Suicide is the second leading cause of death among 25–34 year olds and the third leading cause of death among 15–25 year olds in the United States. In the Emergency Department, where suicidal patients often present, estimating the risk of repeated attempts is generally left to clinical judgment. This paper presents our second attempt to determine the role of computational algorithms in understanding a suicidal patient’s thoughts, as represented by suicide notes. We focus on developing methods of natural language processing that distinguish between genuine and elicited suicide notes. We hypothesize that machine learning algorithms can categorize suicide notes as well as mental health professionals and psychiatric physician trainees do. The data used are comprised of suicide notes from 33 suicide completers and matched to 33 elicited notes from healthy control group members. Eleven mental health professionals and 31 psychiatric trainees were asked to decide if a note was genuine or elicited. Their decisions were compared to nine different machine-learning algorithms. The results indicate that trainees accurately classified notes 49% of the time, mental health professionals accurately classified notes 63% of the time, and the best machine learning algorithm accurately classified the notes 78% of the time. This is an important step in developing an evidence-based predictor of repeated suicide attempts because it shows that natural language processing can aid in distinguishing between classes of suicidal notes.

Background

Suicidal thought is a risk factor and a stage in the suicidal process from planning to attempting and dying by suicide. To date, studies on suicidal thought in the general population, especially in Asian communities, have been limited.

Method

The WHO SUPRE-MISS (the multisite intervention study on suicidal behaviours) community survey questionnaire was filled in for 2,280 randomly selected residents of the DongDa district of Hanoi, Vietnam by means of face-to-face interviews. This multi-factor questionnaire includes such variables as sociodemographic information, suicidal thought and history of suicide attempts, physical health, alcohol consumption and medication.

Results

Prevalence rates for life time suicidal thoughts, suicide plans and suicide attempts were 8.9%, 1.1% and 0.4% respectively. Suicidal thoughts are associated with multiple characteristics, such as female gender, single/widowed/separated/divorced marital status, low income, lifestyle (use of alcohol, sedatives and pain relief medication), but not with low education or employment status. Having no religion and being a Buddhist appear to be protective factors for suicidal thought.

The ratio of suicidal thoughts, suicide plans and suicide attempts on a lifetime basis is 22.3:2.8:1.

Conclusion

In Vietnam, as in Western and other Asian countries, suicidal thoughts are associated with similar negative psychosocial risk factors, lifestyle and emotional problems, which implies that suicide preventive measure developed elsewhere can be adjusted to Vietnamese condition. Understanding the unique and common risks in a culture may assist in prediction and control.