An algorithm studies suicidal intent. And it warns you

by time news

Time.news – There is a research project, unique of its kind, that monitors hundreds of suicidal peopleusing data from smartphones and biosensors to identify periods of high danger for people and thus be able to intervene.

This is reported by the New York Times, which reports the experience of Mrs. Cruz, 29, who left the hospital as part of a vast research project that “attempts to use the advances of artificial intelligence to identify something which has eluded psychiatrists for centuries: preview who might attempt suicide and intervene when most likely that the person does it “.

On her wrist, writes the Times, Ms. Cruz “wears a watch programmed to monitor sleep and physical activity. On his smartphone, an app collects data on his moods, movements and social interactions “and each device provides a continuous flow of information to a team of researchers located on the 12th floor of the William James Building. , which houses the Harvard Department of Psychology.

The Times stresses that never before “in the field of mental health, few new areas generate as much excitement as machine learningwhich uses computer algorithms to better predict human behavior “while” at the same time, there is a growing interest in biosensors capable of tracking a person’s mood in real time, taking into account musical choices, posts on social media, facial expressions, vocal expressions “.

The research aims “to transform these technologies into a sort of preventive warning system that could be used when a patient at risk is discharged from the hospital”.

The American newspaper, however, is skeptical: “There are many reasons to doubt that an algorithm will ever achieve this level of accuracy – he comments -, suicide is such a rare event, even among those at the highest risk, that any effort to predict it is bound to produce false positives, forcing action on people who may not need it.

False negatives, on the other hand, could place the legal responsibility on doctors. Algorithms require long-term granular data for large numbers of people and it is almost impossible to observe them all while attempting suicide. ” Finally, he notes, “the data necessary for this type of monitoring raise doubts about the protection of the privacy of some of the most vulnerable people in society”.

As for Ms. Cruz, on the other hand, she was studying for a nursing degree when the mental health crisis has sent her life into a tailspinbut – writes the Times – she was immediately intrigued by the experience and “answered diligently six times a day, when the apps on her phone questioned her about her suicidal thoughts”.

The sounds were intrusive, but also comforting: “I felt like I wasn’t being ignored,” she confessed, “having someone who knows how I feel takes a lot of weight away.”

You may also like

Leave a Comment