Reliability and validity of a widely-available AI tool for assessment of stress based on speech

Batul A. Yawer; Julie Liss; Visar Berisha

doi:10.1038/s41598-023-47153-1

Reliability and validity of a widely-available AI tool for assessment of stress based on speech

Batul A. Yawer, Julie Liss, Visar Berisha

Health Solutions, College of (CHS)

Research output: Contribution to journal › Article › peer-review

Abstract

Cigna’s online stress management toolkit includes an AI-based tool that purports to evaluate a person’s psychological stress level based on analysis of their speech, the Cigna StressWaves Test (CSWT). In this study, we evaluate the claim that the CSWT is a “clinical grade” tool via an independent validation. The results suggest that the CSWT is not repeatable and has poor convergent validity; the public availability of the CSWT despite insufficient validation data highlights concerns regarding premature deployment of digital health tools for stress and anxiety management.

Original language	English (US)
Article number	20224
Journal	Scientific reports
Volume	13
Issue number	1
DOIs	https://doi.org/10.1038/s41598-023-47153-1
State	Published - Dec 2023

ASJC Scopus subject areas

General

Access to Document

10.1038/s41598-023-47153-1

Cite this

@article{ce4ca145dbb941f199b7bf4fdc87c69e,

title = "Reliability and validity of a widely-available AI tool for assessment of stress based on speech",

abstract = "Cigna{\textquoteright}s online stress management toolkit includes an AI-based tool that purports to evaluate a person{\textquoteright}s psychological stress level based on analysis of their speech, the Cigna StressWaves Test (CSWT). In this study, we evaluate the claim that the CSWT is a “clinical grade” tool via an independent validation. The results suggest that the CSWT is not repeatable and has poor convergent validity; the public availability of the CSWT despite insufficient validation data highlights concerns regarding premature deployment of digital health tools for stress and anxiety management.",

author = "Yawer, {Batul A.} and Julie Liss and Visar Berisha",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2023",

month = dec,

doi = "10.1038/s41598-023-47153-1",

language = "English (US)",

volume = "13",

journal = "Scientific reports",

issn = "2045-2322",

publisher = "Nature Publishing Group",

number = "1",

}

TY - JOUR

T1 - Reliability and validity of a widely-available AI tool for assessment of stress based on speech

AU - Yawer, Batul A.

AU - Liss, Julie

AU - Berisha, Visar

PY - 2023/12

Y1 - 2023/12

N2 - Cigna’s online stress management toolkit includes an AI-based tool that purports to evaluate a person’s psychological stress level based on analysis of their speech, the Cigna StressWaves Test (CSWT). In this study, we evaluate the claim that the CSWT is a “clinical grade” tool via an independent validation. The results suggest that the CSWT is not repeatable and has poor convergent validity; the public availability of the CSWT despite insufficient validation data highlights concerns regarding premature deployment of digital health tools for stress and anxiety management.

AB - Cigna’s online stress management toolkit includes an AI-based tool that purports to evaluate a person’s psychological stress level based on analysis of their speech, the Cigna StressWaves Test (CSWT). In this study, we evaluate the claim that the CSWT is a “clinical grade” tool via an independent validation. The results suggest that the CSWT is not repeatable and has poor convergent validity; the public availability of the CSWT despite insufficient validation data highlights concerns regarding premature deployment of digital health tools for stress and anxiety management.

UR - http://www.scopus.com/inward/record.url?scp=85176926824&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85176926824&partnerID=8YFLogxK

U2 - 10.1038/s41598-023-47153-1

DO - 10.1038/s41598-023-47153-1

M3 - Article

C2 - 37980431

AN - SCOPUS:85176926824

SN - 2045-2322

VL - 13

JO - Scientific reports

JF - Scientific reports

IS - 1

M1 - 20224

ER -

Reliability and validity of a widely-available AI tool for assessment of stress based on speech

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this