@article{ref1,
title="Detection of suicide attempters among suicide ideators using machine learning",
journal="Psychiatry investigation",
year="2019",
author="Ryu, Seunghyong and Lee, Hyeongrae and Lee, Dong-Kyun and Kim, Sung-Wan and Kim, Chul-Eung",
volume="16",
number="8",
pages="588-593",
abstract="OBJECTIVE: We aimed to develop predictive models to identify suicide attempters among individuals with suicide ideation using a machine learning algorithm. <br><br>METHODS: Among 35,116 individuals aged over 19 years from the Korea National Health & Nutrition Examination Survey, we selected 5,773 subjects who reported experiencing suicide ideation and had answered a survey question about suicide attempts. Then, we performed resampling with the Synthetic Minority Over-sampling TEchnique (SMOTE) to obtain data corresponding to 1,324 suicide attempters and 1,330 non-suicide attempters. We randomly assigned the samples to a training set (n=1,858) and a test set (n=796). In the training set, random forest models were trained with features selected through recursive feature elimination with 10-fold cross validation. Subsequently, the fitted model was used to predict suicide attempters in the test set. <br><br>RESULTS: In the test set, the prediction model achieved very good performance [area under receiver operating characteristic curve (AUC)=0.947] with an accuracy of 88.9%. <br><br>CONCLUSION: Our results suggest that a machine learning approach can enable the prediction of individuals at high risk of suicide through the integrated analysis of various suicide risk factors.<p /> <p>Language: en</p>",
language="en",
issn="1738-3684",
doi="10.30773/pi.2019.06.19",
url="http://dx.doi.org/10.30773/pi.2019.06.19"
}