Title: Proposed an effective DeepstrokeNet system for forecasting the early ischemic brain stroke

Authors: Durga Devi P; K. Akila

Addresses: Department of Computer Science and Engineering, SRM Institute of Science and Technology, Vadapalani, Chennai, Tamil Nadu 600026, India ' Department of Computer Science and Engineering, SRM Institute of Science and Technology, Vadapalani, Chennai, Tamil Nadu 600026, India

Abstract: A new method named deep stroke net has been created to improve performance using advanced deep learning techniques across different types of data. DeepstrokeNet's main innovation is its architecture, integrating cutting-edge deep learning methods specifically designed for analysing various types of data. The model uses advanced neural network structures like recurrent neural networks (RNNs) and convolutional neural networks (CNNs) and attention mechanisms to identify key characteristics. This enables the model to identify subtle biomarkers and indicators of early ischemic brain stroke that might be missed by traditional diagnostic methods. The model aims to explain the rationale behind its predictions, helping medical professionals understand how it reaches its conclusions. Transparency is essential in establishing hope and encourages collaboration among human experts and the artificial intelligence (AI) system. As research in this domain continues to evolve, DeepstrokeNet's innovative approach contributes to the ongoing pursuit of accurate and timely ischemic stroke prediction.

Keywords: deep learning; ischemic brain stroke; convolutional neural networks; CNNs; recurrent neural networks; RNNs; state-of-the-art; AI system.

DOI: 10.1504/IJIIDS.2026.150441

International Journal of Intelligent Information and Database Systems, 2026 Vol.18 No.1, pp.126 - 152

Received: 12 Apr 2024
Accepted: 02 Dec 2024
Published online: 13 Dec 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article