与学业相关的压力因素可预测研究生的抑郁症状：机器学习研究

IF 2.6 3区心理学 Q2 BEHAVIORAL SCIENCES

Behavioural Brain Research Pub Date : 2024-11-07 DOI:10.1016/j.bbr.2024.115328

Aline F. Bastos , Orlando Fernandes-Jr , Suzana P. Liberal , Anna Júlia L. Pires , Luisa A. Lage , Olga Grichtchouk , Aline R. Cardoso , Leticia de Oliveira , Mirtes G. Pereira , Giovanni M. Lovisi , Raquel B. De Boni , Eliane Volchan , Fatima S. Erthal

{"title":"与学业相关的压力因素可预测研究生的抑郁症状：机器学习研究","authors":"Aline F. Bastos , Orlando Fernandes-Jr , Suzana P. Liberal , Anna Júlia L. Pires , Luisa A. Lage , Olga Grichtchouk , Aline R. Cardoso , Leticia de Oliveira , Mirtes G. Pereira , Giovanni M. Lovisi , Raquel B. De Boni , Eliane Volchan , Fatima S. Erthal","doi":"10.1016/j.bbr.2024.115328","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Graduate students face higher depression rates worldwide, which were further exacerbated during the COVID-19 pandemic. This study employed a machine learning approach to predict depressive symptoms using academic-related stressors.</div></div><div><h3>Methods</h3><div>We surveyed students across four graduate programs at a Federal University in Brazil between October 15, 2021, and March 26, 2022, when most activities were restricted to taking place online due to the pandemic. Through an online self-reported screening, participants rated ten academic stressors and completed the Patient Health Questionnaire (PHQ-9). Machine learning analysis tested whether the stressors would predict depressive symptoms. Gender, age, and race and ethnicity were used as covariates in the predictive model.</div></div><div><h3>Results</h3><div>Participants (n=172), 67.4 % women, mean age: 28.0 (SD: 4.53) fully completed the online questionnaires. The machine learning approach, employing an epsilon-insensitive support vector regression (Ɛ-SVR) with a k-fold (k=5) cross-validation strategy, effectively predicted depressive symptoms (r=0.51; R<sup>2</sup>=0.26; NMSE=0.79; all p=0.001). Among the academic stressors, those that made the greatest contribution to the predictive model were “fear and worry about academic performance”, “financial difficulties”, “fear and worry about academic progress and plans”, and “fear and worry about academic deadlines”.</div></div><div><h3>Conclusions</h3><div>This study highlights the vulnerability of graduate students to depressive symptoms caused by academic-related stressors during the COVID-19 pandemic through an artificial intelligence methodology. These findings have the potential to guide policy development to create intervention programs and public health initiatives targeted towards graduate students.</div></div>","PeriodicalId":8823,"journal":{"name":"Behavioural Brain Research","volume":"478 ","pages":"Article 115328"},"PeriodicalIF":2.6000,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Academic-related stressors predict depressive symptoms in graduate students: A machine learning study\",\"authors\":\"Aline F. Bastos , Orlando Fernandes-Jr , Suzana P. Liberal , Anna Júlia L. Pires , Luisa A. Lage , Olga Grichtchouk , Aline R. Cardoso , Leticia de Oliveira , Mirtes G. Pereira , Giovanni M. Lovisi , Raquel B. De Boni , Eliane Volchan , Fatima S. Erthal\",\"doi\":\"10.1016/j.bbr.2024.115328\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><h3>Background</h3><div>Graduate students face higher depression rates worldwide, which were further exacerbated during the COVID-19 pandemic. This study employed a machine learning approach to predict depressive symptoms using academic-related stressors.</div></div><div><h3>Methods</h3><div>We surveyed students across four graduate programs at a Federal University in Brazil between October 15, 2021, and March 26, 2022, when most activities were restricted to taking place online due to the pandemic. Through an online self-reported screening, participants rated ten academic stressors and completed the Patient Health Questionnaire (PHQ-9). Machine learning analysis tested whether the stressors would predict depressive symptoms. Gender, age, and race and ethnicity were used as covariates in the predictive model.</div></div><div><h3>Results</h3><div>Participants (n=172), 67.4 % women, mean age: 28.0 (SD: 4.53) fully completed the online questionnaires. The machine learning approach, employing an epsilon-insensitive support vector regression (Ɛ-SVR) with a k-fold (k=5) cross-validation strategy, effectively predicted depressive symptoms (r=0.51; R<sup>2</sup>=0.26; NMSE=0.79; all p=0.001). Among the academic stressors, those that made the greatest contribution to the predictive model were “fear and worry about academic performance”, “financial difficulties”, “fear and worry about academic progress and plans”, and “fear and worry about academic deadlines”.</div></div><div><h3>Conclusions</h3><div>This study highlights the vulnerability of graduate students to depressive symptoms caused by academic-related stressors during the COVID-19 pandemic through an artificial intelligence methodology. These findings have the potential to guide policy development to create intervention programs and public health initiatives targeted towards graduate students.</div></div>\",\"PeriodicalId\":8823,\"journal\":{\"name\":\"Behavioural Brain Research\",\"volume\":\"478 \",\"pages\":\"Article 115328\"},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2024-11-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Behavioural Brain Research\",\"FirstCategoryId\":\"102\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0166432824004844\",\"RegionNum\":3,\"RegionCategory\":\"心理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"BEHAVIORAL SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Behavioural Brain Research","FirstCategoryId":"102","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0166432824004844","RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BEHAVIORAL SCIENCES","Score":null,"Total":0}

