AUTHOR=Liao Shiyi , Wang Yang , Zhou Xiaonan , Zhao Qin , Li Xiaojing , Guo Wanjun , Ji Xiaoyi , Lv Qiuyue , Zhang Yunyang , Zhang Yamin , Deng Wei , Chen Ting , Li Tao , Qiu Peiyuan 

TITLE=Prediction of suicidal ideation among Chinese college students based on radial basis function neural network

JOURNAL=Frontiers in Public Health

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.1042218

DOI=10.3389/fpubh.2022.1042218

ISSN=2296-2565

ABSTRACT=Background: Suicide is one of the leading causes of death for college students. As the first step toward suicide, suicidal ideation has been identified as an important precursor of suicide. The predictors of suicidal ideation among college students are inconsistent and few studies have systematically investigated psychological symptom of college students. Therefore, this study aims to develop a suicidal ideation prediction model and explore important predictors of suicidal ideation among college students. Methods: We recruited 1 500 college students of Sichuan University and followed them for four years. Demographic information of the participants and the behavioral and psychological information were collected through questionnaires from 2014 to 2018. The Radial Basis Function Neural Network (RBFNN) method was used to develop three suicidal ideation risk prediction models and explored the behavioral and psychological contributors to the suicidal ideation among college students. Results: The incidence of suicidal ideation among college students in the last twelve months ranged from 3.00% to 4.07%. The prediction models for suicidal ideation achieved the accuracy from 0.917 to 0.953, sensitivity from 0.500 to 0.667, specificity from 0.934 to 0.962, G-mean from 0.648 to 0.801 and area under curve scores from 0.80 to 0.96. Among college students, previous suicidal ideation and poor subjective sleep quality were the most important predictors. Poor self-rated mental health has also been identified to be an important predictor. Paranoid symptom, internet addiction, poor self-rated physical health, poor self-rated overall health, emotional abuse, low average annual household income per person and heavy study pressure were potential predictors for suicidal ideation. Conclusions: The study suggested that Radial Basis Function Neural Network method provided accuracy in predicting suicidal ideation. More attention should be paid to students who have a history of suicidal ideation, experience sleep problems, and have poor self-rated health in suicide prevention.