchy Process (FAHP), Fuzzy Analytic Hierarchy Process (FAHP), and one-way analysis of variance (ANOVA), have been used to evaluate the "Analysis" and "Decision" stages. These three algorithms are compared with each other using the criteria of Accuracy, Specificity, and Sensitivity. Furthermore, the intelligent network is evaluated based on its network topology, data, and decision-making speed. Results: The simulation results demonstrate that the Fuzzy Analytic Hierarchy Process (FAHP) method exhibits a significantly higher level of accuracy compared to the other methods. The simulation results indicate that the accuracy and speed of the intelligent network monitoring have improved by approximately 9.8 compared to other non-intelligent networks (OODA loop). Conclusions: In this article, an intelligent network is proposed for monitoring breast cancer patients. The intelligent network has an OODA loop for monitoring and controlling the patient. The OODA loop includes observation, analysis, decision, and action, making it a continuous and ever-changing process. In order to expand the OODA loop for better control and monitoring of the patient, we have extended the "observation" and "orientation" phases of the process.The observation method is determined based on the type of data and the network structure. Another method is the directionality, which is determined based on the hierarchical fuzzy analysis. Indeed, the intelligence of the network aims to adjust the decision-making criteria analysis in a way that maximizes the speed of diagnosing the patient with minimal time. [ABSTRACT FROM AUTHOR]