Blood tests and app may predict suicide risk

Scientists have developed blood tests and a new app which may predict the risk of suicides with more than 90 per cent accuracy in people being treated for bipolar disorder and other psychiatric illnesses.
"We believe that widespread adoption of risk prediction tests based on these findings during health-care assessments will enable clinicians to intervene with lifestyle changes or treatments that can save lives," said Alexander B Niculescu III, professor at the Indiana University School of Medicine and research and development investigator at the Richard L Roudebush Veterans Affairs Medical Centre.
People being treated for bipolar disorder and other psychiatric illnesses are at greater risk of attempting suicide.

Using RNA biomarkers from blood samples along with a newly developed questionnaires in the form of an app, the researchers were able to predict which individuals in a group of patients being seen for a variety of psychiatric illnesses would experience significant suicidal ideation with approximately 92 per cent accuracy.
Among patients with bipolar disorder, the accuracy reached 98 per cent, Niculescu said.
The combination of biomarkers and app was also accurate in predicting which of the patients would be hospitalised for suicidality in the year following testing (71 per cent across all diagnoses, 94 per cent for bipolar disorder).

The questionnaires by themselves, implemented as apps on tablets, were able to predict the onset of significant suicidal thoughts with more than 80 per cent accuracy.

The study began with a group of 217 male psychiatric participants, followed by Niculescu and colleagues for several years with diagnoses of bipolar disorder, major depressive disorder, schizoaffective disorder, and schizophrenia.
The researchers identified 37 participants who switched from no suicidal ideation to high suicidal ideation at different testing visits.
The scientists were able to identify RNAs that were present at different levels in blood samples taken at those different testing visits, in common across these 37 individuals.

Those candidate biomarkers were then evaluated to prioritise the best markers. Next, the researchers validated those prioritised biomarkers using blood samples from 26 men who had committed suicide.
Finally, the researchers used blood samples and medical records from a different group of patients with the same psychiatric diagnoses to confirm that the biomarkers and apps predicted suicidal ideation, and also examined their ability to predict future hospitalisations for suicidality in the first year following testing.
One of the apps assesses measures of mood and anxiety; the other asks questions related to life issues including physical and mental health, addictions, cultural factors and environmental stress.

The study was published in the journal Molecular Psychiatry.