An interpretable and generalizable deep learning model for iEEG-based seizure prediction using prototype learning and contrastive learning

被引：0
|
作者：
Gao, Yikai [1 ,2 ]
Liu, Aiping [2 ]
Cui, Heng [2 ]
Qian, Ruobing [2 ]
Chen, Xun [1 ,2 ]
机构：
[1] Department of Neurosurgery, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Anhui, Hefei,230001, China
[2] Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei,230001, China
来源：
Computers in Biology and Medicine | 2024年 / 183卷
关键词：
Epileptic seizure prediction plays a crucial role in enhancing the quality of life for individuals with epilepsy. Over recent years; a multitude of deep learning-based approaches have emerged to tackle this challenging task; leading to significant advancements. However; the ‘black-box’ nature of deep learning models and the considerable interpatient variability significantly impede their interpretability and generalization; thereby severely hampering their efficacy in real-world clinical applications. To address these issues; our study aims to establish an interpretable and generalizable seizure prediction model that meets the demands of clinical diagnosis. Our method extends self-interpretable prototype learning networks into a novel domain adaptation framework designed specifically for cross-patient seizure prediction. The proposed framework enables patient-level interpretability by tracing the origins of significant prototypes. For instance; it could provide information about the seizure type of the patient to which the prototype belongs. This surpasses the existing sample-level interpretability; which is limited to individual patient samples. To further improve the model's generalization capability; we introduce a contrastive semantic alignment loss constraint to the embedding space; enhancing the robustness of the learned prototypes. We evaluate our proposed model using the Freiburg intracranial electroencephalography (iEEG) dataset; which consists of 20 patients and a total of 82 seizures. The experimental results demonstrated a high sensitivity of 79.0%; a low false prediction rate of 0.183; and a high area under the receiver operating characteristic curve (AUC) value of 0.804; achieving state-of-the-art performance with self-interpretable evidence in contrast to the current cross-patient seizure prediction methods. Our study represents a significant step forward in developing an interpretable and generalizable model for seizure prediction; thereby facilitating the application of deep learning models in clinical diagnosis. © 2024 Elsevier Ltd;
D O I：
10.1016/j.compbiomed.2024.109257
中图分类号：
学科分类号：
摘要：
引用
收藏
相关论文
共 50 条
  • [1] Generalizable and Interpretable Deep Learning for Network Congestion Prediction
    Poularakis, Konstantinos
    Qin, Qiaofeng
    Le, Franck
    Kompella, Sastry
    Tassiulas, Leandros
    2021 IEEE 29TH INTERNATIONAL CONFERENCE ON NETWORK PROTOCOLS (ICNP 2021), 2021,
  • [2] A GENERALIZABLE MODEL FOR SEIZURE PREDICTION BASED ON DEEP LEARNING USING CNN-LSTM ARCHITECTURE
    Shahbazi, Mohamad
    Aghajan, Hamid
    2018 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP 2018), 2018, : 469 - 473
  • [3] An Interpretable Deep Learning Classifier for Epileptic Seizure Prediction Using EEG Data
    Jemal, Imene
    Mezghani, Neila
    Abou-Abbas, Lina
    Mitiche, Amar
    IEEE ACCESS, 2022, 10 : 60141 - 60150
  • [4] A generalizable and interpretable deep learning model to improve the prediction accuracy of strain fields in grid composites
    Park, Donggeun
    Jung, Jiyoung
    Gu, Grace X.
    Ryu, Seunghwa
    MATERIALS & DESIGN, 2022, 223
  • [5] A Contrastive Learning-Based Interpretable Prediction Model for Patients with Heart Failure
    Zhang, Jinxiang
    Xu, Tianhan
    Li, Bin
    ARTIFICIAL INTELLIGENCE AND ROBOTICS, ISAIR 2023, 2024, 1998 : 288 - 299
  • [6] Expert and deep learning model identification of iEEG seizures and seizure onset times
    Arcot Desai, Sharanya
    Afzal, Muhammad Furqan
    Barry, Wade
    Kuo, Jonathan
    Benard, Shawna
    Traner, Christopher
    Tcheng, Thomas
    Seale, Cairn
    Morrell, Martha
    FRONTIERS IN NEUROSCIENCE, 2023, 17
  • [7] Seizure Prediction Based on Hybrid Deep Learning Model Using Scalp Electroencephalogram
    Yan, Kuiting
    Shang, Junliang
    Wang, Juan
    Xu, Jie
    Yuan, Shasha
    ADVANCED INTELLIGENT COMPUTING TECHNOLOGY AND APPLICATIONS, ICIC 2023, PT II, 2023, 14087 : 272 - 282
  • [8] SGCL-LncLoc: An Interpretable Deep Learning Model for Improving IncRNA Subcellular Localization Prediction with Supervised Graph Contrastive Learning
    Li, Min
    Zhao, Baoying
    Li, Yiming
    Ding, Pingjian
    Yin, Rui
    Kan, Shichao
    Zeng, Min
    BIG DATA MINING AND ANALYTICS, 2024, 7 (03): : 765 - 780
  • [9] Livestream sales prediction based on an interpretable deep-learning model
    Wang, Lijun
    Zhang, Xian
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [10] Traffic accident severity prediction based on interpretable deep learning model
    Pei, Yulong
    Wen, Yuhang
    Pan, Sheng
    TRANSPORTATION LETTERS-THE INTERNATIONAL JOURNAL OF TRANSPORTATION RESEARCH, 2024,
12345