How Machines Can Help Identify Suicidal Behaviour

Suicidal Behaviour
Suicidal Behaviour

Machine learning gives the computer the ability to learn without programming explicitly. Various scientists taking advantages of it. Similarly, Scientists from the Cincinnati Children’s Hospital Medical Center suggest that new computer tools can identify person’s suicidal behaviour. This new study shows that computer technology known as machine learning can classify 93 percent accurate a suicidal person. It can 85 percent accurate identify a person who is suicidal, has a mental illness but is not suicidal, or neither.

Professor John Pestian said, “Such advanced technology provides us with a strong evidence about machine learning.  By using it as a decision supporting tool, clinicians and caregivers can identify and prevent patient’s suicidal behaviour.

READ: Internet addiction may indicate other mental health problems

These computational approaches provide novel opportunities to apply technological innovations in suicide care and prevention. It surely needed. When you look at health care facilities, you see tremendous support from technology. But not so much for those who care for mental illness. Only now are our algorithms capable of supporting those caregivers. This methodology easily can be extended to schools, shelters, youth clubs, juvenile justice centres, and community centres, where earlier identification may help to reduce suicide attempts and deaths.

To test the tool, scientists involved 379 patients in the study from emergency departments and inpatient and outpatient centres at three sites. The patients were suicidal, diagnosed as mentally ill and not suicidal, or neither. They were serving as a control group.

During the study, scientists asked some questions to patients. The questions were like: “Do you have hope?” “Are you angry?” and “Does it hurt emotionally?”

READ: TensorFlow – Google’s latest machine learning system

While answering the questions, scientists analysed verbal and non-verbal language of patients from the received data. They then used machine learning to classify the difference with higher accuracy.  Additionally, they noticed that the control patients laughs more during interviews, sigh less, and express less anger, less emotional pain and more hope.