Effects of an Artificial Intelligence Platform for Behavioral Interventions on Depression and Anxiety Symptoms: Randomized Clinical Trial

Shiri Sadeh-Sharvit, T Del Camp, Sarah E Horton, Jacob D Hefner, Jennifer M Berry, Eyal Grossman, Steven D Hollon, Shiri Sadeh-Sharvit, T Del Camp, Sarah E Horton, Jacob D Hefner, Jennifer M Berry, Eyal Grossman, Steven D Hollon

Abstract

Background: The need for scalable delivery of mental health care services that are efficient and effective is now a major public health priority. Artificial intelligence (AI) tools have the potential to improve behavioral health care services by helping clinicians collect objective data on patients' progress, streamline their workflow, and automate administrative tasks.

Objective: The aim of this study was to determine the feasibility, acceptability, and preliminary efficacy of an AI platform for behavioral health in facilitating better clinical outcomes for patients receiving outpatient therapy.

Methods: The study was conducted at a community-based clinic in the United States. Participants were 47 adults referred for outpatient, individual cognitive behavioral therapy for a main diagnosis of a depressive or anxiety disorder. The platform provided by Eleos Health was compared to a treatment-as-usual (TAU) approach during the first 2 months of therapy. This AI platform summarizes and transcribes the therapy session, provides feedback to therapists on the use of evidence-based practices, and integrates these data with routine standardized questionnaires completed by patients. The information is also used to draft the session's progress note. Patients were randomized to receive either therapy provided with the support of an AI platform developed by Eleos Health or TAU at the same clinic. Data analysis was carried out based on an intention-to-treat approach from December 2022 to January 2023. The primary outcomes included the feasibility and acceptability of the AI platform. Secondary outcomes included changes in depression (Patient Health Questionnaire-9) and anxiety (Generalized Anxiety Disorder-7) scores as well as treatment attendance, satisfaction, and perceived helpfulness.

Results: A total of 72 patients were approached, of whom 47 (67%) agreed to participate. Participants were adults (34/47, 72% women and 13/47, 28% men; mean age 30.64, SD 11.02 years), with 23 randomized to the AI platform group, and 24 to TAU. Participants in the AI group attended, on average, 67% (mean 5.24, SD 2.31) more sessions compared to those in TAU (mean 3.14, SD 1.99). Depression and anxiety symptoms were reduced by 34% and 29% in the AI platform group versus 20% and 8% for TAU, respectively, with large effect sizes for the therapy delivered with the support of the AI platform. No group difference was found in 2-month treatment satisfaction and perceived helpfulness. Further, therapists using the AI platform submitted their progress notes, on average, 55 hours earlier than therapists in the TAU group (t=-0.73; P<.001).

Conclusions: In this randomized controlled trial, therapy provided with the support of Eleos Health demonstrated superior depression and anxiety outcomes as well as patient retention, compared with TAU. These findings suggest that complementing the mental health services provided in community-based clinics with an AI platform specializing in behavioral treatment was more effective in reducing key symptoms than standard therapy.

Trial registration: ClinicalTrials.gov NCT05745103; https://classic.clinicaltrials.gov/ct2/show/NCT05745103.

Keywords: anxiety; artificial intelligence; augmentation; cognitive-behavioral therapy; community-based center; depression; depressive; evidence-based practices; health force burnout.

Conflict of interest statement

Conflicts of Interest: SSS and EG are employees of Eleos Health Inc, which provided the AI platform used in this study. TDC, SEH, JDH, and JMB declare no conflict of interests. SDH is a nonpaid advisor of Eleos Health.

©Shiri Sadeh-Sharvit, T Del Camp, Sarah E Horton, Jacob D Hefner, Jennifer M Berry, Eyal Grossman, Steven D Hollon. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 10.07.2023.

Figures

Figure 1
Figure 1
The study’s CONSORT-AI flow diagram. CONSORT-AI: Consolidated Standards of Reporting Trials-artificial intelligence.
Figure 2
Figure 2
The session analytics provided by the Eleos Health platform.
Figure 3
Figure 3
The automated progress notes provided by the Eleos Health platform the notes feature.
Figure 4
Figure 4
Depressive symptom change over the first 2 months of therapy. PHQ-9: Patient Health Questionnaire-9.
Figure 5
Figure 5
Anxiety symptom change over the first 2 months of therapy. GAD-7: Generalized Anxiety Disorder-7.

