Stigma, biomarkers, and algorithmic bias: recommendations for precision behavioral health with artificial intelligence

Colin G Walsh; Beenish Chaudhry; Prerna Dua; Kenneth W Goodman; Bonnie Kaplan; Ramakanth Kavuluru; Anthony Solomonides; Vignesh Subbian

doi:10.1093/jamiaopen/ooz054

Stigma, biomarkers, and algorithmic bias: recommendations for precision behavioral health with artificial intelligence

JAMIA Open. 2020 Jan 22;3(1):9-15. doi: 10.1093/jamiaopen/ooz054. eCollection 2020 Apr.

Authors

Colin G Walsh¹, Beenish Chaudhry², Prerna Dua³, Kenneth W Goodman⁴, Bonnie Kaplan⁵, Ramakanth Kavuluru⁶, Anthony Solomonides⁷, Vignesh Subbian⁸

Affiliations

¹ Biomedical Informatics, Medicine and Psychiatry, Vanderbilt University Medical Center, 2525 West End, Suite 1475, Nashville, TN, USA.
² School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, Louisiana, USA.
³ Department of Health Informatics and Information Management, Louisiana Tech University, Ruston, Louisiana, USA.
⁴ Institute for Bioethics and Health Policy, University of Miami, Miller School of Medicine, Miami, Florida, USA.
⁵ Yale Center for Medical Informatics, Yale Bioethics Center, Yale Information Society, Yale Solomon Center for Health Law & Policy, Yale University, New Haven, Connecticut, USA.
⁶ Division of Biomedical Informatics, Department of Internal Medicine, University of Kentucky, Lexington, Kentucky, USA.
⁷ Outcomes Research and Biomedical Informatics, NorthShore University HealthSystem, Research Institute, Evanston, Illinois, USA.
⁸ Department of Biomedical Engineering, Department of Systems and Industrial Engineering, The University of Arizona, Tucson, Arizona, USA.

Abstract

Effective implementation of artificial intelligence in behavioral healthcare delivery depends on overcoming challenges that are pronounced in this domain. Self and social stigma contribute to under-reported symptoms, and under-coding worsens ascertainment. Health disparities contribute to algorithmic bias. Lack of reliable biological and clinical markers hinders model development, and model explainability challenges impede trust among users. In this perspective, we describe these challenges and discuss design and implementation recommendations to overcome them in intelligent systems for behavioral and mental health.

Keywords: artificial intelligence; behavioral health; ethics; health disparities, algorithms, mental health; precision medicine; predictive modeling.

Grants and funding

R01 MH116269/MH/NIMH NIH HHS/United States