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

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

Biomedical Engineering

Research output: Contribution to journal › Review article › peer-review

66 Scopus citations

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.

Original language	English (US)
Pages (from-to)	9-15
Number of pages	7
Journal	JAMIA Open
Volume	3
Issue number	1
DOIs	https://doi.org/10.1093/JAMIAOPEN/OOZ054
State	Published - 2021

Keywords

Algorithms
Artificial intelligence
Behavioral health
Ethics
Health disparities
Mental health
Precision medicine
Predictive modeling

ASJC Scopus subject areas

Health Informatics

Access to Document

10.1093/JAMIAOPEN/OOZ054

Cite this

@article{af69feb6edff4f1b90efb8c4c65ab694,

title = "Stigma, biomarkers, and algorithmic bias: Recommendations for precision behavioral health with artificial intelligence",

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 = "Algorithms, Artificial intelligence, Behavioral health, Ethics, Health disparities, Mental health, Precision medicine, Predictive modeling",

author = "Walsh, {Colin G.} and Beenish Chaudhry and Prerna Dua and Goodman, {Kenneth W.} and Bonnie Kaplan and Ramakanth Kavuluru and Anthony Solomonides and Vignesh Subbian",

note = "Funding Information: Authors{\textquoteright} effort were partially supported by the following grants: under grant # W81XWH-10-2-0181 and R01 MH116269-01 (CGW), the National Institute of General Medical Sciences of the National Institutes of Health under grant #P20 GM103424-17 (PD); U.S. National Center for Advancing Translational Sciences via grant #UL1TR001998 (RK); National Science Foundation under grant #1838745 (VS). Publisher Copyright: {\textcopyright} The Author(s) 2020.",

year = "2021",

doi = "10.1093/JAMIAOPEN/OOZ054",

language = "English (US)",

volume = "3",

pages = "9--15",

journal = "JAMIA Open",

issn = "2574-2531",

publisher = "Oxford University Press",

number = "1",

}

TY - JOUR

T1 - Stigma, biomarkers, and algorithmic bias

T2 - Recommendations for precision behavioral health with artificial intelligence

AU - Walsh, Colin G.

AU - Chaudhry, Beenish

AU - Dua, Prerna

AU - Goodman, Kenneth W.

AU - Kaplan, Bonnie

AU - Kavuluru, Ramakanth

AU - Solomonides, Anthony

AU - Subbian, Vignesh

N1 - Funding Information: Authors’ effort were partially supported by the following grants: under grant # W81XWH-10-2-0181 and R01 MH116269-01 (CGW), the National Institute of General Medical Sciences of the National Institutes of Health under grant #P20 GM103424-17 (PD); U.S. National Center for Advancing Translational Sciences via grant #UL1TR001998 (RK); National Science Foundation under grant #1838745 (VS). Publisher Copyright: © The Author(s) 2020.

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

KW - Algorithms

KW - Artificial intelligence

KW - Behavioral health

KW - Ethics

KW - Health disparities

KW - Mental health

KW - Precision medicine

KW - Predictive modeling

UR - http://www.scopus.com/inward/record.url?scp=85090455528&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85090455528&partnerID=8YFLogxK

U2 - 10.1093/JAMIAOPEN/OOZ054

DO - 10.1093/JAMIAOPEN/OOZ054

M3 - Review article

AN - SCOPUS:85090455528

SN - 2574-2531

VL - 3

SP - 9

EP - 15

JO - JAMIA Open

JF - JAMIA Open

IS - 1

ER -

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

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this