ISSN 0439-755X
CN 11-1911/B

心理学报 ›› 2022, Vol. 54 ›› Issue (9): 1031-1047.doi: 10.3724/SP.J.1041.2022.01031

• 研究报告 • 上一篇    下一篇


孙芳#, 宋巍#, 温晓通a(), 李欢欢a(), 欧阳李晟, 魏诗洁   

  1. 中国人民大学心理学系, 北京 100872
  • 收稿日期:2021-12-16 发布日期:2022-07-21 出版日期:2022-09-25
  • 通讯作者: 温晓通,李欢欢;
  • 作者简介:# 为共同一作者
  • 基金资助:

Efficacy of suicide ideation classification based on pain avoidance and the EEG characteristics under self-referential punishment

SUN Fang#, SONG Wei#, WEN Xiaotonga(), LI Huanhuana(), OUYANG Lisheng, WEI Shijie   

  1. Department of Psychology, Renmin University of China, Beijing 100872, China
  • Received:2021-12-16 Online:2022-07-21 Published:2022-09-25
  • Contact: WEN Xiaotong,LI Huanhuan;


采用支持向量机的特征递归选择算法, 创新性采用三维心理痛苦量表和自我参照情感激励延迟任务, 建构自杀意念分类模型的重要特征集, 并比较自杀意念和抑郁的分类模型重要特征集差异。结果发现, 痛苦逃避是自杀意念分类模型的首位特征; 基于痛苦加工特征的自杀意念多模态分类模型效能优良。研究首次证实了在机器学习建构复杂的自杀意念分类模型中, 痛苦逃避及其相关脑电成分的重要性。拓展了结合心理痛苦三因素模型和机器学习算法对自杀预测的临床应用可行性。

关键词: 心理痛苦, 自杀意念, 机器学习, 脑电


Depressed students are at high-risk for suicide. Psychological pain, especially pain avoidance, was a more robust predictor for suicide ideation than depression at the behavioral level. Due to suicide as a complex classification model, machine learning algorisms applied to integrate behavioral data and neural characteristic can advance suicide prediction, and the accuracy of multimodality features is superior than clinical interview. The present study aimed to integrate data-driven machine learning algorisms and the three-dimensional psychological pain model to figure out the optimal features in the prediction of suicide ideation.
Seventy-seven college students were recruited by advertisement and divided into three groups: depressed group with high levels of suicide ideation (HSI, n = 25), depressed group with low levels of suicide ideation (LSI, n = 20), and healthy controls (HC, n = 32). All participants completed the three-dimensional psychological pain scale (TDPPS), Beck depression inventory-I (BDI), Beck suicide ideation inventory (BSI), and the self-referential affective incentive delay task (SAID). The value of support vector based on machine-recursive feature elimination (RFE-SVM) algorithm applied to combine the scale scores, resting state and punitive-related EEG components for feature ranking in a nonlinear way.
Results showed that: (1) Scores of pain avoidance in the HSI was higher than the LSI group. (2) The multimodal psychological pain-based model for suicide ideation classification (Accuracy = 85.66%, Precision = 0.82, Recall = 0.73, AUC = 0.92) was sufficient and superior than the EEG single-modal model. Importantly, the pain avoidance and BDI scores ranked the top two features in the classification model of suicide ideation, whereas painful feeling and pain arousal subscale scores ranked the top two features in the classification model of depression. The EEG optimal features of overlap in the pain avoidance and suicide ideation classification models were the LPP and target-P3 under self-referential punitive conditions. (3) The powers of delta and beta band were negatively correlated with the BSI-W and pain avoidance subscale scores. The FRN amplitude under other- and self-referential punitive conditions were negatively corelated with the pain avoidance subscale scores. In the HSI group, power of delta elicited by positive feedback under self-referential conditions was significantly lower than those under other-referential conditions. In the HSI group, the amplitude of LPP in other-referential punitive conditions was higher than those under reward and neutral conditions, whereas in the LSI group, the amplitude of LPP under self-referential punitive conditions was higher than that under neutral conditions.
As a pilot study, the current study provided a support for the prominent role of pain avoidance and its related neuroelectrophysiological correlates in the prediction of suicide. The clinical significance of these results will be discussed.

Key words: three-dimensional psychological pain, suicide ideation, machine learning, EEG