Research and data

Understanding the risk of suicide

understanding suicide risks

The World Health Organization (WHO) reports that close to 800,000 people die by suicide every year. Here in the United States, 13 people per 100,000 die by suicide annually, a statistic that has not decreased in 50 years. These are staggering numbers, but what is even more alarming is the fact that the numbers of attempted suicides each year are nearly 10X this sum.

The WHO report also found:

  • A prior suicide attempt is the single most important risk factor for suicide in the general population.
  • Suicide is the second leading cause of death among people aged 15 to 29.
  • Suicide is the third leading cause of death in 15-19-year-olds.
  • 79% of global suicides occur in low- and middle-income countries.
  • Ingestion of pesticides, hanging, and self-inflicted gunshot wounds are among the most common methods of suicide.

While suicide is complicated to study, what is known is that there is a distinct correlation between one’s mental health and suicide. But, mental health and suicide are not exclusive.

Jaimie Gradus, an associate professor of epidemiology here at the Boston University School of Public Health was quoted in this article, stating, “Every suicide death is the result of multiple interacting risk factors in one’s life. One of the reasons that the suicide rate has not really improved, despite decades of research, is because studies have been hampered by what traditional statistics will allow us to look at, at once.”

Gradus and a team of her peers from both BUSPH and Aarhus University in Denmark, recently conducted a study that suggests physical health issues are an important predictor of suicide by men, but not in women. The authors hypothesize that this may be the case because doctors are more likely to ask men about their physical health (versus mental health) and vice versa for women. Alternatively, it may be because women are more likely to discuss mental health symptoms with doctors, when men are more likely to report physical health issues. It’s also possible that men’s experience of mental distress results in more physical health symptoms than is true for women, ultimately leading to more questions that are worth studying.

A key question that the study set out to answer was, “how can we better or more optimally detect suicide risk?” To help find the answer, the study was the first to use machine-based learning methods to examine the suicide risk in a full civilian population.

“…psychiatric disorders emerged as the most important predictors of suicide. This finding is largely consistent with what is known about psychiatric disorders and suicide risk. However, some specific disorders that appeared in our results were novel. While schizophrenia and depression are well-established risk factors for suicide, there is some controversy in the literature with regard to whether stress disorders are a risk factor for suicide aside from depression. In these results, stress disorders are an important predictor of suicide among both men and women in models simultaneously evaluating depression. Furthermore, antidepressants, antipsychotics, hypnotics/sedatives, and medications used to treat addictions were important to the accuracy of predicting suicide across analyses. Although our results indicate that pharmacotherapy is important to suicide prediction, our non-causal models could not elucidate the direction or magnitude of associations.”

Predicting suicide with perfect accuracy is still not possible, but it’s ever important to understand the factors that lead to suicide. Studies like this one and similar work may help to improve the accuracy of screening models. This continued research will, hopefully, one day help to better predict and reduce suicide risk.

Suicide is more than just a death. “To me, suicide is an indicator of years lived in suffering,” Gradus says, for the decedent and for those left behind. Her hope is that one day her research can lead to help for those suffering.

Further reading:

Understanding the Complex ‘Constellation of Factors’ That Shape Mental Health.”

Predicting Suicide.

On Suicide.

If you are experiencing suicidal thoughts of any kind and are in need of someone to talk to, don’t hesitate to reach out to the following resources:

Suicide Hotline


To Write Love on Her Arms

New call-to-action

If you are interested in working with Professor Gradus to further improve the accuracy of screening models or in understanding the impacts of suicide loss, please contact us at

You may also like

data analysis
In the news
Why Health Data Is Good Infrastructure

We need to strengthen and build robust health data utilities that can link and connect public health and clinical data systems. It makes sense to build these data utilities as public-private…

mental health and physical health are intrinsically tied together
Research and data
Mental health and physical health cannot be separated

The mind and body are deeply intertwined, and mental wellbeing is crucial for physical wellbeing. People with mental illness, such as depression, are at increased risk of chronic disease, such…

How machine learning helps identify people at high risk of suicide after discharge
Research and data
How Machine Learning Helps Predict Suicide After Discharge from Psychiatric Hospitalization

Suicide is a major public health problem, with approximately 800,000 suicide deaths globally each year. Thus, it’s crucial to accurately predict who will engage in suicidal behavior so that they…