基于网络分析的抑郁症产生与演变预测  

Prediction of depression onset and development based on network analysis

作　　者：张伟霞 席敏 阴甜甜 王成 司书宾[3,4] ZHANG Weixia;XI Min;YIN Tiantian;WANG Cheng;SI Shubin(Sports Department,Northwestern Polytechnical University,Xi’an 710072,China;Hospital of Northwestern Polytechnical University,Xi’an 710072,China;School of Mechanical Engineering,Northwestern Polytechnical University,Xi’an 710072,China;Key Laboratory of Industrial Engineering and Intelligent Manufacturing(Ministry of Industry and Information Technology),Xi’an 710072,China)

机构地区：[1]西北工业大学体育部,西安710072 [2]西北工业大学医院,西安710072 [3]西北工业大学机电学院,西安710072 [4]工业工程与智能制造工业和信息化部重点实验室,西安710072

出　　处：《心理科学进展》2023年第11期2129-2141,共13页Advances in Psychological Science

基　　金：国家自然科学基金(72171193);西北工业大学特色文科发展计划——青年创新能力培养项目(23GH030635);西北工业大学教育教学改革研究项目(23GZ13163)资助。

摘　　要：抑郁症是现代社会亟需解决的公共健康问题,预防是应对该问题最有效的方式之一。有效预防的关键在于准确识别潜在抑郁症患者,捕捉抑郁状态发生变化的预警信号,及时采取预防措施。抑郁是由多种症状相互作用而成的网络系统,该网络的结构特征和动力特征能为抑郁症发生与演变的预测提供新的理论视角和可测量的指标。以如何预测抑郁症发生与演化的关键问题为切入点,从理论的角度论述症状网络与抑郁的关系,进一步考察抑郁症状网络的拓扑结构特征、临界现象相关指标在预测抑郁发作及突变中的表现力。为增加早期预警信号在抑郁状态预测方面的准确性,未来研究应当构建更系统、全面的网络,通过使用综合的或基于机器学习的预警指标,优化抑郁状态确定方法。Depression is a public health problem that needs to be solved urgently in modern society,and prevention is one of the most effective ways to deal with this problem.The key of successful prevention is to accurately identify potential depression patients,capture warning signals indicating the state transition,and take preventive actions timely.Depression is a network composed of multiple symptoms interacting with each other.The structural and dynamic features of this network can provide new theoretical perspectives and measurable indicators for the occurrence and evolution of depression.Starting from the key issue of predicting the occurrence and changes of depression,this paper discusses the relationship between symptom networks and depression from a theoretical perspective,and further examines the performance of structural features and critical phenomena-related indicators of depression symptom networks in predicting depression onset and mutations.To increase the accuracy of early warning signals in predicting depression,future studies should construct more comprehensive networks,and optimize the method of determining depression states by using composite or machine learning based warning indictors.

关 键 词：网络分析 抑郁症状演变 预测 临界现象 早期预警信号 

分 类 号：R395[哲学宗教—心理学]