Georgia Scientists Receive Grant to Improve Mood Disorder Treatment Tool
A team of Georgia State scientists has received a two-year grant to further develop a tool to help psychiatrists better diagnose and treat mood disorders. The $875,110 grant was provided by the National Institute of Mental Health and it will fund studies that will make it easier for mental health professionals to quickly diagnose and treat mental health conditions with accuracy. The researchers are based at the Center for the Translational Research in Neuroimaging and Data Science (TReNDS).
TReNDS is a tri-institutional effort supported by Georgia State University, Georgia Institute of Technology, and Emory University that is focused on making better use of complex brain imaging data. The grant was awarded to Advanced Biomedical Informatics Group LLC, a startup led by Jeremy Bockholt. The tool the firm will develop is based on research by Vince Calhoun, Distinguished University Professor of Psychology, and a Georgia Research Alliance Eminent Scholar.
Calhoun holds appointments in Electrical and Computer Engineering at Georgia Tech and Neurology and Psychiatry at Emory University and is the founding director of TReNDS. He has collaborated with Calhoun, the leader of the study for more than 15 years. Calhoun and his team plan to use data from functional magnetic resonance imaging (“fMRI”) to allow psychiatrists to more accurately predict how patients will react to medication. Their algorithm would then use machine learning to analyze a patient’s fMRI scan and compare it to scans from thousands of other individuals.
By studying how individuals with the same brain activity reacted to medication, the tool could predict how a patient will likely respond to one medication versus another. This information will help psychiatrists decide which medication to prescribe to patients. At the moment, there are no biologically based clinical tools to diagnose mental illness, with conditions like bipolar disorder taking an average of six to ten years to properly diagnose.
“This tool can give clinicians an objective window into a patient’s brain, helping them make more tailored treatment recommendations. Regardless of the diagnosis, is the patient’s brain more similar to someone who responded better to mood stabilizers or to someone who responded better to antidepressants?” asks Bockholt. The two-year grant will allow the team to refine the algorithm by feeding it additional data, including scans from a diverse group of patients as well as scans from various types of fMRI machines.
Eric Verner, Associate Director of Innovation at TReNDS and Project Co-Investigator, George State University says that “on the previous data set, our tool was over 90% accurate in predicting medication outcomes, so that shows us that we’re on the right track. By training the model on more data, it should perform better on a wider variety of patients.”
“We’re focusing on a patient population that is difficult to diagnose and treat using current methods,” says Calhoun. “It can be hard to know what type of medication is warranted. This could help inform those decisions and get patients on the right medication sooner.”
It would be interesting to see how the functionality of this tool would improve when paired with the systems used to develop customized treatments by biomedical companies like Predictive Oncology (NASDAQ: POAI).
Please see full terms of use and disclaimers on the BioMedWire website applicable to all content provided by BMW, wherever published or re-published: http://BMW.fm/Disclaimer
A team of Georgia State scientists has received a two-year grant to further develop a tool to help psychiatrists better diagnose and treat mood disorders. The $875,110 grant was provided by the National Institute of Mental Health and it will fund studies that will make it easier for mental health professionals to quickly diagnose and treat mental health conditions with accuracy. The researchers are based at the Center for the Translational Research in Neuroimaging and Data Science (TReNDS).
TReNDS is a tri-institutional effort supported by Georgia State University, Georgia Institute of Technology, and Emory University that is focused on making better use of complex brain imaging data. The grant was awarded to Advanced Biomedical Informatics Group LLC, a startup led by Jeremy Bockholt. The tool the firm will develop is based on research by Vince Calhoun, Distinguished University Professor of Psychology, and a Georgia Research Alliance Eminent Scholar.
Calhoun holds appointments in Electrical and Computer Engineering at Georgia Tech and Neurology and Psychiatry at Emory University and is the founding director of TReNDS. He has collaborated with Calhoun, the leader of the study for more than 15 years. Calhoun and his team plan to use data from functional magnetic resonance imaging (“fMRI”) to allow psychiatrists to more accurately predict how patients will react to medication. Their algorithm would then use machine learning to analyze a patient’s fMRI scan and compare it to scans from thousands of other individuals.
By studying how individuals with the same brain activity reacted to medication, the tool could predict how a patient will likely respond to one medication versus another. This information will help psychiatrists decide which medication to prescribe to patients. At the moment, there are no biologically based clinical tools to diagnose mental illness, with conditions like bipolar disorder taking an average of six to ten years to properly diagnose.
“This tool can give clinicians an objective window into a patient’s brain, helping them make more tailored treatment recommendations. Regardless of the diagnosis, is the patient’s brain more similar to someone who responded better to mood stabilizers or to someone who responded better to antidepressants?” asks Bockholt. The two-year grant will allow the team to refine the algorithm by feeding it additional data, including scans from a diverse group of patients as well as scans from various types of fMRI machines.
Eric Verner, Associate Director of Innovation at TReNDS and Project Co-Investigator, George State University says that “on the previous data set, our tool was over 90% accurate in predicting medication outcomes, so that shows us that we’re on the right track. By training the model on more data, it should perform better on a wider variety of patients.”
“We’re focusing on a patient population that is difficult to diagnose and treat using current methods,” says Calhoun. “It can be hard to know what type of medication is warranted. This could help inform those decisions and get patients on the right medication sooner.”
It would be interesting to see how the functionality of this tool would improve when paired with the systems used to develop customized treatments by biomedical companies like Predictive Oncology (NASDAQ: POAI).
Please see full terms of use and disclaimers on the BioMedWire website applicable to all content provided by BMW, wherever published or re-published: http://BMW.fm/Disclaimer
