A Multilayer Residual Dendritic Neural Model for Predicting Stroke Prognosis

IF 3.6 3区计算机科学 Q2 COMPUTER SCIENCE, INFORMATION SYSTEMS

IEEE Access Pub Date : 2025-07-23 DOI:10.1109/ACCESS.2025.3591799

Yuxi Wang;Haochang Jin;Maocheng Cao;Xiong Xiao;Li Wang

引用次数: 0

Abstract

Stroke, caused by occlusion or rupture of cerebral blood vessels, is a leading cause of disability and death globally. Accurate stroke prognosis can enhance clinical decisions and rehabilitation strategies. The dendritic neural model (DNM), inspired by biological neurons, shows strong predictive capability, but struggles with real-world small-scale tabular stroke data. Therefore, an improved residual dendritic neural model (RDNM) is proposed. It contains a series of stacked synaptic and dendritic layers to enhance the power. Residual connections are added between layers to address the vanishing gradient problem. Evaluations using one public and two private stroke prognosis datasets demonstrate that RDNM significantly outperforms original DNM and state-of-the-art deep-learning methods, highlighting its potential for clinical applications. Source code is available at https://github.com/jhc050998/RDNM.

查看原文本刊更多论文

预测脑卒中预后的多层残差树突状神经模型

由脑血管闭塞或破裂引起的中风是全球致残和死亡的主要原因。准确的脑卒中预后可以提高临床决策和康复策略。受生物神经元启发的树突神经模型（DNM）显示出强大的预测能力，但在现实世界的小规模表格中风数据方面存在困难。为此，提出了一种改进的残差树突神经模型。它包含一系列堆叠的突触和树突层来增强功率。为了解决梯度消失的问题，在层与层之间增加了残余连接。使用一个公共和两个私人中风预后数据集的评估表明，RDNM显着优于原始DNM和最先进的深度学习方法，突出了其临床应用潜力。源代码可从https://github.com/jhc050998/RDNM获得。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Access COMPUTER SCIENCE, INFORMATION SYSTEMSENGIN-ENGINEERING, ELECTRICAL & ELECTRONIC

CiteScore

9.80

自引率

7.70%

发文量

6673

审稿时长

6 weeks

期刊介绍： IEEE Access® is a multidisciplinary, open access (OA), applications-oriented, all-electronic archival journal that continuously presents the results of original research or development across all of IEEE''s fields of interest. IEEE Access will publish articles that are of high interest to readers, original, technically correct, and clearly presented. Supported by author publication charges (APC), its hallmarks are a rapid peer review and publication process with open access to all readers. Unlike IEEE''s traditional Transactions or Journals, reviews are "binary", in that reviewers will either Accept or Reject an article in the form it is submitted in order to achieve rapid turnaround. Especially encouraged are submissions on: Multidisciplinary topics, or applications-oriented articles and negative results that do not fit within the scope of IEEE''s traditional journals. Practical articles discussing new experiments or measurement techniques, interesting solutions to engineering. Development of new or improved fabrication or manufacturing techniques. Reviews or survey articles of new or evolving fields oriented to assist others in understanding the new area.