Last updated November 14, 2017 at 8:22 am
A combination of brain imaging and artificial intelligence could help to distinguish patients with suicidal thoughts from non-suicidal individuals, scientists at Carnegie Mellon University, Pittsburgh, say.
They presented suicidal patients and control individuals undergoing functional magnetic resonance imaging (fMRI) scans with death- and life-related words.
Neural activity in response to six words (death, cruelty, trouble, carefree, good and praise) and in five brain locations best discriminated between the suicidal patients and controls, they found.
If their small-sample study can be replicated, it could represent a significant advance in the difficult task of diagnosing psychiatric disorders.
But there is some scepticism about the limitations to the study.
“The findings contribute to a growing body of research suggesting that ‘biological markers’ can be equally, if not more useful than subjective measures (for example, a patient’s own report of their feelings), in psychiatric decision making,” said Associate Professor Sarah Whittle from the Melbourne School of Psychological Sciences at The University of Melbourne.
“The research, however, is a long way from having an impact on the actual treatment of suicidal individuals.”
The assessment of suicide risk is among the most challenging problems facing doctors.
“Predictions by both clinicians and patients of future suicide risk have been shown to be relatively poor predictors of future suicide attempt,” the researchers write in the study published by Nature Human Behaviour.
“In addition, suicidal patients may disguise their suicidal intent as part of their suicidal planning or to avoid more restrictive care.”
After measuring neural response to the words, Marcel Just, David Brent, and colleagues then trained a machine-learning algorithm to use the information to identify which participants were patients and which were controls.
The algorithm correctly identified 15 of 17 patients as belonging to the suicide group and 16 of 17 healthy individuals as belonging to the control group.
The authors then divided the suicidal patients into two groups: those who had attempted suicide (nine participants) and those who had not (eight participants).
The authors trained a new algorithm that correctly distinguished between suicide attempters and non-attempters in 16 out of 17 cases.
But the research presents some difficulties, experts say.
“For one, there were a small number of participants in the study, and most were male. Therefore, we don’t know how reliable the results might be, or if they apply to females,” Whittle said.
“Also, the suicidal young adults were more depressed and anxious than the non-suicidal adults. So, we don’t know if the researchers’ have found biological markers of suicidality, or psychiatric problems more generally.”
Professor Max Coltheart, Emeritus Professor of Cognitive Science from Macquarie University, said the study was missing a vital check.
“Even when you have found a way of classifying people into two groups on the basis of analysing brain imaging data, you cannot claim that you have a genuine method for doing such classification unless you show that the artificial intelligence algorithm can successfully classify a new set of people on whom it has not been trained,” he said.
Professor Matthew Large from the School of Psychiatry at the University of New South Wales agreed there could be potential in the technique.
“Suicide risk assessment works notoriously badly and it might be very useful to have some sort of test for future suicide,” he said.
However, he said the study should be seen in the light of two major limitations.
“First, it is entirely unsurprising that the very many data points produced by functional magnetic imaging can be used to retrospectively classify a very small sample of patients,” he said.
“Any excitement about this should await replication in a larger, untested group of people.
“Second, even if suicide thoughts could be reliably determined by a machine, suicide thoughts themselves are only weakly associated with suicide attempts and are of next to no value in predicting who will and will not suicide.”