Identifying socio-demographic risk factors for suicide using data on an individual level

Suicide is a complex issue. Due to the relative rarity of the event, studies into risk factors are regularly limited by sample size or biased samples. The aims of the study were to find risk factors for suicide that are robust to intercorrelation, and which were based on a large and unbiased sample.

Using a training set of 5854 suicides and 596,416 control cases, we fit a logistic regression model and then evaluate the performance on a test set of 1425 suicides and 594,893 control cases. The data used was micro-data of Statistics Netherlands (CBS) with data on each inhabitant of the Netherlands.

Taking the effect of possible correlating risk factors into account, those with a higher risk for suicide are men, middle-aged people, people with low income, those living alone, the unemployed, and those with mental or physical health problems. People with a lower risk are the highly educated, those with a non-western immigration background, and those living with a partner.

We confirmed previously known risk factors such as male gender, middle-age, and low income and found that they are risk factors that are robust to intercorrelation. We found that debt and urbanicity were mostly insignificant and found that the regional differences found in raw frequencies are mostly explained away after correction of correlating risk factors, indicating that these differences were primarily caused due to the differences in the demographic makeup of the regions. We found an AUC of 0.77, which is high for a model predicting suicide death and comparable to the performance of deep learning models but with the benefit of remaining explainable.