Berkeley uses deep learning to address suicide risks among veterans
Researchers from Berkeley Lab at the University of California been applying deep learning and analytics to electronic health record data to help the Veterans Administration tackle medical and psychological challenges of returning service members.
WHY IT MATTERS
Working with a publicly available dataset containing medical record information on about 40,000 patients from one Boston hospital intensive care unit, researchers searched for patterns that might point to suicide risk.
The goal is to improve identification of patients at risk for suicide through new patient-specific algorithms that produce tailored and dynamic suicide risk scores, and make those resources available to VA caregivers and patients.
Suicide is the 10th leading cause of death in the U.S., and it is significantly higher in the veteran population, with 20-22 deaths per day – an alarming statistic the VA’s Million Veteran Program Suicide Prevention Exemplar project is designed to help address.
Early efforts focused primarily on finding patterns in a diverse and complex pool of data, such as building a deep learning network that can distinguish and classify patients at high risk for suicide from discharge notes and physicians’ notes found in these datasets.
The neural network was trained to classify between patients who are at high risk for suicide and those who are not to find patterns in the doctors’ language.
The U.S. Department of Energy and the VA are also working to apply supercomputing, software development and networking to medical data sets collected by the VA from around 700,000 veterans and EHR data from another 22 million vets.
The initial focus of this program, which combines the VA’s EHR system with DOE’s high performance computing, artificial intelligence and data analytics resources, is on suicide prevention, prostate cancer, and cardiovascular diseases.
THE LARGER TREND
As part of Berkeley Lab’s Machine Learning for Science strategic initiative, the lab released a workshop report in February on the basic research needs for scientific machine learning and core technologies for AI.
Deep learning methods represent a promising approach for analytics in science for discovering subtle patterns in very complex scientific data of all kinds – the recently opened Center for Clinical Artificial Intelligence, will innovate new advances and applications for AI and machine learning in healthcare.
Meanwhile the first quantitative AI tools for medical imaging have received clearance from the FDA, and Northwestern Medicine is working with a cardiac monitoring platform from Eko to pilot machine learning for heart disease.
ON THE RECORD
“The VA has been collecting medical records and genomic data from some 700,000 veterans, and they need help from DOE to interpret all of this information to improve healthcare for these individuals,” said Silvia Crivelli, lead for Berkeley Lab’s involvement in the suicide prevention project, said in a statement.
The team believes incorporating the physician’s knowledge to the platform will improve the accuracy and defensibility of scientific deep learning models.
“We are aware that we need to gain the trust of the physicians, and that’s why are working on developing models that are interpretable,” Crivelli explained.
Nathan Eddy is a healthcare and technology freelancer based in Berlin.
Email the writer: firstname.lastname@example.org
Healthcare IT News is a HIMSS Media publication.
This article is automatically posted by WP-AutoPost Plugin