Project Spotlight: Multimodal Biomarkers

Depression is a leading cause of disability worldwide. Effective, evidence-based treatments for depression exist but many individuals suffering from depression go undetected and therefore untreated. Efforts to increase the accuracy, efficiency, and adoption of depression screening thus have the potential to minimize human suffering and even save lives.

Recent advances in computer-sensing technologies provide exciting new opportunities to improve depression screening, especially in terms of their objectivity, scalability, and accessibility. Professor Morency and Dr. Szigethy are collaborating to develop sensing technologies to automatically measure subtle changes in individuals’ behavior that are related to affective, cognitive, and psychosocial functioning. Their goal is to develop and refine computational tools that automatically measure depression-related behavioral biomarkers and to evaluate the clinical utility of these measurements.

Please share a little about your background and your research experiences.

 As a clinical researcher with a doctorate in basic neuroscience and masters in translational clinical science, Eva Szigethy, MD, PhD has focused the past 15 years of her research career characterizing symptoms in patients with inflammatory bowel disease (IBD) and designing behavioral interventions to target neuropsychiatric manifestations of IBD and irritable bowel syndrome (IBS). Specifically, her focus has been on how behavioral interventions can be used to target specific domains of depression and, once positive effects have been shown, how such interventions can be disseminated to clinicians in the field. One aspect of her work has been studying and implementing strategies to get diagnostic measures and interventions more broadly using behavioral health technology.

Louis-Philippe Morency, PhD, is the Finmeccanica Associate Professor of Computer Science in the Language Technology Institute at Carnegie Mellon University where he leads the Multimodal Communication and Machine Learning Laboratory. His research group brings together multi-disciplinary expertise across machine learning, natural language processing, computer vision, and social psychology to develop algorithms and models that will enable computerized analysis of human behaviors that are exhibited during social interactions.

What led you to the PHDA?

The population of patients with functional gastrointestinal disorders has a rate of depression of 25-30%, and at least 50% having some depressive symptoms. Resources from the PHDA allow our team to develop a more comprehensive understanding of diagnosing depression within this population using biometric tools. The project involves sampling voice and behavioral-based markers to detect depressive symptoms, rather than a patient’s report alone. If proved to be valid, these tools will allow for more accurate and efficient depression screening.

Walk us through your project.

Louis-Philippe Morency, PhD, and Eva Szigethy, MD, PhD, are conducting research to build upon existing multimodal technologies to detect and rate depression directly from human voice and behaviors. Their current study focuses on subjects with functional gastrointestinal disorders, many of whom suffer from depression. The project involves sampling voice and non-invasive biomarkers alongside a standard clinical psychiatric interview, computerized psychiatric evaluation, and validated questionnaires for diagnosing depression. The multimodal technology result is then compared to the reported answers through the clinical and computerized interviews. If patients show depressive symptoms, they are given access to a smartphone application to aid with depression/anxiety relief alongside routine care and are re-assessed three months after the initial assessment. Patients who screen positive are offered behavioral interventions embedded into their gastrointestinal care, including digital cognitive behavioral therapy.

How is the PHDA uniquely positioned to assist your team and grow your project to commercialization?

Many patients drive great distances to see gastroenterologists at UPMC. This technology would allow for diagnoses to be detected early so that further ancillary care services can be offered in advance. If successful, these types of biometric screening tools may allow for a more objective measure for depression compared to the current gold standard, patient self-report.

What are your project’s next steps?

Our project’s next steps are to continue recruitment within The UPMC Program for Gut Brain Health (PGH), which is an integrated behavioral-medical program and is based in the Department of Gastroenterology at UPMC. As recruitment continues to grow, we are developing further understanding to enhance the multimodal fusion algorithm and gain new insights into how depression can be diagnosed and effectively prevented or treated going forward.

Subscribe to our newsletter to get the latest Alliance news, event invitations and updates, and behind-the-scenes spotlights on our researchers, projects, and team members.
Subscribe

By clicking Submit, I agree to the Pittsburgh Health Data Alliance's Terms of Use and Privacy Policy.