引用次数: 0

摘要

背景：全世界的研究生都面临着较高的抑郁症发病率，而在 COVID-19 大流行期间，这种情况进一步加剧。本研究采用机器学习方法，利用与学业相关的压力因素预测抑郁症状：我们在2021年10月15日至2022年3月26日期间对巴西一所联邦大学四个研究生项目的学生进行了调查。通过在线自我报告筛查，参与者对十项学业压力因素进行了评级，并填写了患者健康问卷（PHQ-9）。机器学习分析测试了这些压力因素是否能预测抑郁症状。预测模型中使用了性别、年龄、种族和民族作为协变量：参与者（n=172），67.4% 为女性，平均年龄：28.0（SD：4.53），全部完成了在线问卷调查。机器学习方法采用了对epsilon不敏感的支持向量回归（Ɛ-SVR）和k-fold（k=5）交叉验证策略，有效地预测了抑郁症状（r=0.51；R2=0.26；NMSE=0.79；所有p=0.001）。在学业压力源中，对预测模型贡献最大的是 "对学业成绩的恐惧和担忧"、"经济困难"、"对学业进度和计划的恐惧和担忧 "以及 "对学业截止日期的恐惧和担忧"：本研究通过人工智能方法强调了在 COVID-19 大流行期间，研究生容易因与学业相关的压力因素而出现抑郁症状。这些发现有可能为制定针对研究生的干预计划和公共卫生倡议的政策提供指导。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Academic-related stressors predict depressive symptoms in graduate students: A machine learning study

Background

Graduate students face higher depression rates worldwide, which were further exacerbated during the COVID-19 pandemic. This study employed a machine learning approach to predict depressive symptoms using academic-related stressors.

Methods

We surveyed students across four graduate programs at a Federal University in Brazil between October 15, 2021, and March 26, 2022, when most activities were restricted to taking place online due to the pandemic. Through an online self-reported screening, participants rated ten academic stressors and completed the Patient Health Questionnaire (PHQ-9). Machine learning analysis tested whether the stressors would predict depressive symptoms. Gender, age, and race and ethnicity were used as covariates in the predictive model.

Results

Participants (n=172), 67.4 % women, mean age: 28.0 (SD: 4.53) fully completed the online questionnaires. The machine learning approach, employing an epsilon-insensitive support vector regression (Ɛ-SVR) with a k-fold (k=5) cross-validation strategy, effectively predicted depressive symptoms (r=0.51; R²=0.26; NMSE=0.79; all p=0.001). Among the academic stressors, those that made the greatest contribution to the predictive model were “fear and worry about academic performance”, “financial difficulties”, “fear and worry about academic progress and plans”, and “fear and worry about academic deadlines”.

Conclusions

This study highlights the vulnerability of graduate students to depressive symptoms caused by academic-related stressors during the COVID-19 pandemic through an artificial intelligence methodology. These findings have the potential to guide policy development to create intervention programs and public health initiatives targeted towards graduate students.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Behavioural Brain Research 医学-行为科学

CiteScore

5.60

自引率

0.00%

发文量

383

审稿时长

61 days

期刊介绍： Behavioural Brain Research is an international, interdisciplinary journal dedicated to the publication of articles in the field of behavioural neuroscience, broadly defined. Contributions from the entire range of disciplines that comprise the neurosciences, behavioural sciences or cognitive sciences are appropriate, as long as the goal is to delineate the neural mechanisms underlying behaviour. Thus, studies may range from neurophysiological, neuroanatomical, neurochemical or neuropharmacological analysis of brain-behaviour relations, including the use of molecular genetic or behavioural genetic approaches, to studies that involve the use of brain imaging techniques, to neuroethological studies. Reports of original research, of major methodological advances, or of novel conceptual approaches are all encouraged. The journal will also consider critical reviews on selected topics.