Measuring algorithmic bias to analyze the reliability of AI tools that predict depression risk using smartphone sensed-behavioral data

Author:

Adler Daniel A.1,Stamatis Caitlin A.2,Meyerhoff Jonah2,Mohr David C.2,Wang Fei3,Aranovich Gabriel J.1,Sen Srijan4,Choudhury Tanzeem1

Affiliation:

1. Cornell Tech

2. Northwestern University Feinberg School of Medicine

3. Weill Cornell Medicine

4. Michigan Medicine

Abstract

Abstract

AI tools intend to transform mental healthcare by providing remote estimates of depression risk using behavioral data collected by sensors embedded in smartphones. While these tools accurately predict elevated symptoms in small, homogenous populations, recent studies show that these tools are less accurate in larger, more diverse populations. In this work, we show that accuracy is reduced because sensed-behaviors are unreliable predictors of depression across individuals; specifically the sensed-behaviors that predict depression risk are inconsistent across demographic and socioeconomic subgroups. We first identified subgroups where a developed AI tool underperformed by measuring algorithmic bias, where subgroups with depression were incorrectly predicted to be at lower risk than healthier subgroups. We then found inconsistencies between sensed-behaviors predictive of depression across these subgroups. Our findings suggest that researchers developing AI tools predicting mental health from behavior should think critically about the generalizability of these tools, and consider tailored solutions for targeted populations.

Publisher

Research Square Platform LLC

Reference60 articles.

1. Trends In Mental Health Care Delivery By Psychiatrists And Nurse Practitioners In Medicare, 2011–19;Cai A;Health Aff. (Millwood),2022

2. Banbury Forum Consensus Statement on the Path Forward for Digital Mental Health Treatment;Mohr DC;Psychiatr. Serv. appi.ps.,2021

3. The relationship between text message sentiment and self-reported depression;Liu T;J. Affect. Disord.,2022

4. Xu, X. et al. GLOBEM: Cross-Dataset Generalization of Longitudinal Human Behavior Modeling. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 6, 190:1-190:34 (2023).

5. Mobile Phone Sensor Correlates of Depressive Symptom Severity in Daily-Life Behavior: An Exploratory Study;Saeb S;J. Med. Internet Res.,2015

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3