Digital technologies like smartphones and machine learning have revolutionized education. At the McGovern Brain Institute's Spring 2024 Symposium, “Transformative Strategies for Mental Health,” experts from a variety of scientific disciplines, including psychiatry, psychology, neuroscience, and computer science, agreed that these technologies could also play a key role in advancing the diagnosis and treatment of mental health disorders and neurological diseases.
The symposium, co-hosted by the McGovern Institute, MIT Open Learning, MacLean Hospital, the MIT Poitras Center for Research on Mental Illness, and the Wellcome Trust, sounded the alarm about the rise in mental health issues and introduced new diagnostic and treatment options.
John Gabrieli, Grover Herman Professor of Health Sciences and Technology at MIT, opened the symposium by calling for an effort comparable to the Manhattan Project, in which leading scientists came together in the 1940s to accomplish something that seemed impossible. While the mental health challenge is quite different from the Manhattan Project, Gabrieli emphasized that the complexity and urgency of the problem are similar. In his subsequent talk, “How Science Can Help Psychiatry Improve Mental Health,” he noted that teen suicide deaths increased 35 percent between 1999 and 2000, and emergency room visits for young people ages 5 to 18 who had attempted suicide or experienced suicidal thoughts increased 100 percent between 2007 and 2015.
“There's no moral ambiguity here, but all of us who are speaking today are holding this conference because we feel this urgency,” said Gabrieli, a professor of brain and cognitive sciences, director of MIT Open Learning's Integrated Learning Initiative (MITili), and a member of the McGovern Institute. “To make a difference, we have to do something together with the scientific community as all sorts of partners.”
Urgent Issues
In 2021, U.S. Surgeon General Vivek Murthy issued recommendations about the rise in mental health issues among youth, and in 2023 released another warning about the impact of social media on young people's mental health. At the symposium, Susan Whitfield Gabrieli, a research fellow at the McGovern Institute and professor of psychology and director of the Center for Biomedical Imaging at Northeastern University, cited these recent recommendations, saying they underscore the need to “innovate new ways of intervention.”
Other speakers at the symposium also highlighted evidence that mental health problems are on the rise among youth and adolescents. Christian Webb, an associate professor of psychology at Harvard Medical School, said that by the end of adolescence, 15 to 20 percent of teenagers will experience at least one episode of clinical depression, with girls at highest risk. He added that the majority of young people who experience depression don't receive treatment.
Adults with mental health problems also need new interventions. Antidepressants have limitations in their efficacy, said John Crystal, Robert L. McNeill Jr. Professor of Translational Research and Chair of Psychiatry at the Yale School of Medicine. Antidepressants typically take about two months to work for patients. People with treatment-resistant depression have a 75 percent chance of relapsing within the first year of starting an antidepressant. Treatments for other mental health disorders, such as bipolar disorder and psychotic disorders, can have serious side effects that can cause patients to abandon treatment, said Virginie Anne Chouinard, research director at MacLean OnTrackTM, the first-episode psychosis program at MacLean Hospital.
New treatments, new technologies
Emerging technologies such as smartphone technology and artificial intelligence are key interventions shared by speakers at the symposium.
In a talk on AI and the brain, Dina Katabi, the Tuan and Nicole Pham Professor of Electrical Engineering and Computer Science at MIT, talked about new ways to detect diseases like Parkinson's and Alzheimer's. Early-stage research includes developing devices that can analyze how movement in space affects the electromagnetic fields around us, as well as ways to detect breathing and sleep stages with radio signals.
“This may sound like a pipe dream,” Katabi says, “but it's not. This device is now made possible by the neural network and AI revolution, and is being used by real patients.”
Parkinson's disease often goes undiagnosed until significant damage has occurred. In a series of studies, Katabi's team collected nighttime breathing data and trained a custom neural network to detect the onset of Parkinson's disease. They found that the network was more than 90 percent accurate. The team then used AI to analyze two sets of breathing data collected from patients six years apart. Could the custom neural network identify patients who weren't diagnosed with Parkinson's disease at their first appointment, but were later diagnosed? The answer was mostly yes, with machine learning able to identify 75 percent of patients who would go on to receive a diagnosis.
Early identification of high-risk patients can make a big difference in intervention and treatment. Similarly, research by Jordan Smoller, professor of psychiatry at Harvard Medical School and director of the Center for Precision Psychiatry at Massachusetts General Hospital, demonstrated that an AI-powered suicide risk prediction model could detect 45% of suicide attempts and deaths with 90% accuracy, about two to three years in the future.
Other presentations, including a series of lightning talks, shared new and emerging treatments such as the use of ketamine in treating depression, the use of smartphones including daily text surveys and mindfulness apps in treating adolescent depression, metabolic interventions for psychiatric illnesses, the use of machine learning to detect impairment due to THC intoxication, and family-focused rather than individual therapy for adolescent depression.
Deepen your understanding
The frequency and severity of adverse mental health events in children, adolescents and adults demonstrates the need for funding mental health research and the open sharing of research findings.
Neil Boyce, head of mental health field building at the Wellcome Trust, a global charitable foundation that uses science to solve urgent health problems, said the foundation's funding philosophy is to support research that is “collaborative, coherent and focused”, focusing “on what matters most to those most affected”. Wellcome research managers Anum Farid and Tayla MacLeod highlighted the importance of projects involving people with lived experience of mental health issues, and “blue sky thinking” that can take risks and advance understanding in innovative ways. Wellcome requires that all published research resulting from its funding be open and accessible to maximise its benefits.
Symposium speakers agreed that transformative approaches to mental health, whether through therapeutic models, medications or machine learning, require collaboration and innovation.
“Understanding mental health requires an understanding of the incredible diversity of human beings,” Gabrieli says. “We must use all the tools we have to develop new treatments that work for people for whom traditional treatments don't work.”
