The grant will help Clarigent Health researchers continue to examine the role demographic and environmental factors play in machine learning algorithms that identify mental health risks
Clarigent Health, a mental health technology company, today announced their receipt of a competitive Small Business Innovation Research (SBIR) grant from the National Institutes of Health (NIH) to advance development of their machine learning algorithms. Clarigent Health’s proprietary algorithms analyze speech to help identify patients at risk of suicide and other mental health concerns. The Clarigent Health platform delivers this objective metric to mental health professionals alongside patient-reported assessments and clinical impressions to help inform clinical decisions.
HR Technology: Forbes Recognizes Evoqua Water Technologies Among Top Employers In America
“Our goal is to improve prediction accuracy and understand how these characteristics directly or indirectly bias our models. This is an important and often overlooked component of machine learning and I’m excited to work on it”
Clarigent Health is committed to building machine learning algorithms that treat diverse groups fairly without over- or under- reporting levels of risk. The grant will support Clarigent Health’s ongoing analysis of the data used to design the algorithms to ensure fair and accurate assessments. Researchers will investigate how patient and setting characteristics, such as demographics, influence the algorithms’ accuracy. This will enable a thorough understanding of model training data to identify and correct any potential biases.
The grant will also support investigation of the effects of COVID-19 on the algorithms. Data collected in different environments, including telehealth environments, may impact the model results. It is also possible that relevant ‘thought markers’ for suicide have shifted across the population because everyone has experienced such dramatic life changes.
HR Technology: Employee Survey Software: Exploring A Few Of The Best
“Our organization is constantly working to improve our algorithms and ensure fairness and accuracy,” said Clarigent founder and CEO, Don Wright.
“Our goal is to improve prediction accuracy and understand how these characteristics directly or indirectly bias our models. This is an important and often overlooked component of machine learning and I’m excited to work on it,” added Joshua Cohen, PhD, Clarigent Health’s Data Science Director and the grant’s Principal Investigator.
The research team has already begun the analysis and will continue collaborating to consider clinical implications. In addition to Dr. Joshua Cohen, PhD and Dr. David Black, PhD at Clarigent Health, the research team and collaborators include Dr. Jennifer Wright-Berryman, MSW, PhD, Associate Professor and clinician researcher at the University of Cincinnati, clinical psychologist Dr. Bailey Bryant MA, PsyD, Dr. Cheryl McCullumsmith, MD, PhD, Chair of the Department of Psychiatry at the University of Toledo, and Dr. John Greden, MD, Executive Director of the University of Michigan Comprehensive Depression Center and Professor of Psychiatry and Clinical Neurosciences. Together, they will provide clinical perspective and interpretation of research findings to inform implementation in Clarigent Health’s products.