Diagnosing Mental Illness With AI

More than half of the people living with an alcohol or substance use disorder also contend with a co-occurring mental health condition. In the field of addiction medicine, it is critical that patients receive screenings for a dual diagnosis. Research indicates, unequivocally, that individuals who do not receive simultaneous treatment for coöccuring disorders while in rehab are unlikely to stay on track working a program of addiction recovery.

Addiction is a treatable mental illness and success depends on treating the whole patient. Attending to a use disorder without addressing a client's comorbidity almost guarantees a relapse down the road. Conversely, when people receive treatment for all of their conditions at once – learning how to manage the symptoms without drugs and alcohol – they can lead productive lives in recovery.

While conditions like depression and bipolar disorder are manageable with the help of evidence-based therapies, there are times when medication is required to keep symptoms at bay. Naturally, there is a multitude of prescription drugs that can help improve people’s life quality. Deciding which drug works best depends entirely on how a patient responds; it is often the case that several different meds are tried before finding the one that works best. The process of finding the right drug for a client can be a challenging task, but technology may one day help things along.

 

Using Artificial Intelligence to Better Diagnose Mental illness

Diagnosing mental illness is a complicated task that can take a significant amount of time; finding the medication that works best for a patient, often takes even longer. Research shows that A.I. has something to offer in the quest for diagnosing and treating mental health disorders. Researchers at Canada’s Lawson Health Research Institute, The Mind Research Network in New Mexico and the Brainnetome Center of the Chinese Academy of Sciences, designed an artificial intelligence algorithm that analyzes brain scans to classify illness in patients with a complex mental illness, PyschCentral reports. What’s more, the algorithm can predict how a patient will respond to a particular medication.

“Antidepressants are the gold standard pharmaceutical therapy for [major depressive disorder] MDD while mood stabilizers are the gold standard for bipolar I,” said Dr. Elizabeth Osuch, a clinician-scientist at Lawson and co-lead investigator on the study. “But it becomes difficult to predict which medication will work in patients with complex mood disorders when a diagnosis is not clear. Will they respond better to an antidepressant or to a mood stabilizer?” 

When the researchers tested their algorithm on 78 adult patients from mental health programs, it correctly classified their illness with 92.4 percent accuracy, according to the article. And, 11 out of 12 participants responded to the medication predicted by the algorithm.

“Patients may also have more than one diagnosis, such as a combination of a mood disorder and a substance abuse disorder, further complicating diagnosis,” said Dr. Osuch. “Having a biological test or procedure to identify what class of medication a patient will respond to would significantly advance the field of psychiatry.”

Co-Occurring Disorder Treatment

If you or a loved one is living with addiction and co-occurring mental illness, please contact Celebrate Hope. We specialize in treating patients with a dual diagnosis and can help you begin a life-changing journey of recovery.