Digital technologies similar to smartphones and machine learning have revolutionized education. At the McGovern Institute for Brain Research's 2024 Spring Symposium on “Transformational Strategies in Mental Health,” experts from all scientific disciplines – including psychiatry, psychology, neuroscience, computer science, and others – agreed that these technologies could also play a vital role in advancing the diagnosis and treatment of mental disorders and neurological diseases.
The symposium, co-hosted by the McGovern Institute, MIT Open Learning, McClean Hospital, the Poitras Center for Psychiatric Disorders Research at MIT, and the Wellcome Trust, warned of the increasing prevalence of mental health problems and highlighted the potential of latest diagnostic and treatment methods.
John Gabrieli, MIT's Grover Hermann Professor of Health Sciences and Technology, opened the symposium by calling for an initiative on par with the Manhattan Project, which brought together leading scientists within the Forties to attain the seemingly inconceivable. While mental health presents a really different challenge, Gabrieli stressed, the complexity and urgency of the issue are similar. In his later talk, “How can the science of psychiatry help improve mental health?” he pointed to a 35 percent increase in teen suicide deaths between 1999 and 2000 and a 100% increase in emergency room visits by youth ages 5 to 18 who had experienced a suicide attempt or suicidal thoughts between 2007 and 2015.
“We haven’t any moral doubts, but all of us speaking today are holding this meeting partly because we feel this urgency,” said Gabrieli, who can also be a professor of brain and cognitive sciences, director of the Integrated Learning Initiative (MITili) at MIT Open Learning, and a member of the McGovern Institute. “We must work together as a community of scientists and partners of every kind to make a difference.”
An urgent problem
In 2021, U.S. Surgeon General Vivek Murthy issued a warning concerning the rise in mental health problems amongst adolescents; in 2023, he issued one other warning concerning the impact of social media on adolescent mental health. At the symposium, Susan Whitfield-Gabrieli, a research fellow on the McGovern Institute and professor of psychology and director of the Biomedical Imaging Center at Northeastern University, cited these recent warnings, saying they underscore the necessity to “develop recent methods of intervention.”
Other speakers on the symposium also pointed to growing mental health problems amongst teens and adolescents. Christian Webb, associate professor of psychology at Harvard Medical School, said that 15 to twenty percent of all teenagers have experienced at the least one episode of clinical depression by the top of adolescence, with girls being most in danger. Most teens who are suffering from depression don’t receive treatment, he added.
Adults with mental health problems also need recent treatments. John Krystal, Robert L. McNeil Jr. Professor of Translational Research and chair of the Department of Psychiatry at Yale University School of Medicine, pointed to the limited effectiveness of antidepressants, which generally take about two months to take effect. Patients with treatment-resistant depression have a 75 percent likelihood of relapse inside a yr of starting antidepressants. Treatments for other mental disorders, including bipolar and psychotic disorders, have serious uncomfortable side effects that may prevent patients from adhering to treatment, said Virginie-Anne Chouinard, director of research at McLean OnTrackTM, a first-onset psychosis program at McLean Hospital.
New treatments, recent technologies
New technologies, including smartphone technology and artificial intelligence, play a central role within the contributions of the symposium speakers.
In a chat on AI and the brain, Dina Katabi, the Thuan and Nicole Pham Professor of Electrical Engineering and Computer Science at MIT, discussed recent ways to detect Parkinson's and Alzheimer's, in addition to other diseases. Early research has developed devices that may analyze how movement in a room affects the encircling electromagnetic field, and the way wireless signals can detect respiratory and sleep phases.
“I realize this appears like a dreamland,” Katabi said. “But it's not! This device is getting used by real patients today, made possible by a revolution in neural networks and artificial intelligence.”
Parkinson's often can’t be diagnosed until significant impairment has already occurred. In a series of studies, Katabi's team collected nighttime respiratory data and trained a custom neural network to detect cases of Parkinson's. They found that the network achieved over 90 percent accuracy in its detection. Next, the team used AI to research two sets of respiratory data collected from patients six years apart. Could their custom neural network discover patients who didn’t have a Parkinson's diagnosis at the primary visit but later received one? The answer was mostly yes: Machine learning identified 75 percent of patients who later received a diagnosis.
Early detection of high-risk patients could make a big difference in intervention and treatment. Similarly, a study by Jordan Smoller, professor of psychiatry at Harvard Medical School and director of the Center for Precision Psychiatry at Massachusetts General Hospital, found that an AI-powered model for predicting suicide risk can detect 45 percent of suicide attempts or deaths with 90 percent accuracy, about two to a few years prematurely.
Additional presentations, including a series of lightning talks, highlighted recent and emerging treatments, similar to using ketamine to treat depression, using smartphones (including every day text surveys and mindfulness apps) to treat depression in adolescents, metabolic interventions for psychotic disorders, using machine learning to detect impairments from THC intoxication, and family-centered treatment slightly than individual therapy for depression in adolescents.
Promote understanding
The frequency and severity of negative mental health outcomes in children, adolescents and adults show that mental health research must be funded – and that findings should be shared openly.
Niall Boyce, Head of Mental Health on the Wellcome Trust – a worldwide charitable foundation dedicated to finding scientific solutions to pressing health problems – explained the inspiration's funding philosophy of supporting research that’s “collaborative, coherent and focused” and focuses on “what matters most to those most affected”. Wellcome's research leaders Anum Farid and Tayla McCloud stressed the importance of projects involving individuals with first-hand experience of mental health problems, and of “blue sky pondering” that takes risks and may advance understanding in revolutionary ways. Wellcome requires that every one published research resulting from its funding is open and accessible to maximise its profit.
Whether through therapeutic models, pharmaceutical treatments or machine learning, speakers on the symposium agreed that transformative approaches to mental health require collaboration and innovation.
“To understand mental health, we want to grasp the incredible diversity of individuals,” Gabrieli said. “We need to make use of all of the tools at our disposal today to develop recent treatments that work for people for whom our conventional treatments don't work.”
