,
Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation , Guntur, Andhra Pradesh , India
,
Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation , Guntur, Andhra Pradesh , India
,
Department of Computer Science and Engineering, Gokaraju Rangaraju Institute of Engineering and Technology , Hyderabad, Telangana , India
G. Narayanamma Institute of Technology and Science , Hyderabad, Telangana , India
The detection of stroke is vital since any delay in diagnosis may lead to significant disability or the loss of life. The existing predictive models fail to capture stroke symptoms with accuracy because of low complexity, and the ability to be used in the real-time situation in the clinical setting. In the following paper, an AI-based system of early stroke detection is suggested with the help of a hybrid and multimodal approach that will include the optimal selection of features, ensemble modeling, state-of-the-art CNNs, and reinforcement learning. The proposed HBS model is a model that depends on XGBoost, SVM, and random forest methodologies with high sensitivity and specificity of 95% and 92% respectively in predicting stroke. To detect stroke using MRI, Dual-Attention Residual 3D CNN (DA-Res3D-CNN) is proposed, which uses spatial and channel attention, which increase accuracy by 8% when compared to the other algorithms and reaches 94% region detection. Also, Deep Q-Network with Adaptive Memory Replay (DQN-AMR) also enhances adjustments in real time prediction and tailored treatment suggestions and increases model accuracy by 5-10%. The proposed biomedical engineering framework is a computationally effective method to identify a stroke on time, which is vital in the clinical decision-making process and patient outcomes through automated AI-based diagnostic support systems. Such method combination is a major breakthrough in predictive healthcare as it enhances the accuracy of detection, computational efficiency, and clinical flexibility, adding to better patient care.
This is an open access article distributed under the Creative Commons Attribution Non-Commercial License (CC BY-NC) License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
0
The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.