Source: Carnegie Mellon University
Summary: Researchers with the help of machine learning algorithms have developed an innovative method to identify suicidal thoughts in individuals.
Suicidal risks are very difficult to assess and predict. In the US, suicide is the second leading cause of death amongst young individuals. Researchers from Carnegie Mellon University and University of Pittsburgh developed an innovative approach to detect suicidal thoughts in individuals. They used machine-learning algorithms (Gaussian Naive Bayes) to evaluate the neural representation of specific concepts related to suicide. This study opens a window into the brain and mind which helps to know how a suicidal individual thinks about suicide and emotion-related concepts. This innovative approach helps in assessing psychiatric disorders. The study was published in the journal Nature Human behaviour.
For the study, two groups of 17 people with suicidal tendencies (suicidal ideators) and 17 neurotypical individuals (control group) were selected and presented with a list of 10 death-related words, 10 words are related to positive ideas (e.g. carefree) and 10 words related to negative ideas (e.g. trouble). Then the machine-learning algorithm was applied to six word-concepts (death, cruelty, trouble, carefree, good and praise) and this program was able to identify whether an individual was from suicidal ideator group or control group with 91% accuracy. A similar program was applied focusing only on the suicidal ideators and the program was able to distinguish the nine who attempted suicide with 94% accuracy. Researchers are hopeful that these basic cognitive neuroscience research findings can be used to save lives.
Marcel A. Just said, “The benefit of this latter approach, sometimes called explainable artificial intelligence, is more revealing of what discriminates the two groups, namely the types of emotions that the discriminating words evoke”, “People with suicidal thoughts experience different emotions when they think about some of the test concepts. For example, the concept of ‘death’ evoked more shame and more sadness in the group that thought about suicide. This extra bit of understanding may suggest an avenue to treatment that attempts to change the emotional response to certain concepts.”
More Information: Marcel Adam Just, “Machine learning of neural representations of suicide and emotion concepts identifies suicidal youth”, Nature Human Behaviour (2017). www.nature.com/articles/s41562-017-0234-y