NIMH awards grant to Vanderbilt for AI suicide study
The National Institute of Mental Health has awarded researchers at Vanderbilt University Medical Center a $2.7 million grant to study the use of artificial intelligence for the prediction of suicide risk.
The National Institute of Mental Health has awarded researchers at Vanderbilt University Medical Center a $2.7 million grant to study the use of artificial intelligence for the prediction of suicide risk.
VUMC investigators will leverage predictive algorithms previously developed using machine learning and electronic health record data to assign suicide risk scores to thousands of genotyped patients.
“In this study, we tackle two key challenges,” says principal investigator Colin Walsh, MD, VUMC assistant professor of biomedical informatics, medicine and psychiatry and behavioral sciences. “First, we know that many cases of suicidal thoughts and behaviors are missed if we rely on structured data alone. In one study, suicidal thoughts were only coded 3 percent of the time, even when documented in text in primary care.
VUMC-CROP.jpg
“Second, text features extracted through natural language processing of physician notes, patient messages and more should allow us to improve our predictive algorithms by capturing more complete and nuanced risk factors,” adds Walsh.
The five-year NIMH grant is intended to predict suicidal ideation and suicide attempt by tapping into routine EHRs—including clinician notes—as well as data from a Vanderbilt and UK biobank.
Researchers will leverage Vanderbilt’s BioVU, the world’s largest repository of human DNA stored at a single site, which is linked to de-identified health records. In addition, colleagues from Stanford University will use data from the UK Biobank to conduct genetic analyses of suicidal ideation risk in a second population.
“Expanding our capture of suicidal phenotypes will enable improved understanding of the genetic architecture of suicidal thoughts and behaviors and the contributing genetic and clinical risk factors,” said principal investigator Douglas Ruderfer, VUMC assistant professor of medicine, psychiatry and behavioral sciences and biomedical informatics.
“While most individuals who consider suicide do not attempt it, we know ideation is an important risk factor and, if identified, could provide a flag for patients whom we might be able to help,” adds Ruderfer.
VUMC investigators will leverage predictive algorithms previously developed using machine learning and electronic health record data to assign suicide risk scores to thousands of genotyped patients.
“In this study, we tackle two key challenges,” says principal investigator Colin Walsh, MD, VUMC assistant professor of biomedical informatics, medicine and psychiatry and behavioral sciences. “First, we know that many cases of suicidal thoughts and behaviors are missed if we rely on structured data alone. In one study, suicidal thoughts were only coded 3 percent of the time, even when documented in text in primary care.
“Second, text features extracted through natural language processing of physician notes, patient messages and more should allow us to improve our predictive algorithms by capturing more complete and nuanced risk factors,” adds Walsh.
The five-year NIMH grant is intended to predict suicidal ideation and suicide attempt by tapping into routine EHRs—including clinician notes—as well as data from a Vanderbilt and UK biobank.
Researchers will leverage Vanderbilt’s BioVU, the world’s largest repository of human DNA stored at a single site, which is linked to de-identified health records. In addition, colleagues from Stanford University will use data from the UK Biobank to conduct genetic analyses of suicidal ideation risk in a second population.
“Expanding our capture of suicidal phenotypes will enable improved understanding of the genetic architecture of suicidal thoughts and behaviors and the contributing genetic and clinical risk factors,” said principal investigator Douglas Ruderfer, VUMC assistant professor of medicine, psychiatry and behavioral sciences and biomedical informatics.
“While most individuals who consider suicide do not attempt it, we know ideation is an important risk factor and, if identified, could provide a flag for patients whom we might be able to help,” adds Ruderfer.
More for you
Loading data for hdm_tax_topic #better-outcomes...