Leading US supercomputer supports mental health research
During the pandemic, the crucial role of high performance computing and artificial intelligence in the treatment of disease has become very clear. Even though viral illness is squarely in the crosshairs of supercomputing, mental illness has remained relatively foreign to the world of computational medicine. Now, a collaboration between Oak Ridge National Laboratory (ORNL), Cincinnati Children’s Hospital, the University of Cincinnati, and the University of Colorado seeks to change that, working with the largest supercomputer in the United States. to try to better understand the development of mental disorders. health in children.
“Even before the onset of the COVID-19 pandemic, it was clear that today’s children are experiencing unprecedented levels of stress which has led to a steep rise in many types of mental disorders,” explained John Pestian, professor of paediatrics, psychiatry and biomedical informatics. at the Cincinnati Children’s Hospital Medical Center, in an interview with HPCwire. “The disruptions, isolations and personal losses caused by the pandemic have only made things worse for children. … Unfortunately, compared to other areas of medical care, innovations in mental health treatment have not kept pace with significant technological advances, such as the rapid growth of computing power.
Pestian, along with dozens of colleagues, works to leverage a vast collection of health data to gain valuable insights into how children’s mental health develops and what factors affect different outcomes. But conducting this type of research, on this scale, involved mobilizing significant computing resources.
Fortunately, Pestian is also a joint faculty member with ORNL, host of Summit, the nation’s most powerful publicly ranked supercomputer. The IBM-built system, rolled out in 2018, still ranks second on the global list of the world’s 500 most powerful supercomputers.
“We are working with Oak Ridge National Laboratory…to develop the first decision support tool that can analyze all of the many important factors that can put a child on the path to becoming an adult with severe anxiety, depression or suicidal ideation,” Pestian said. . “We are working to train [Summit] how to weigh an extremely complex set of factors, which will combine data on an individual’s genetic traits, medical history, environmental exposures, demographics and other social determinants of health with their speech patterns, body language and other behaviors.
“From there, we’re looking to calculate a child’s mental health trajectory, much like the curves used in a pediatric growth chart that show where a child is in relation to standards for weight, height, etc. .”, he continued. “Ultimately, clinicians, counselors and others could use this information to decide when and how to intervene with services that may prevent early mental illness from continuing into adulthood.”
Pestian explained that establishing this type of trajectory relies on “thousands of contributing factors working with each other as the child grows,” assembled using anonymized data from medical records. electronic data from millions of patient encounters, which are supplemented with overlaid data on the local environment. living conditions, socio-economic status and other external factors. Pestian said that as the research continues, they will also start incorporating genetic variant data.
This research, of course, is far beyond the capabilities of hospital computer systems, let alone the workstations available to psychiatrists.
“We need to use a supercomputer to begin to understand the network activity that runs through our brains,” Pestian said. “The task is at least as complex as tracing pathways through galaxies with billions of stars. … Through our unique collaboration with Oak Ridge, we can combine our clinical and computational expertise to develop near real-time visualizations patient-specific mental health trajectories This will identify patients with clinically elevated symptoms earlier and connect them to services, leading to better outcomes and quality of life.
The team’s research is still in its early stages, but Pestian is excited about the promise it holds for the future of mental health.
“Currently, we are training the algorithm and we plan to publish more of our progress in peer-reviewed scientific journals,” he said. “Within a few months to a year, we hope to have a first trajectory tool available for certain clinicians to evaluate. As the system is refined, we plan to obtain the necessary approvals to develop and deploy the tool. Although the process may still take years, it is now becoming possible thanks to the vast amounts of data that are becoming available through digital medical records and advances in artificial intelligence-based algorithms. This collaboration truly reflects a new era in mental health research.