OEDL: an optimized ensemble deep learning method for the prediction of acute ischemic stroke prognoses using union features

被引:4
|
作者
Ye, Wei [1 ]
Chen, Xicheng [1 ]
Li, Pengpeng [1 ]
Tao, Yongjun [2 ]
Wang, Zhenyan [1 ]
Gao, Chengcheng [1 ]
Cheng, Jian [3 ]
Li, Fang [1 ]
Yi, Dali [1 ,4 ]
Wei, Zeliang [1 ]
Yi, Dong [1 ]
Wu, Yazhou [1 ]
机构
[1] Army Med Univ, Coll Prevent Med, Dept Hlth Stat, Chongqing, Peoples R China
[2] Taizhou Municipal Hosp, Dept Neurol, Taizhou, Zhejiang, Peoples R China
[3] Taizhou Municipal Hosp, Dept Radiol, Taizhou, Zhejiang, Peoples R China
[4] Army Med Univ, Coll Prevent Med, Dept Hlth Educ, Chongqing, Peoples R China
来源
FRONTIERS IN NEUROLOGY | 2023年 / 14卷
基金
中国国家自然科学基金;
关键词
MRI; radiomics; deep learning; ensemble learning; metaheuristic algorithms; ischemic stroke; NEURAL-NETWORK; GLOBAL BURDEN; EPIDEMIOLOGY; INTERNET; CHINA;
D O I
10.3389/fneur.2023.1158555
中图分类号
R74 [神经病学与精神病学];
学科分类号
摘要
BackgroundEarly stroke prognosis assessments are critical for decision-making regarding therapeutic intervention. We introduced the concepts of data combination, method integration, and algorithm parallelization, aiming to build an integrated deep learning model based on a combination of clinical and radiomics features and analyze its application value in prognosis prediction. MethodsThe research steps in this study include data source and feature extraction, data processing and feature fusion, model building and optimization, model training, and so on. Using data from 441 stroke patients, clinical and radiomics features were extracted, and feature selection was performed. Clinical, radiomics, and combined features were included to construct predictive models. We applied the concept of deep integration to the joint analysis of multiple deep learning methods, used a metaheuristic algorithm to improve the parameter search efficiency, and finally, developed an acute ischemic stroke (AIS) prognosis prediction method, namely, the optimized ensemble of deep learning (OEDL) method. ResultsAmong the clinical features, 17 features passed the correlation check. Among the radiomics features, 19 features were selected. In the comparison of the prediction performance of each method, the OEDL method based on the concept of ensemble optimization had the best classification performance. In the comparison to the predictive performance of each feature, the inclusion of the combined features resulted in better classification performance than that of the clinical and radiomics features. In the comparison to the prediction performance of each balanced method, SMOTEENN, which is based on a hybrid sampling method, achieved the best classification performance than that of the unbalanced, oversampled, and undersampled methods. The OEDL method with combined features and mixed sampling achieved the best classification performance, with 97.89, 95.74, 94.75, 94.03, and 94.35% for Macro-AUC, ACC, Macro-R, Macro-P, and Macro-F1, respectively, and achieved advanced performance in comparison with that of methods in previous studies. ConclusionThe OEDL approach proposed herein could effectively achieve improved stroke prognosis prediction performance, the effect of using combined data modeling was significantly better than that of single clinical or radiomics feature models, and the proposed method had a better intervention guidance value. Our approach is beneficial for optimizing the early clinical intervention process and providing the necessary clinical decision support for personalized treatment.
引用
收藏
页数:20
相关论文
共 50 条
  • [1] Deep Learning of Tissue Fate Features in Acute Ischemic Stroke
    Stier, Noah
    Vincent, Nicholas
    Liebeskind, David
    Scalzo, Fabien
    PROCEEDINGS 2015 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE, 2015, : 1316 - 1321
  • [2] Prediction of Tissue Outcome and Assessment of Treatment Effect in Acute Ischemic Stroke Using Deep Learning
    Nielsen, Anne
    Hansen, Mikkel Bo
    Tietze, Anna
    Mouridsen, Kim
    STROKE, 2018, 49 (06) : 1394 - 1401
  • [3] Functional Outcome Prediction in Acute Ischemic Stroke Using a Fused Imaging and Clinical Deep Learning Model
    Liu, Yongkai
    Yu, Yannan
    Ouyang, Jiahong
    Jiang, Bin
    Yang, Guang
    Ostmeier, Sophie
    Wintermark, Max
    Michel, Patrik
    Liebeskind, David S.
    Lansberg, Maarten G.
    Albers, Gregory W.
    Zaharchuk, Greg
    STROKE, 2023, 54 (09) : 2316 - 2327
  • [4] StackDPPred: Multiclass prediction of defensin peptides using stacked ensemble learning with optimized features
    Arif, Muhammad
    Musleh, Saleh
    Ghulam, Ali
    Fida, Huma
    Alqahtani, Yasser
    Alam, Tanvir
    METHODS, 2024, 230 : 129 - 139
  • [5] Ischemic stroke outcome prediction with diversity features from whole brain tissue using deep learning network
    Yang, Yingjian
    Guo, Yingwei
    FRONTIERS IN NEUROLOGY, 2024, 15
  • [6] Optimized stock market prediction using ensemble learning
    Asad, Muhammad
    2015 9TH INTERNATIONAL CONFERENCE ON APPLICATION OF INFORMATION AND COMMUNICATION TECHNOLOGIES (AICT), 2015, : 263 - 268
  • [7] Prediction of Subacute Infarction in Acute Ischemic Stroke Using Baseline Multi-modal MRI and Deep Learning
    Yu Yannan
    Xie, Yuan
    Thamm, Thoralf
    Chen, Kevin T.
    Gong Enhao
    Zaharchuk, Greg
    STROKE, 2019, 50
  • [8] Tissue at Risk and Ischemic Core Estimation Using Deep Learning in Acute Stroke
    Yu, Y.
    Xie, Y.
    Thamm, T.
    Gong, E.
    Ouyang, J.
    Christensen, S.
    Marks, M. P.
    Lansberg, M. G.
    Albers, G. W.
    Zaharchuk, G.
    AMERICAN JOURNAL OF NEURORADIOLOGY, 2021, 42 (06) : 1030 - 1037
  • [9] Heart Disease Prediction Model Using Feature Selection and Ensemble Deep Learning with Optimized Weight
    Al-Mahdi, Iman S.
    Darwish, Saad M.
    Madbouly, Magda M.
    CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES, 2025,
  • [10] Student grade prediction for effective learning approaches using the optimized ensemble deep neural network
    Abdasalam, Mahmoud
    Alzubi, Ahmad
    Iyiola, Kolawole
    EDUCATION AND INFORMATION TECHNOLOGIES, 2024,