The main goal driving this work is to develop computer-aided classification models relying on clinical data to identify coronary artery disease (CAD) instances with high accuracy while incorporating the expert’s opinion as input, making it a "man-in-the-loop" approach. CAD is traditionally diagnosed in a definite manner by Invasive Coronary Angiography (ICA). A dataset was created using biometric and clinical data from 571 patients (21 total features, 43% ICA-confirmed CAD instances) along with the expert’s diagnostic yield. Five machine learning classification algorithms were applied to the dataset. For the selection of the best feature set for each algorithm, three different parameter selection algorithms were used. Each ML model’s performance was evaluated using common metrics, and the best resulting feature set for each is presented. A stratified ten-fold validation was used for the performance evaluation. This procedure was run both using the assessments of experts/doctors as input and without them. The significance of this paper lies in its innovative approach of incorporating the expert's opinion as input in the classification process, making it a "man-in-the-loop" approach. This approach not only increases the accuracy of the models but also provides an added layer of explainability and transparency, allowing for greater trust and confidence in the results. Maximum achievable accuracy, sensitivity, and specificity are 83.02%, 90.32%, and 85.49% when using the expert's diagnosis as input, compared to 78.29%, 76.61%, and 86.07% without the expert's diagnosis. The results of this study demonstrate the potential for this approach to improve the diagnosis of CAD and highlight the importance of considering the role of human expertise in the development of computer-aided classification models.
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.
Production line calibration is a critical industrial task that requires thoroughly planned actions. Even tiny deviations from the optimal settings can cause dramatic deficiencies. Automated Root Cause Analysis can be employed to suggest the actions that result in faulty states, and therefore, to resolve situations and prevent recurrence. This work presents a methodology for Root Cause Analysis focused on the calibration process of a valve block in an elevator system. The causalities (weighted interconnections) between oil flow control (actions) and system velocity (output) are estimated using Pearson Correlation. The produced weight matrix is evaluated by exploiting expert knowledge. An FCM model for Root Cause Analysis is developed to study the system behavior and explore the root causes of deficiencies. The proposed approach eliminates the need for labeled root causes. Results support the efficiency of the proposed FCM model for correcting the sub-optimal configurations; the proposed approach seems to work even when the calibration actions are unknown.
The exploration and the implementation of a deep learning method using a state-of-the-art convolutional neural network for the classification of polar maps represent myocardial perfusion for the detection of coronary artery disease.
In the proposed research, the dataset includes stress and rest polar maps in attenuation-corrected (AC) and non-corrected (NAC) format, counting specifically 144 normal and 170 pathological cases. Due to the small number of the dataset, the following methods were implemented: First, transfer learning was conducted using VGG16, which is applied broadly in medical industry. Furthermore, data augmentation was utilized, wherein the images are rotated and flipped for expanding the dataset. Secondly, we evaluated a custom convolutional neural network called RGB CNN, which utilizes fewer parameters and is more lightweight. In addition, we utilized the k-fold validation for evaluating variability and overall performance of the examined model.
Our RGB CNN model achieved an agreement rating of 92.07% with a loss of 0.2519. The transfer learning technique (VGG16) attained 95.83% accuracy.
The proposed model could be an effective tool for medical classification problems, in the case of polar map data acquired from myocardial perfusion images.
The main goal driving this work is to develop computer-aided classification models relying on clinical data to identify coronary artery disease (CAD) instances with high accuracy while incorporating the expert’s opinion as input, making it a "man-in-the-loop" approach. CAD is traditionally diagnosed in a definite manner by Invasive Coronary Angiography (ICA). A dataset was created using biometric and clinical data from 571 patients (21 total features, 43% ICA-confirmed CAD instances) along with the expert’s diagnostic yield. Five machine learning classification algorithms were applied to the dataset. For the selection of the best feature set for each algorithm, three different parameter selection algorithms were used. Each ML model’s performance was evaluated using common metrics, and the best resulting feature set for each is presented. A stratified ten-fold validation was used for the performance evaluation. This procedure was run both using the assessments of experts/doctors as input and without them. The significance of this paper lies in its innovative approach of incorporating the expert's opinion as input in the classification process, making it a "man-in-the-loop" approach. This approach not only increases the accuracy of the models but also provides an added layer of explainability and transparency, allowing for greater trust and confidence in the results. Maximum achievable accuracy, sensitivity, and specificity are 83.02%, 90.32%, and 85.49% when using the expert's diagnosis as input, compared to 78.29%, 76.61%, and 86.07% without the expert's diagnosis. The results of this study demonstrate the potential for this approach to improve the diagnosis of CAD and highlight the importance of considering the role of human expertise in the development of computer-aided classification models.