A simple machine encyclopedism algorithm is able-bodied to identifysuicidal peopleby analyzing the thing they say , researchers bring out in the journalSuicide and Life - Threatening Behavior .
“ destruction by felo-de-se demonstrates profound personal hurt and social failure , ” explain the study authors , who trust to see their new approach used to help health professional assist those who are at risk of developing self-destructive tendencies .
“ This methodology easily can be extend to school day , shelters , youth clubs , puerile Justice Department centre , and residential area centers , where early identification may help to reduce self-destruction endeavor and Death , ” said study co - writer John Pestian in astatement .
To test their algorithm , the team recruited 379 participants , some of whom had been diagnosed assuicidal , while others were mentally ill but not suicidal and some were neither . Each patient was then require a serial publication of questions such as “ does it hurt emotionally ? ” , “ do you have any fear ? ” , and “ do you have hope ? ”
By registering what each individual said in reply to these questions , as well as their tone of voice , the computer was capable to identify which of the three category they fall into , with an accuracy of 85 percent .
It was particularly successful at recognizing those who were suicidal , achieving a 93 per centum accuracy for this group .
Though the algorithm was plan to peck up on a chain of verbal and non - verbal cues , the study authors reveal that certain tell - tale sign helped the electronic computer to dispatch its job . For example , those with no mental malady orsuicidal behaviors“tended to express mirth more during interviews , suspire less , and express less ire , less emotional pain , and more hope . ”
According to Pestian , the results of this survey provide evidence of the value that technology can bring to self-annihilation care . “ When you face around health aid readiness , you see tremendous reinforcement from technology , but not so much for those who give care for mental illness , ” he read . “ Only now are our algorithms capable of supporting those caregivers . ”
