Alzheimer’s disease prediction using CAdam optimized reinforcement learning-based deep convolutional neural network model

• Published in: Biomedical signal processing and control Vol. 108; p. 107968
• Main Authors: Chaudhari, Puja A., Khot, Suhas S.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.10.2025
• Subjects: Alzheimer prediction; CAdam optimizer; Deep Convolutional neural network; Magnetic Resonance Imaging; Reinforcement learning; Magnetic Resonance Imaging; CAdam optimizer; Alzheimer prediction; Reinforcement learning; Deep Convolutional neural network
• ISSN: 1746-8094
• DOI: 10.1016/j.bspc.2025.107968

Alzheimer’s Disease (AD), a neurological disorder, gradually declines cognitive ability, but detecting it at an early stage can effectively mitigate symptoms. Due to the shortage of expertise medical staff, automatic diagnosis becomes highly important, however, a detailed analysis of brain disorder tissues is required for accurate diagnosis using magnetic resonance imaging (MRI). Various detection methods are introduced to detect AD through MRI, but extracting the optimal brain regions and informative features is still a complicated and time-consuming factor. Moreover, the class imbalance issue of the OASIS and ADNI datasets needs to be addressed. Here, a Coyote Adam optimized Reinforcement Learning-Deep Convolutional Neural Network (CAdam-RL-DCNN) is proposed to address the aforementioned issues on AD detection using MRI. The effectiveness of the proposed method relies on effectively detecting the features automatically and SMOTE handles the class imbalance issues of the dataset through the minority samples. The computational complexity of the model is reduced through the appropriate model training using the proposed CAdam optimizer, which incorporates adaptive parameters of Adam using social behaviors and invasive hunting of coyote optimizer. In addition, the hybrid features combining the ResNet features, statistical features and modified textural pattern reduces the data complexity and promotes the model training towards an improved performance in AD prediction. The proposed model attains 96.31% accuracy, 97.50% sensitivity, 94.06% specificity, 93.87% precision, 97.50% recall, and 95.65% F1-score using ADNI dataset. Furthermore, the proposed model attains the superior performance achieving 95.09% accuracy, 94.52% sensitivity, 95.57% specificity, 93.14% precision, 94.52% recall, and 93.83% F1-score using OASIS dataset respectively.