基于Outlier-SMOTE和果蝇优化支持向量机的颅内动脉瘤破裂风险预测模型

陈广新; 才莹; 郭金兴

doi:10.3969/j.issn.2096-6091.2024.02.002

您当前的位置：

首页 >

文章列表页 >

基于Outlier-SMOTE和果蝇优化支持向量机的颅内动脉瘤破裂风险预测模型

研究论文 | 更新时间：2025-04-02

- 基于Outlier-SMOTE和果蝇优化支持向量机的颅内动脉瘤破裂风险预测模型
- Intracranial Aneurysm Rupture Risk Prediction Model Based on Outlier-SMOTE and Fruit Fly Optimization Support Vector Machine
- 新一代信息技术 2024年7卷第2期页码：8-12
- 作者机构：
  
  1.牡丹江医科大学，黑龙江牡丹江 157011
  2.牡丹江医科大学附属红旗医院，黑龙江牡丹江 157011
- 作者简介：
  
  陈广新（1978—），男，讲师，硕士。研究方向：医学人工智能。
  才莹（1996—），女，主治医师，研士。研究方向：医学人工智能。
  郭金兴（1984—），女，主管护师。研究方向：医学人工智能。E-mail： 44642581@126.com
- 基金信息：
  
  黑龙江省省属高校科研基本业务费科研项目(2020-KYYWF-0795)
- DOI：10.3969/j.issn.2096-6091.2024.02.002
  中图分类号： TP181
- 纸质出版日期：2024-02-25
- 稿件说明：
移动端阅览
陈广新, 才莹, 郭金兴. 基于Outlier-SMOTE和果蝇优化支持向量机的颅内动脉瘤破裂风险预测模型[J]. 新一代信息技术, 2024, 7(2): 08-12

CHEN Guang-xin, CAI Ying, GUO Jin-xing. Intracranial Aneurysm Rupture Risk Prediction Model Based on Outlier-SMOTE and Fruit Fly Optimization Support Vector Machine[J]. New Generation of Information Technology, 2024, 7(2): 08-12
陈广新, 才莹, 郭金兴. 基于Outlier-SMOTE和果蝇优化支持向量机的颅内动脉瘤破裂风险预测模型[J]. 新一代信息技术, 2024, 7(2): 08-12 DOI： 10.3969/j.issn.2096-6091.2024.02.002.

CHEN Guang-xin, CAI Ying, GUO Jin-xing. Intracranial Aneurysm Rupture Risk Prediction Model Based on Outlier-SMOTE and Fruit Fly Optimization Support Vector Machine[J]. New Generation of Information Technology, 2024, 7(2): 08-12 DOI： 10.3969/j.issn.2096-6091.2024.02.002.

摘要

本研究旨在通过Outlier-SMOTE算法和FOA-SVM模型，提高颅内动脉瘤患者风险预测的准确性。首先使用形态学指标和血流动力学指标构建了一个结合形态学与血流动力学特征的数据集。并采用Outlier-SMOTE、SMOTE和ADASYN算法对原始数据集进行采样，以平衡数据集中的少数类样本。实验结果表明，在Outlier-SMOTE算法构建的数据集上，FOA-SVM在预测正例以及反例上表现最佳。本文通过Outlier-SMOTE算法和FOA-SVM模型，成功地实现了对颅内动脉瘤患者风险的预测。实验结果表明，Outlier-SMOTE算法在平衡数据集和提高FOA-SVM分类性能方面表现最佳，为临床诊断和治疗提供了有力的支持。

Abstract

This study aimed to enhance the accuracy of risk prediction for intracranial aneurysm patients through the use of the Outlier-SMOTE algorithm and the FOA-SVM model. First

a data set integrating morphological and hemodynamic features is constructed using morphological and hemodynamic indicators. Subsequently

the original data set is resampled using the Outlier-SMOTE

SMOTE

and ADASYN algorithms to balance the minority class samples. Experimental results indicate that the FOA-SVM performed optimally in predicting both positive and negative cases on the data set constructed by the Outlier-SMOTE algorithm. The study successfully predicte the risk of intracranial aneurysm patients through the Outlier-SMOTE algorithm and the FOA-SVM model. The experimental results demonstrate that the Outlier-SMOTE algorithm excelled in balancing the data set and improving the classification performance of the FOA-SVM

providing robust support for clinical diagnosis and treatment.

