Mayo Clinic researchers study use of AI to predict antidepressant outcomes in youth


News

Mayo Clinic researchers are using artificial intelligence (AI) to help predict early antidepressant treatment outcomes in children and adolescents suffering from major depressive disorder.

For the study published in The Journal of Child Psychology and Psychiatry, researchers with Mayo Clinic’s departments of Molecular Pharmacology and Experimental Therapeutics and Psychiatry and Psychology identified variations in six common symptoms of depression: difficulty having fun, social withdrawal, excessive fatigue, irritability, low self-esteem, and depressed feelings. They then used AI to assess these symptoms with the Children's Depression Rating Scale-Revised to predict outcomes of 10 to 12 weeks of antidepressant pharmacotherapy across two classes of antidepressants.

Arjun Athreya, Ph.D., a Mayo Clinic researcher and lead author of the study, says early results show that:

  • In fluoxetine testing datasets, the six symptoms predicted 10- to 12-week outcomes at four to six weeks, with an average accuracy of 73%.
  • In duloxetine testing datasets, the same six symptoms predicted 10- to 12-week outcomes at four to six weeks, with an average accuracy of 76%.
  • In placebo-treated patients, predicting response and remission accuracy was lower than for antidepressants, at 67%.

The outcomes show the potential of AI and patient data to ensure children and adolescents receive treatment that has the highest likelihood of delivering therapeutic benefits with minimized side effects.

Read more.

Luci Gens

Luci Gens is a senior marketing specialist. She joined Mayo Clinic in 2022 and has over ten years of experience in hospital-based marketing and communications.