Closing the accessibility gap to mental health treatment with a personalized self-referral chatbot | Nature Medicine Skip to main content Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript. Advertisement View all journals Saved research Search Account Log in Content Explore content About the journal Publish with us Subscribe Sign up for alerts RSS feed nature nature medicine articles article Article Published: 05 February 2024 Closing the accessibility gap to mental health treatment with a personalized self-referral chatbot Johanna Habicht ORCID: orcid.org/0000-0001-5043-7129 1 , Sruthi Viswanathan 1 , Ben Carrington ORCID: orcid.org/0009-0005-1990-0724 1 , Tobias U. Hauser 1 , 2 , 3 , 4 , Ross Harper ORCID: orcid.org/0000-0002-2403-2088 1 & … Max Rollwage 1 Show authors Nature Medicine volume 30 , pages 595–602 ( 2024 ) Cite this article Save article View saved research 11k Accesses 145 Citations 388 Altmetric Metrics details Abstract Inequality in treatment access is a pressing issue in most healthcare systems across many medical disciplines. In mental healthcare, reduced treatment access for minorities is ubiquitous but remedies are sparse. Here we demonstrate that digital tools can reduce the accessibility gap by addressing several key barriers. In a multisite observational study of 129,400 patients within England’s NHS services, we evaluated the impact of a personalized artificial intelligence-enabled self-referral chatbot on patient referral volume and diversity in ethnicity, gender and sexual orientation. We found that services that used this digital solution identified substantially increased referrals (15% increase versus 6% increase in control services). Critically, this increase was particularly pronounced in minorities, such as nonbinary (179% increase) and ethnic minority individuals (29% increase). Using natural language processing to analyze qualitative feedback from 42,332 individuals, we found that the chatbot’s human-free nature and the patients’ self-realization of their need for treatment were potential drivers for the observed improvement in the diversity of access. This provides strong evidence that digital tools may help overcome the pervasive inequality in mental healthcare. This is a preview of subscription content, access via your institution Access options Access through your institution Access Nature and 54 other Nature Portfolio journals Get Nature+, our best-value online-access subscription 27,99 € / 30 days cancel any time Learn more Subscribe to this journal Receive 12 print issues and online access 251,40 € per year only 20,95 € per issue Learn more Buy this article Purchase on SpringerLink Instant access to the full article PDF. 39,95 € Prices may be subject to local taxes which are calculated during checkout Additional access options: Log in Learn about institutional subscriptions Read our FAQs Contact customer support Fig. 1: The total number of referrals pre- and postimplementation of the personalized self-referral chatbot. Fig. 2: Percentage change for sociodemographic groups for services implementing the personalized self-referral chatbot (pink) and the matched control services (gray). Fig. 3: Feedback themes from minority (pink bars) and majority (gray bars) groups. Fig. 4: Illustrations of the personalized self-referral chatbot on the NHS Talking Therapies website. Fig. 5: The study design and treatment pathway in NHS Talking Therapies services. Similar content being viewed by others Innovation and challenges of artificial intelligence technology in personalized healthcare Article Open access 16 August 2024 Healthcare professionals and the public sentiment analysis of ChatGPT in clinical practice Article Open access 07 January 2025 Trust in AI-assisted health systems and AI’s trust in humans Article Open access 28 March 2025 Explore related subjects Discover the latest articles and news in related subjects. Health services Machine learning Medical research Data availability The referral data is publicly available on the NHS Digital database. The specific data used for the referral analysis is available in a dedicated GitHub repository. The qualitative feedback data will not be publicly available because the individuals did not provide explicit consent for the public sharing of this feedback data. Code availability The code used for the analyses is available at a dedicated GitHub repository. References World Health Organization. World mental health report: transforming mental health for all. www.who.int/publications/i/item/9789240049338 (2022). Steel, Z. et al. The global prevalence of common mental disorders: a systematic review and meta-analysis 1980–2013. Int J. Epidemiol. 43 , 476–493 (2014). Article PubMed PubMed Central Google Scholar Thome, J. et al. The impact of the early phase of the COVID-19 pandemic on mental-health services in Europe. World J. Biol. Psychiatry 22 , 516–525 (2021). Article PubMed Google Scholar Ornell, F. et al. The next pandemic: impact of COVID-19 in mental healthcare assistance in a nationwide epidemiological study. Lancet Reg. Health Am. 4 , 100061 (2021). PubMed PubMed Central Google Scholar Loosen, A. M., Skvortsova, V. & Hauser, T. U. Obsessive–compulsive symptoms and information seeking during the COVID-19 pandemic. Transl. Psychiatry 11 , 309 (2021). Article CAS PubMed PubMed Central Google Scholar COVID-19 Mental Disorders Collaborators Global prevalence and burden of depressive and anxiety disorders in 204 countries and territories in 2020 due to the COVID-19 pandemic. Lancet 398 , 1700–1712 (2021). Article Google Scholar The Lancet Global Health. Mental health matters. Lancet. Glob. Health. 