关键词

Keywords

references

TURHON M , LI M X , KANG H B , et al . Development and validation of a deep learning model for prediction of intracranial aneurysm rupture risk based on multi-omics factor [J ] . European Radiology , 2023 , 33 ( 10 ): 6759 - 6770 .

刘艺超 , 修良昌 , 王超 , 等 . 三维CT血管成像对颅内动脉瘤的诊断价值 [J ] . 中国CT和MRI杂志 , 2023 , 21 ( 11 ): 31 - 33 .

ZHENG Y T , XU F , REN J M , et al . Assessment of intracranial aneurysm rupture based on morphology parameters and anatomical locations [J ] . Journal of Neurointerventional Surgery , 2016 , 8 ( 12 ): 1240 - 1246 .

汪仁勇 , 杨少春 . 形态学和血流动力学因素预测颅内动脉瘤破裂风险的研究进展 [J ] . 医学综述 , 2023 , 29 ( 21 ): 4668 - 4672 .

陈建秋 , 徐峰 , 仇成丞 , 等 . 基于CTA分析颅内动脉瘤破裂危险因素的初步研究 [J ] . 中国CT和MRI杂志 , 2023 , 21 ( 11 ): 28 - 30 .

费佳 , 段凯 . 基于3D-Slicer软件行CTA重建预测颅内动脉瘤破裂的相关性研究 [J ] . 中国CT和MRI杂志 , 2023 , 21 ( 3 ): 35 - 37 .

TANHA J , ABDI Y , SAMADI N , et al . Boosting methods for multi-class imbalanced data classification: An experimental review [J ] . Journal of Big Data , 2020 , 7 ( 1 ): 70 .

LIU Y X , LIU Y , YU B X B , et al . Noise-robust oversampling for imbalanced data classification [J ] . Pattern Recognition , 2023 , 133 : 109008 .

BALLA A , HABAEBI M H , ELSHEIKH E A A , et al . The effect of dataset imbalance on the performance of SCADA intrusion detection systems [J ] . Sensors , 2023 , 23 ( 2 ): 758 .

TURLAPATI V P K , PRUSTY M R . Outlier-SMOTE: A refined oversampling technique for improved detection of COVID-19 [J ] . Intelligence-Based Medicine , 2020 , 3 : 100023 .

LI Y , HUAN L C , LU W P , et al . Integrate prediction of machine learning for single ACoA rupture risk: A multicenter retrospective analysis [J ] . Frontiers in Neurology , 2023 , 14 : 1126640 .

NGUYEN T , MENGERSEN K , SOUS D , et al . SMOTE-CD: SMOTE for compositional data [J ] . PLoS One , 2023 , 18 ( 6 ): e0287705 .

RANJAN R K , KUMAR V . A systematic review on fruit fly optimization algorithm and its applications [J ] . Artificial Intelligence Review , 2023 , 56 ( 11 ): 13015 - 13069 .

GU Q H , CHANG Y X , LI X H , et al . A novel F-SVM based on FOA for improving SVM performance [J ] . Expert Systems with Applications , 2021 , 165 : 113713 .

CHEN X , WANG M , WU S , et al . Optimal SVM using an improved FOA of evolutionary computing [M ] // Communications in Computer and Information Science . Singapore : Springer Nature Singapore , 2022 : 55 - 68 .

刘睿 , 赵坤 . 基于优化算法的多传感器自动规划技术 [J ] . 电子技术与软件工程 , 2021 ( 18 ): 90 - 93 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于血流动力学与形态学特征融合的动脉瘤破裂风险机器学习预测研究

面向不平衡数据集的脑卒中风险预测研究