This study explored how users respond to a depression self-diagnosis app with two outcomes: “doctor-generated” and “AI-generated.” The doctor-generated result was based on participants’ actual PHQ-9 depression scores, while the AI-generated result was randomly selected and sometimes matched the true diagnosis. Participants (n = 47) with depressive symptoms used the app while pupil dilation was recorded using a Tobii Pro Spectrum eye tracker. Pupil dilation was analyzed before and during the decision phase. Participants who chose the doctor-generated result showed no difference in pupil dilation compared to those who chose AI. Our Extreme Gradient Boosting (XGB) model predicted trust with an AUROC of 0.871. These findings show that users engage equally with both AI and doctor-labeled diagnoses, but pupil diameter is indicative of their trust.
AjenaghughrureI. B.SousaS. D. C.LamasD. (2020). Measuring trust with psychophysiological signals: A systematic mapping study of approaches used. Multimodal Technologies and Interaction, 4(3), 63.
2.
AnthesE. (2016). Pocket psychiatry: Mobile mental-health apps have exploded onto the market, but few have been thoroughly tested. Nature, 532(7597), 20–24.
3.
BachT. A.KhanA.HallockH.BeltrãoG.SousaS. (2024). A systematic literature review of user trust in AI-enabled systems: An HCI perspective. International Journal of Human–Computer Interaction, 40(5), 1251–1266.
4.
BeattyJ.Lucero-WagonerB. (2000). The pupillary system. In CacioppoJ. T.TassinaryL. G.BerntsonG. G. (Eds.), Handbook of psychophysiology (2nd ed., pp. 142–162). Cambridge University Press.
5.
BitskoR. H. (2022). Mental health surveillance among children—United States, 2013–2019. MMWR Supplements, 71(2), 1–42.
6.
BradleyM. M.MiccoliL.EscrigM. A.LangP. J. (2008). The pupil as a measure of emotional arousal and autonomic activation. Psychophysiology, 45(4), 602–607.
7.
BuruckG.TomaschekA.WendscheJ.OchsmannE.DörfelD. (2019). Psychosocial areas of worklife and chronic low back pain: A systematic review and meta-analysis. BMC Musculoskeletal Disorders, 20(1), 1–16. https://doi.org/10.1186/s12891-019-2826-3
8.
CastagnoS.KhalifaM. (2020). Perceptions of artificial intelligence among healthcare staff: A qualitative survey study. Frontiers in Artificial Intelligence, 3, 578983.
9.
ChenT.HeT.BenestyM.KhotilovichV.TangY.ChoH.ChenK.MitchellR.CanoI.ZhouT. (2015). Xgboost: Extreme gradient boosting. R Package Version 0.4-2.
10.
De VisserE. J.MonfortS. S.McKendrickR.SmithM. A.McKnightP. E.KruegerF.ParasuramanR. (2016). Almost human: Anthropomorphism increases trust resilience in cognitive agents. Journal of Experimental Psychology: Applied, 22(3), 331.
11.
GliksonE.WoolleyA. W. (2020). Human trust in artificial intelligence: Review of empirical research. Academy of Management Annals, 14(2), 627–660.
12.
HoffK. A.BashirM. (2015). Trust in automation: Integrating empirical evidence on factors that influence trust. Human Factors, 57(3), 407–434.
13.
JustM. A.CarpenterP. A.KellerT. A.EddyW. F.ThulbornK. R. (1996). Brain activation modulated by sentence comprehension. Science, 274(5284), 114–116.
14.
KahnemanD.BeattyJ. (1966). Pupil diameter and load on memory. Science, 154(3756), 1583–1585.
15.
KretM. E.FischerA. H.De DreuC. K. (2015). Pupil mimicry correlates with trust in in-group partners with dilating pupils. Psychological Science, 26(9), 1401–1410.
16.
LeeJ. D.SeeK. A. (2004). Trust in automation: Designing for appropriate reliance. Human Factors, 46(1), 50–80.
17.
LongoniC.BonezziA.MorewedgeC. K. (2019). Resistance to medical artificial intelligence. Journal of Consumer Research, 46(4), 629–650.
18.
MadhavanP.WiegmannD. A. (2007). Similarities and differences between human–human and human–automation trust: An integrative review. Theoretical Issues in Ergonomics Science, 8(4), 277–301.
PedregosaF.VaroquauxG.GramfortA.MichelV.ThirionB.GriselO.BlondelM.PrettenhoferP.WeissR.DubourgV. (2011). Scikit-learn: Machine learning in Python. The Journal of Machine Learning Research, 12, 2825–2830.
21.
ProchazkovaE.ProchazkovaL.GiffinM. R.ScholteH. S.De DreuC. K.KretM. E. (2018). Pupil mimicry promotes trust through the theory-of-mind network. Proceedings of the National Academy of Sciences, 115(31), E7265–E7274.
22.
RamosR. M.ChengP. G. F.JonasS. M. (2019). Validation of an mHealth app for depression screening and monitoring (psychologist in a pocket): Correlational study and concurrence analysis. JMIR mHealth and uHealth, 7(9), e12051.
23.
Relaño-IborraH.BækgaardP. (2020). PUPILS pipeline: A flexible Matlab toolbox for eyetracking and pupillometry data processing. arXiv preprint arXiv:2011.05118.
24.
SimpsonH.HaleS. M. (1969). Pupillary changes during a decision-making task. Perceptual and Motor Skills, 29(2), 495–498.
25.
SonawaneA.ShahS.PoteS.HeM. (2023). The application of artificial intelligence: Perceptions from healthcare professionals. Health and Technology, 13(5), 861–867.
26.
TorousJ.MyrickK. J.Rauseo-RicuperoN.FirthJ. (2020). Digital mental health and COVID-19: Using technology today to accelerate the curve on access and quality tomorrow. JMIR Mental Health, 7(3), e18848.
27.
UraiA. E.BraunA.DonnerT. H. (2017). Pupil-linked arousal is driven by decision uncertainty and alters serial choice bias. Nature Communications, 8(1), 14637.
28.
Van der WelP.Van SteenbergenH. (2018). Pupil dilation as an index of effort in cognitive control tasks: A review. Psychonomic Bulletin & Review, 25, 2005–2015.
29.
WehebrinkK. S.KoelkebeckK.PiestS.de DreuC. K.KretM. E. (2018). Pupil mimicry and trust—Implication for depression. Journal of Psychiatric Research, 97, 70–76.
30.
WinnM. B.WendtD.KoelewijnT.KuchinskyS. E. (2018). Best practices and advice for using pupillometry to measure listening effort: An introduction for those who want to get started. Trends in Hearing, 22, 1–32.
31.
World Health Organization. (2021). Comprehensive mental health action plan 2013–2030. WHO.
