With the help of AI, we may soon measure depression changes similar to how we track blood pressure, according to a new research published in the renowned scientific journal Nature.
In the study conducted by scientists from the Georgia Institute of Technology, Emory University School of Medicine, and the Icahn School of Medicine, ten patients participated in deep brain stimulation (DBS) therapy for six months.
While previous DBS results were diverse, these scientists used electrode implants and AI analysis to track changes in the patients' brain activity brought about by DBS.
Through this, they were able to find a brain signal that serves as an indicator of when DBS therapy works and when it doesn't, proving to have an estimated 90% accuracy.
"Nine out of 10 patients in the study got better, providing a perfect opportunity to use a novel technology to track the trajectory of their recovery," Dr. Helen Mayberg of Icahn School of Medicine explained.
"Our goal is to identify an objective, neurological signal to help clinicians decide when, or when not, to make a DBS adjustment," she added.
AI’s Role in DBS
The AI was trained using the brain images of each patient at the start and end of the six-month experimental therapy.
Through this, the technology was able to identify differences in the brain that would otherwise be difficult for humans to see, providing scientists, doctors, and researchers with more accurate readings of the data.
Furthermore, it was able to help detect signs of relapse among patients, giving leeway for the DBS treatment to be adjusted to prevent it.
"This study also gives us an amazing scientific platform to understand the variation between patients, which is key to treating complex psychiatric disorders like treatment-resistant depression," Georgia Institute's Christopher Rozell shared.
The Future of Medicine Is AI
With its ability to process large volumes of complex data and perform in-depth analysis in an instant, AI has become a prominent tool for practitioners to obtain accurate insights, identify patterns that might go unnoticed by human observation, and optimize decision-making processes through its predictive capabilities.
Marinka Zitnik, assistant professor of biomedical informatics at Harvard Medical School, said she is excited not only for AI's contribution to scientific understanding but also its ability to generate knowledge on its own.
"For example, this could be the discovery of a molecule to treat Alzheimer’s disease. Such a discovery would require identifying indirect relationships across publications and disciplines — chemistry, biology, medicine — connecting chemical properties of molecules to biologic behavior of molecular pathways implicated in Alzheimer’s disease and then to clinical phenotypes and patients’ symptoms," she explained.
Additionally, Zitnik noted that doing this would be impossible for humans. “We hope that in the future scientists will spend less time doing routine laboratory work and more time guiding, accessing, and evaluating AI hypotheses and steering AI models toward the research questions they’re interested in,” she concluded.
Edited by Nikola Djuric