Using a patient's own words, machine learning automatically identifies suicidal behavior

November 07, 2016

CINCINNATI -- Using a person's spoken or written words, new computer tools can identify with great accuracy whether that person is suicidal, mentally ill but not suicidal, or neither.

A new study shows that computer technology known as machine learning is up to 93 percent accurate in correctly classifying a suicidal person and 85 percent accurate in identifying a person who is suicidal, has a mental illness but is not suicidal, or neither. These results provide strong evidence for using advanced technology as a decision-support tool to help clinicians and caregivers identify and prevent suicidal behavior, says John Pestian, PhD, professor in the divisions of Biomedical Informatics and Psychiatry at Cincinnati Children's Hospital Medical Center and the study's lead author.

"These computational approaches provide novel opportunities to apply technological innovations in suicide care and prevention, and it surely is needed," says Dr. Pestian. "When you look around 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 centers, and community centers, where earlier identification may help to reduce suicide attempts and deaths."

The study is published in the journal Suicide and Life-Threatening Behavior, a leading journal for suicide research.

Dr. Pestian and his colleagues enrolled 379 patients in the study between Oct. 2013 and March 2015 from emergency departments and inpatient and outpatient centers at three sites. Those enrolled included patients who were suicidal, were diagnosed as mentally ill and not suicidal, or neither - serving as a control group.

Each patient completed standardized behavioral rating scales and participated in a semi-structured interview answering five open-ended questions to stimulate conversation, such as "Do you have hope?" "Are you angry?" and "Does it hurt emotionally?"

The researchers extracted and analyzed verbal and non-verbal language from the data. They then used machine learning algorithms to classify the patients into one of the three groups. The results showed that machine learning algorithms can tell the differences between the groups with up to 93 percent accuracy. The scientists also noticed that the control patients tended to laugh more during interviews, sigh less, and express less anger, less emotional pain and more hope.
-end-


Cincinnati Children's Hospital Medical Center

Related Mental Illness Articles from Brightsurf:

Mental illness, mental health care use among police officers
A survey study of Texas police officers examines how common mental illness and mental health care use are in a large urban department.

Hospitals miss mental illness diagnosis in more than a quarter of patients
Severe mental illness diagnoses are missed by clinicians in more than one quarter of cases when people are hospitalised for other conditions, finds a new study led by UCL researchers, published in PLOS Medicine.

Young migrants at risk of mental illness
Experience of trauma, abuse and poverty puts the mental health of many young refugees at risk.

Chronic illness in childhood linked to higher rates of mental illness
Children with long-term health conditions may be more likely to experience mental illness in early adolescence than healthy children, according to new research from Queen Mary University of London.

Did 'Joker' movie perpetuate prejudices against those with mental illness?
Researchers in this survey study examined whether watching the 2019 movie 'Joker,' in which the namesake character is violent and has mental illness, was associated with a change in the level of prejudice toward people with mental illness compared with others who watched another movie.

Skills training opens 'DOORS' to digital mental health for patients with serious mental illness
Digital technologies, especially smartphone apps, have great promise for increasing access to care for patients with serious mental illness such as schizophrenia.

Research calls for new measures to treat mental illness and opioid use
Opioid use among psychiatric hospital patients needs to be addressed through an integrated approach to managing mental illness, pain and substance use, a study by researchers at the University of Waterloo has found.

Researchers challenge myth of the relationship between mental illness and incarceration
Researchers examined the relationship between psychiatric diagnoses and future incarceration by merging data from psychiatric interviews that took place in the 1980s with 30 years of follow-up data.

New research raises important questions on how mental illness is currently diagnosed
This research raises questions as to whether current diagnoses accurately reflect the underlying neurobiology of mental illness.

Young teens of color more likely to avoid peers with mental illness
Students identifying as black or Latino are more likely to say they would socially distance themselves from peers with a mental illness, a key indicator of mental illness stigma, according to research published by the American Psychological Association.

Read More: Mental Illness News and Mental Illness Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.