The predictive value of light gradient boosting machine model based on three nonlinear features of scalp electroencephalography on the preictal phase of epilepsy.

Objective Constructing a classification model based on 3 nonlinear features of scalp electroencephalography (SEEG) for identifying the preictal phase of epilepsy. Methods Total 83 patients with epilepsy who underwent long - term SEEG monitoring at He'nan Provincial People's Hospital from January 201...

Full description

Bibliographic Details
Published in:Chinese Journal of Contemporary Neurology & Neurosurgery Vol. 26; no. 3; pp. 227 - 235
Main Authors: REN, Zhe, GAO, Jing, YUE, Meng-yan, ZHAO, Ting, WANG, Na, CHEN, Ya-nan, HAN, Xiong
Format: research tables/charts Journal Article
Published: Chinese Journal of Contemporary Neurology & Neurosurgery Mar2026
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=193030408&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 193030408
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        16726731
        FDQ6
      jtl: Chinese Journal of Contemporary Neurology & Neurosurgery
      issn: 16726731
      maglogo: N
    pubinfo:
      dt: Mar2026
      vid: 26
      iid: 3
      pid: 80951
      pub: Chinese Journal of Contemporary Neurology & Neurosurgery
    artinfo:
      ui:
        193030408
        193030408
        193030408
        10.3969/j.issn.1672-6731.2026.03.004
        193030408
      ppf: 227
      ppct: 8
      formats:
        fmt:
          @attributes:
            type: P
      tig:
        atl: The predictive value of light gradient boosting machine model based on three nonlinear features of scalp electroencephalography on the preictal phase of epilepsy.
      aug:
        au:
          REN, Zhe
          GAO, Jing
          YUE, Meng-yan
          ZHAO, Ting
          WANG, Na
          CHEN, Ya-nan
          HAN, Xiong
        affil: Department of Neurology, He'nan Provincial People's Hospital, Zhengzhou 450003, He'nan, China
      sug:
        subj:
          Epilepsy Diagnosis
          Boosting Machine Learning Algorithms
          Computer Simulation
          Predictive Value of Tests
          Scalp
          Electroencephalography
          Human
          China
          Analysis of Variance
          Mann-Whitney U Test
          Chi Square Test
          Support Vector Machine
          Machine Learning Algorithms
          Sensitivity and Specificity
          ROC Curve
          Funding Source
          Retrospective Design
          Record Review
          Tertiary Health Care China
          Data Analysis Software
      ab: Objective Constructing a classification model based on 3 nonlinear features of scalp electroencephalography (SEEG) for identifying the preictal phase of epilepsy. Methods Total 83 patients with epilepsy who underwent long - term SEEG monitoring at He'nan Provincial People's Hospital from January 2014 to December 2021 were enrolled. Three nonlinear features [phase lag index (PLI), Lempel- Ziv complexity (LZC) and sample entropy (SampEn)] were calculated. Analysis of variance, rank sum test, and χ2 test were used to complete feature selection of disease predictive value. Single and general models were constructed to identify the preictal phase of epilepsy, respectively, using different machine learning (ML) algorithms including support vector machine (SVM), light gradient boosting machine (LightGBM), and k nearest neighbor (KNN) methods based on five -fold cross-validation. Results The LightGBM model constructed with rank sum test feature selection (α + β + δ + θ + whole) performed best. The average performance in the single model was 0.929 for sensitivity, 0.924 for specificity, 0.934 for accuracy, 0.930 for precision, 0.928 for the F1-score, and 0.971 for the area under the curve (AUC). In the general model, the performance was 0.712 for sensitivity, 0.652 for specificity, 0.682 for accuracy, 0.677 for precision, 0.694 for the F1-score, and 0.766 for AUC. Conclusions The LightGBM model constructed using rank sum test was effective in identifying the preictal phase of epilepsy.
      pubtype: Academic Journal
      doctype:
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: Chinese
    refInfo:
    holdings:
      @attributes:
        islocal: N