References

    1. Sadeh-Sharvit S, Hollon SD. Leveraging the power of nondisruptive technologies to optimize mental health treatment: case study. JMIR Ment Health. 2020 Nov 26;7(11):e20646. doi: 10.2196/20646. v7i11e20646
    1. Hepner K, Roth CP, Sloss EM, Paddock SM, Iyiewuare PO, Timmer MJ, Pincus HA. Quality of care for PTSD and depression in the military health system: final report. Rand Health Q. 2018 Apr;7(3):4.
    1. Pincus H, England MJ. Improving the quality of psychosocial interventions for mental and substance use disorders: a report from the IOM. JAMA. 2015;314(12):1227–8. doi: 10.1001/jama.2015.9212. doi: 10.1001/jama.2015.9212.2398305
    1. Caton L, Cheng H, Garneau HC, Fisher T, Harris-Mills B, Hurley B, Newman S, McGovern MP. COVID-19 adaptations in the care of patients with opioid use disorder: a survey of California primary care clinics. J Gen Intern Med. 2021 Apr 28;36(4):998–1005. doi: 10.1007/s11606-020-06436-3. 10.1007/s11606-020-06436-3
    1. Moreno C, Wykes T, Galderisi S, Nordentoft M, Crossley N, Jones N, Cannon M, Correll CU, Byrne L, Carr S, Chen EYH, Gorwood P, Johnson S, Kärkkäinen H, Krystal JH, Lee J, Lieberman J, López-Jaramillo C, Männikkö M, Phillips MR, Uchida H, Vieta E, Vita A, Arango C. How mental health care should change as a consequence of the COVID-19 pandemic. The Lancet Psychiatry. 2020 Sep;7(9):813–824. doi: 10.1016/s2215-0366(20)30307-2.
    1. Crocker K, Gnatt I, Haywood D, Butterfield I, Bhat R, Lalitha ARN, Jenkins Zoe M, Castle David J. The impact of COVID-19 on the mental health workforce: a rapid review. Int J Ment Health Nurs. 2023 Apr;32(2):420–445. doi: 10.1111/inm.13097.
    1. Lluch C, Galiana L, Doménech P, Sansó N. The impact of the COVID-19 pandemic on burnout, compassion fatigue, and compassion satisfaction in healthcare personnel: a systematic review of the literature Published during the First Year of the Pandemic. Healthcare (Basel) 2022 Feb 13;10(2):364. doi: 10.3390/healthcare10020364. healthcare10020364
    1. Sklar M, Ehrhart MG, Aarons GA. COVID-related work changes, burnout, and turnover intentions in mental health providers: a moderated mediation analysis. Psychiatr Rehabil J. 2021 Sep;44(3):219–228. doi: 10.1037/prj0000480. 2021-45244-001
    1. Wilkinson C, Infantolino ZP, Wacha-Montes A. Evidence-based practice as a potential solution to burnout in university counseling center clinicians. Psychol Serv. 2017 Nov;14(4):543–548. doi: 10.1037/ser0000156. doi: 10.1037/ser0000156.2017-49948-015
    1. Parrish D, Lemmons B, Washburn M, Oxhandler H, Sturdivant R. Predictors of social work practitioner engagement in evidence-based practice: a cross-sectional survey. Journal of Evidence-Based Social Work. 2023 Jan 23;20(3):425–443. doi: 10.1080/26408066.2023.2168508.
    1. Alvidrez J, Nápoles AM, Bernal G, Lloyd J, Cargill V, Godette D, Cooper L, Horse Brave Heart MY, Das R, Farhat T. Building the evidence base to inform planned intervention adaptations by practitioners serving health disparity populations. Am J Public Health. 2019 Jan;109(S1):S94–S101. doi: 10.2105/ajph.2018.304915.
    1. Yu SH, Brookman-Frazee L, Kim JJ, Barnett ML, Wright B, Lau AS. Therapist adaptations to evidence-based practices and associations with implementation outcomes in child therapy sessions. J Consult Clin Psychol. 2022 Jan;90(1):39–50. doi: 10.1037/ccp0000667. 2021-76821-001
    1. Bickman L. Improving mental health services: a 50-year journey from randomized experiments to artificial intelligence and precision mental health. Adm Policy Ment Health. 2020 Sep;47(5):795–843. doi: 10.1007/s10488-020-01065-8. 10.1007/s10488-020-01065-8
    1. Kellogg KC, Sadeh-Sharvit S. Pragmatic AI-augmentation in mental healthcare: key technologies, potential benefits, and real-world challenges and solutions for frontline clinicians. Front Psychiatry. 2022 Sep 6;13:990370. doi: 10.3389/fpsyt.2022.990370.
