JMIR Publications

ABSTRACT

Background:

South Korea has the highest suicide rate among the OECD nations, with particularly elevated figures among persons with disabilities (PWD). Research has shown a strong correlation between suicidal ideation and suicide attempts.

Objective:

This study aimed to investigate the factors that contribute to suicidal ideation among PWD, utilizing machine learning methods based on data from the 2020 National Survey on Persons with Disabilities.

Methods:

The analysis employed data from the 2020 National Survey on Persons with Disabilities in South Korea, which included 7,025 respondents. The primary variable of interest was the answer to the question, "In the past year, have you considered suicide?" The dataset was divided into training (80%) and testing (20%) subsets. Feature selection was conducted using a random forest, followed by the implementation of five machine learning models that predicted suicidal ideation based on the selected features: logistic regression, support vector machine, random forest, XGBoost, and feed-forward neural network.

Results:

A total of 12.1% of the survey respondents indicated they had contemplated suicide within the past year. Significant factors that impacted suicidal ideation included intense feelings of sadness, difficulties associated with their disabilities, and overall health satisfaction. Among the models tested, the random forest model exhibited the best predictive performance.

Conclusions:

This study highlights critical predictors of suicidal ideation in PWD in South Korea, underscoring the necessity for focused mental health interventions. The results demonstrate the potential of machine learning to identify these factors, which can aid in the development of future suicide prevention strategies.