When assessing mental health problems, AI tools really have to beat human doctors.

Release date: 2016-12-28

Editor's Note: According to a survey by the National Institutes of Health, approximately 20% of adolescents in the United States have mental health problems. But the tools used by mental health professionals are becoming more intelligent, and they use artificial intelligence to diagnose patients, and the results are usually more accurate than human diagnosis. The author Peter Rejcek has decades of experience in science journalism.

A study published in the journal Suicide and Life-threatening Behavior showed that machine learning accuracy was as high as 93% when identifying suicidal tendencies in patients. The study was led by John Pestian, a professor at the Cincinnati Children's Hospital Medical Center, and involved 379 adolescents from three regional hospitals. According to the university's press release, each patient completed a standard behavioral level assessment and participated in a semi-structured interview, answering five open questions. The researchers analyzed the tester's voiced and nonverbal behavior, and then used machine learning algorithms to get accurate results, to determine whether the tester had suicidal tendencies, whether there was mental illness but no suicidal tendency, and other possibilities.

In his press release, Pentian said that these calculations are technically indispensable for the protection and prevention of suicidal behavior. According to the American Society of Suicide Studies, suicide was the tenth leading cause of death in the United States in 2014, but it is the second leading cause of death among people aged 15 to 24.

A recent study published in the Psychological Bulletin further highlights the need for social tools to prevent suicide. A meta-analysis of 365 studies conducted over the past 50 years found that mental health experts predict that a person's probability of attempting suicide is almost a random probability.

Harvard University writer Joseph Franklin said in an email to Singularity Hub that one of the main reasons for this is that researchers almost always use a single factor (such as a diagnosis of depression) to predict such events. The complex nature behind this patient's thoughts and behaviors requires consideration of dozens or even hundreds of factors to make accurate predictions.

In a submission to Psychological Medicine earlier this year, Franklin et al. stated that machine learning and related technologies are ideal for mental health treatment. Search engines that use only one factor to return results are ineffective, as are attempts to predict suicidal behavior.

Researchers in Boston, including his Harvard colleague Matthew K. Nock, used machine learning to predict suicidal behavior with an accuracy of 70%-85%. However, the research is still in its infancy and the sample size is small.

Franklin added:

The work of the Pestian team is also very interesting, and the audio mode/natural language processing methods they use are unique in this area. Although there are some limitations, their research is a radically different innovation from what the researchers have been doing for the past 50 years.

According to Franklin, machine learning has not yet been used in treatment, and most conventional methods of treating suicidal mental illness are lacking. Even if several cutting-edge organizations are about to master AI technology that accurately predicts suicidal behavior across the healthcare system, we don't know how to help those who put themselves at risk to reduce risk.

To this end, Franklin and colleagues developed a free app called Tec-Tec that seems to be effective in reducing self-harm and suicidal behavior. The application is based on a psychological technique called evaluative conditioning that changes the association of certain objects and concepts by constantly pairing certain words and images. In game-like design, Tec-Tec attempts to change the association of factors that may increase the risk of self-injury.

Franklin et al. are conducting other experiments and hope to create an app for everyone through machine learning and connect with the patients who need it most.

Capturing the language of patients with schizophrenia

Last year, in a study published in the journal Schizophrenia, researchers also used machine learning algorithms to predict the outcomes of late-onset neuropathies in high-risk youth. Thirty-four participants were assessed quarterly during the two-and-a-half-year test period.

The automatic analysis method evaluates the consistency and speech complexity of the interview transcript according to the conditions and the number of sentences answered by the tester.

The computer predicts the subsequent psychotic development of the tester by analyzing the linguistic features, and the accuracy rate is 100%, which is better than the clinical interview. The article stated that the latest advances in computer science in natural language processing have laid the foundation for the future development of psychiatric clinical trials.

Early diagnosis of attention deficit hyperactivity disorder (ADHD)

In a ongoing project, scientists from the University of Texas at Arlington (UTA) and Yale University have designed an artificial intelligence system that combines computing power and psychiatry to assess ADHD in adolescents. According to the Centers for Disease Control and Prevention, the prevalence of children and adolescents between the ages of 8 and 15 is as high as 8.5%.

According to UTA's press release, the study uses "the latest methods of computer vision, machine learning, and data mining" to evaluate children's attention during their physical and physical exercises, by testing their attention, decision-making, and emotions. Manage the capabilities and analyze the data to determine the type of intervention.

Professor Fillia Makedon of the UTA Department of Computer Science and Engineering stated:

We believe that this method of calculation will provide us with quantifiable early diagnosis methods and help us monitor progress. In particular, children can help them overcome their learning difficulties and let them enjoy a healthy and fulfilling life.

Pay close attention to people with autism

At the same time, a team at the State University of New York at Buffalo developed a mobile app that detects autism spectrum disorder (ASD) at the age of two, with an accuracy rate of nearly 94%. The findings were published at the recent IEEE Wireless Health Conference.

Eye movements in ASD patients are usually different from those in other people's eyes. The app tracks the child's eye movements as the child views the social scene image, such as viewing photos with multiple people.

According to the Centers for Disease Control and Prevention, about one in every 68 children in the United States is diagnosed with ASD. The current research project at the State University of New York involves 32 children between the ages of 2 and 10 who plan to expand their research in the future.

The app's testing takes only 1 minute and can be done at home with the help of a parent to determine if the child needs a professional assessment.

Xu Wenyao, an assistant professor at the School of Engineering and Applied Science at the State University of New York, believes that this technology bridges the gap between autism and diagnosis and treatment.

Source: 36氪