SRPNet : stroke risk prediction based on two-level feature selection and deep fusion network
(2024) In Frontiers in Physiology 15.- Abstract
Background: Stroke is one of the major chronic non-communicable diseases (NCDs) with high morbidity, disability and mortality. The key to preventing stroke lies in controlling risk factors. However, screening risk factors and quantifying stroke risk levels remain challenging. Methods: A novel prediction model for stroke risk based on two-level feature selection and deep fusion network (SRPNet) is proposed to solve the problem mentioned above. First, the two-level feature selection method is used to screen comprehensive features related to stroke risk, enabling accurate identification of significant risk factors while eliminating redundant information. Next, the deep fusion network integrating Transformer and fully connected neural... (More)
Background: Stroke is one of the major chronic non-communicable diseases (NCDs) with high morbidity, disability and mortality. The key to preventing stroke lies in controlling risk factors. However, screening risk factors and quantifying stroke risk levels remain challenging. Methods: A novel prediction model for stroke risk based on two-level feature selection and deep fusion network (SRPNet) is proposed to solve the problem mentioned above. First, the two-level feature selection method is used to screen comprehensive features related to stroke risk, enabling accurate identification of significant risk factors while eliminating redundant information. Next, the deep fusion network integrating Transformer and fully connected neural network (FCN) is utilized to establish the risk prediction model SRPNet for stroke patients. Results: We evaluate the performance of the SRPNet using screening data from the China Stroke Data Center (CSDC), and further validate its effectiveness with census data on stroke collected in affiliated hospital of Jining Medical University. The experimental results demonstrate that the SRPNet model selects features closely related to stroke and achieves superior risk prediction performance over benchmark methods. Conclusions: SRPNet can rapidly identify high-quality stroke risk factors, improve the accuracy of stroke prediction, and provide a powerful tool for clinical diagnosis.
(Less)
- author
- Zhang, Daoliang ; Yu, Na ; Yang, Xiaodan ; De Marinis, Yang LU ; Liu, Zhi Ping and Gao, Rui
- organization
- publishing date
- 2024
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- deep fusion network, feature selection, stroke risk factors, stroke risk prediction, transformer
- in
- Frontiers in Physiology
- volume
- 15
- article number
- 1357123
- publisher
- Frontiers Media S. A.
- external identifiers
-
- scopus:85210070124
- pmid:39588269
- ISSN
- 1664-042X
- DOI
- 10.3389/fphys.2024.1357123
- language
- English
- LU publication?
- yes
- id
- b4ccb527-5922-4525-b205-d05127e80649
- date added to LUP
- 2025-01-15 16:53:28
- date last changed
- 2025-07-17 08:00:30
@article{b4ccb527-5922-4525-b205-d05127e80649,
abstract = {{<p>Background: Stroke is one of the major chronic non-communicable diseases (NCDs) with high morbidity, disability and mortality. The key to preventing stroke lies in controlling risk factors. However, screening risk factors and quantifying stroke risk levels remain challenging. Methods: A novel prediction model for stroke risk based on two-level feature selection and deep fusion network (SRPNet) is proposed to solve the problem mentioned above. First, the two-level feature selection method is used to screen comprehensive features related to stroke risk, enabling accurate identification of significant risk factors while eliminating redundant information. Next, the deep fusion network integrating Transformer and fully connected neural network (FCN) is utilized to establish the risk prediction model SRPNet for stroke patients. Results: We evaluate the performance of the SRPNet using screening data from the China Stroke Data Center (CSDC), and further validate its effectiveness with census data on stroke collected in affiliated hospital of Jining Medical University. The experimental results demonstrate that the SRPNet model selects features closely related to stroke and achieves superior risk prediction performance over benchmark methods. Conclusions: SRPNet can rapidly identify high-quality stroke risk factors, improve the accuracy of stroke prediction, and provide a powerful tool for clinical diagnosis.</p>}},
author = {{Zhang, Daoliang and Yu, Na and Yang, Xiaodan and De Marinis, Yang and Liu, Zhi Ping and Gao, Rui}},
issn = {{1664-042X}},
keywords = {{deep fusion network; feature selection; stroke risk factors; stroke risk prediction; transformer}},
language = {{eng}},
publisher = {{Frontiers Media S. A.}},
series = {{Frontiers in Physiology}},
title = {{SRPNet : stroke risk prediction based on two-level feature selection and deep fusion network}},
url = {{http://dx.doi.org/10.3389/fphys.2024.1357123}},
doi = {{10.3389/fphys.2024.1357123}},
volume = {{15}},
year = {{2024}},
}