INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Stroke remains a major global health concern, necessitating proactive strategies for risk prediction and prevention. In recent years, deep learning has demonstrated remarkable capabilities in various healthcare applications, including disease risk prediction. In this study, we propose a novel approach for stroke risk prediction leveraging a hybrid deep transfer learning framework. The hybrid framework combines the strengths of deep neural networks and transfer learning to enhance the accuracy and generalization of stroke risk prediction models. We harness the power of convolutional neural networks (CNNs) to automatically extract discriminative features from medical imaging data, such as brain scans and vascular images. Simultaneously, we employ transfer learning techniques to leverage pre-trained models on extensive healthcare datasets, fine-tuning them for stroke risk prediction. Key components of our approach include data preprocessing, feature extraction, model architecture design, and training with a diverse dataset of stroke patients and controls. We employ advanced techniques for handling imbalanced data, ensuring that our model exhibits robust predictive performance. The experimental results demonstrate the efficacy of our hybrid deep transfer learning framework. Our model achieves state-of-the-art accuracy in stroke risk prediction, effectively identifying individuals at high risk. Moreover, the interpretability of the model is enhanced through feature visualization and importance analysis, providing insights into the factors contributing to stroke risk. Our approach holds significant promise for real-world applications, enabling early identification of individuals susceptible to stroke and facilitating targeted intervention and prevention strategies. The hybrid deep transfer learning framework introduced in this study represents a valuable addition to the arsenal of tools available for stroke risk assessment, with potential implications for improving public health and reducing the burden of stroke-related morbidity and mortality.
Keywords:
hybrid deep transfer learning, global health ,convolutional neural networks
Cite Article:
"Stroke Risk prediction with hybrid deep transfer learning framework ", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 11, page no.a300-a312, November-2023, Available :http://www.ijnrd.org/papers/IJNRD2311033.pdf
Downloads:
000118752
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn