Early diagnosis of Alzheimer's is crucial to slow the progression of the disease. In this regard, there are many attempts to detect this disease at the early stages using AI techniques such as deep learning. We have proposed an explainable method to solve the early‐stage detection of Alzheimer's using transfer learning as a well‐known approach when there is not enough data. The employed transfer learning method is a combination of fine‐tuned ResNet‐50 and Inception‐V3 with Soft‐max and SVM classifiers using averaging. Moreover, local interpretable model‐agnostic explanations (LIME) are used to show the explainability of the proposed method. The AUC, accuracy, specificity, and sensitivity on structural MRI data of 100 MCI patients were 0.94, 87%, 92%, and 82%, respectively. Also, the LIME results were subjectively evaluated. The results showed the proposed method outperformed some related works. In addition, LIME technique make model more reliable to identify the parts involved in the patient's brain.

Background: Acute kidney injury (AKI) is a complication that occurs for various reasons after surgery, especially cardiac surgery. This complication can lead to a prolonged treatment process, increased costs, and sometimes death. Prediction of postoperative AKI can help anesthesiologists to implement preventive and early treatment strategies to reduce the risk of AKI. Objectives: This study tries to predict postoperative AKI using interpretable machine learning models. Methods: For this study, the information of 1435 patients was collected from multiple centers. The gathered data are in six categories: demographic characteristics and type of surgery, past medical history (PMH), drug history (DH), laboratory information, anesthesia and surgery information, and postoperative variables. Machine learning methods, including support vector machine (SVM), multilayer perceptron (MLP), decision tree (DT), random forest (RF), logistic regression, XGBoost, and AdaBoost, were used to predict postoperative AKI. Local interpretable model-agnostic explanations (LIME) and the Shapley methods were then leveraged to check the interpretability of models. Results: Comparing the area under the curves (AUCs) obtained for different machine learning models show that the RF and XGBoost methods with values of 0.81 and 0.80 best predict postoperative AKI. The interpretations obtained for the machine learning models show that creatinine (Cr), cardiopulmonary bypass time (CPB time), blood sugar (BS), and albumin (Alb) have the most significant impact on predictions. Conclusions: The treatment team can be informed about the possibility of postoperative AKI before cardiac surgery using machine learning models such as RF and XGBoost and adjust the treatment procedure accordingly. Interpretability of predictions for each patient ensures the validity of obtained predictions.

No abstract

No abstract

No abstract