    1. Antoniadi AM, Du Y, Guendouz Y, Wei L, Mazo C, Becker BA, Mooney C. Current challenges and future opportunities for XAI in machine learning-based clinical decision support systems: a systematic review. Appl Sci. 2021 May 31;11(11):5088. doi: 10.3390/app11195088. doi: 10.3390/app11115088.
    1. Bertl M, Ross P, Draheim D. A survey on AI and decision support systems in psychiatry – uncovering a dilemma. Expert Syst Appl. 2022 Sep;202:117464. doi: 10.1016/j.eswa.2022.117464. doi: 10.1016/j.eswa.2022.117464.
    1. Liu X, Rivera SC, Moher D, Calvert MJ, Denniston AK, SPIRIT-AICONSORT-AI Working Group Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI Extension. BMJ. 2020 Sep 09;370:m3164. doi: 10.1136/bmj.m3164.
    1. Kroenke K, Spitzer RL, Williams JBW. The PHQ-9: validity of a brief depression severity measure. J Gen Intern Med. 2001 Sep;16(9):606–13. doi: 10.1046/j.1525-1497.2001.016009606.x. jgi01114
    1. Spitzer RL, Kroenke K, Williams JBW, Löwe B. A brief measure for assessing generalized anxiety disorder: the GAD-7. Arch Intern Med. 2006 May 22;166(10):1092–7. doi: 10.1001/archinte.166.10.1092.166/10/1092
    1. Sadeh-Sharvit S, Rego SA, Jefroykin S, Peretz G, Kupershmidt T. A comparison between clinical guidelines and real-world treatment data in examining the use of session summaries: retrospective study. JMIR Form Res. 2022 Aug 16;6(8):e39846. doi: 10.2196/39846. v6i8e39846
    1. Sadeh-Sharvit S, Hollon S D. Revolutionizing Mental Healthcare Services through AI-Augmentation: A New Model. PsyArXiv. doi: 10.31234/. Preprint posted online on Feb 21, 2023.
    1. Jensen-Doss A, Haimes EMB, Smith AM, Lyon AR, Lewis CC, Stanick CF, Hawley KM. Monitoring treatment progress and providing feedback is viewed favorably but rarely used in practice. Adm Policy Ment Health. 2018 Jan;45(1):48–61. doi: 10.1007/s10488-016-0763-0. 10.1007/s10488-016-0763-0
    1. Vetter J, Schultebraucks K, Galatzer-Levy I, Boeker He, Brühl Annette, Seifritz Erich, Kleim Birgit. Predicting non-response to multimodal day clinic treatment in severely impaired depressed patients: a machine learning approach. Sci Rep. 2022 Mar 31;12(1):5455. doi: 10.1038/s41598-022-09226-5. doi: 10.1038/s41598-022-09226-5.10.1038/s41598-022-09226-5
    1. Mallinckrodt CH, Clark WS, David SR. Accounting for dropout bias using mixed-effects models. J Biopharm Stat. 2011 Jul 24;11(1-2):9–21. doi: 10.1081/bip-100104194.
    1. Heuer A. More evidence that the healthcare administrative burden is real, widespread and has serious consequences comment on "perceived burden due to registrations for quality monitoring and improvement in hospitals: a mixed methods study". Int J Health Policy Manag. 2022 Apr 01;11(4):536–538. doi: 10.34172/ijhpm.2021.129.
    1. Worsening mental health crisis pressures psychologist workforce. American Psychological Association. 2021. [2023-07-03]. .
    1. Van Hoy A, Rzeszutek M, Pięta M, Mestre JM, Rodríguez-Mora Álvaro, Midgley N, Omylinska-Thurston J, Dopierala A, Falkenström Fredrik, Ferlin J, Gergov V, Lazić M, Ulberg R, Røssberg Jan Ivar, Hancheva C, Stoyanova S, Schmidt SJ, Podina I, Ferreira N, Kagialis A, Löffler-Stastka Henriette, Gruszczyńska E. Burnout among psychotherapists: a cross-cultural value survey among 12 European countries during the coronavirus disease pandemic. Sci Rep. 2022 Aug 08;12(1):13527. doi: 10.1038/s41598-022-17669-z. 10.1038/s41598-022-17669-z
    1. Spagnolo J, Beauséjour M, Fleury M, Clément JF, Gamache C, Sauvé Carine, Couture L, Fleet R, Knight S, Gilbert C, Vasiliadis H. Perceptions on barriers, facilitators, and recommendations related to mental health service delivery during the COVID-19 pandemic in Quebec, Canada: a qualitative descriptive study. BMC Prim Care. 2022 Feb 21;23(1):32. doi: 10.1186/s12875-022-01634-w. 10.1186/s12875-022-01634-w

Source: PubMed

Sponzoři a spolupracovníci

Zdravotní podmínky

Drogové intervence

3
Předplatit