A Fuzzy Cognitive Map Learning Approach for Coronary Artery Disease Diagnosis in Nuclear Medicine.

Coronary artery disease (CAD) is the primary cause of death and chronic disability among cardiovascular conditions worldwide. Its diagnosis is challenging and cost-effective. In this research work, Fuzzy Cognitive Maps with Particle Swarm Optimization (FCM-PSO) were used for CAD classification (healthy and diseased). In particular, a new DeepFCM framework, which integrates image and clinical data of the patients is proposed. In this context, we employed the FCM-PSO method enhanced by experts’ knowledge, along with an efficient attention Convolutional Neural Network, to improve diagnosis. The proposed method is evaluated using 571 participants and achieved 77.95 ± 5.58% accuracy, 0.22 ± 0.05 loss, 76.98 ± 8.27% sensitivity, 77.39 ± 7.13% specificity, and 73.97 ± 0.09% precision, implementing a 10-fold cross-validation process. The results extracted from the proposed model demonstrate the model’s efficiency and outperform traditional machine learning algorithms. An essential asset of the proposed DeepFCM framework is the explainability, as it offers nuclear physicians’ meaningful causal relationships between clinical factors regarding the diagnosis.