8 , e1352 (2020). Article CAS PubMed PubMed Central Google Scholar Cuijpers, P. et al. The effects of psychotherapies for major depression in adults on remission, recovery and improvement: a meta-analysis. J. Affect. Disord. 159 , 118–126 (2014). Article PubMed Google Scholar Hofmann, S. G. & Smits, J. A. Cognitive-behavioral therapy for adult anxiety disorders: a meta-analysis of randomized placebo-controlled trials. J. Clin. Psychiatry 69 , 621 (2008). Article PubMed PubMed Central Google Scholar World Health Organization. WHO report highlights global shortfall in investment in mental health. www.who.int/news/item/08-10-2021-who-report-highlights-global-shortfall-in-investment-in-mental-health (2021). Mahase, E. Workforce crisis has left mental health staff at ‘breaking point’ as demand rises. BMJ. 368 , m88 (2020). Article PubMed Google Scholar Wang, P. S. et al. Delay and failure in treatment seeking after first onset of mental disorders in the World Health Organization’s World Mental Health Survey Initiative. World Psychiatry. 6 , 177–185 (2007). PubMed PubMed Central Google Scholar Department of Health and Social Care. Progress in improving mental health services in England. www.nao.org.uk/wp-content/uploads/2023/02/Progress-in-improving-mental-health-services-CS.pdf (2023). Andrade, L. H. et al. Barriers to mental health treatment: results from the WHO World Mental Health surveys. Psychol. Med. 44 , 1303–1317 (2014). Article CAS PubMed Google Scholar Thornicroft, G. et al. The Lancet Commission on ending stigma and discrimination in mental health. Lancet 400 , 1438–1480 (2022). Article PubMed Google Scholar Clement, S. et al. What is the impact of mental health-related stigma on help-seeking? A systematic review of quantitative and qualitative studies. Psychol. Med. 45 , 11–27 (2015). Article CAS PubMed Google Scholar Corrigan, P. W., Druss, B. G. & Perlick, D. A. The impact of mental illness stigma on seeking and participating in mental health care. Psychol. Sci. Public Interest 15 , 37–70 (2014). Article PubMed Google Scholar Williams, M. E., Latta, J. & Conversano, P. Eliminating the wait for mental health services. J. Behav. Health Serv. Res. 35 , 107–114 (2008). Article PubMed Google Scholar Reichert, A. & Jacobs, R. The impact of waiting time on patient outcomes: evidence from early intervention in psychosis services in England. Health Econ. 27 , 1772–1787 (2018). Article PubMed PubMed Central Google Scholar De Girolamo, G., Dagani, J., Purcell, R., Cocchi, A. & McGorry, P. Age of onset of mental disorders and use of mental health services: needs, opportunities and obstacles. Epidemiol. Psychiatr. Sci. 21 , 47–57 (2012). Article PubMed Google Scholar Moitra, M. et al. The global gap in treatment coverage for major depressive disorder in 84 countries from 2000–2019: a systematic review and Bayesian meta-regression analysis. PLoS Med. 19 , e1003901 (2022). Article PubMed PubMed Central Google Scholar Volpe, U., Mihai, A., Jordanova, V. & Sartorius, N. The pathways to mental healthcare worldwide: a systematic review. Curr. Opin. Psychiatry 28 , 299–306 (2015). Article PubMed Google Scholar Brown, J. S., Boardman, J., Whittinger, N. & Ashworth, M. Can a self-referral system help improve access to psychological treatments? Br. J. Gen. Pract. 60 , 365–371 (2010). Article PubMed PubMed Central Google Scholar The National Collaborating Centre for Mental Health. The improving access to psychological therapies manual. www.england.nhs.uk/wp-content/uploads/2018/06/the-nhs-talking-therapies-manual-v6.pdf (2021). NHS Digital. Improving access to psychological therapies self-referral process research. digital.nhs.uk/publication-system/statistical/improving-access-to-psychological-therapies-key-performance-indicators-iapt-kpis/iapt-self-referral-process-research (2019). Car, L. et al. Conversational agents in healthcare: scoping review and conceptual analysis. J. Med. Internet Res. 22 , e17158 (2020). Article Google Scholar Rudd, B. N. & Beidas, R. S. Digital mental health: the answer to the global mental health crisis? JMIR Ment. Health 7 , e18472 (2020). Article PubMed PubMed Central Google Scholar Taylor, C. B., Fitzsimmons-Craft, E. E. & Graham, A. K. Digital technology can revolutionize mental health services delivery: the COVID-19 crisis as a catalyst for change. Int. J. Eat. Disord. 53 , 1155–1157 (2020). Article PubMed PubMed Central Google Scholar Kola, L. et al. COVID-19 mental health impact and responses in low-income and middle-income countries: reimagining global mental health. Lancet Psychiatry 8 , 535–550 (2021). Article PubMed PubMed Central Google Scholar Rollwage, M. et al. Using conversational AI to facilitate mental health assessments and improve clinical efficiency within psychotherapy services: real-world observational study. JMIR AI 2 , e44358 (2023). Article Google Scholar Jayaraajan, K. et al. The use of digital solutions in alleviating the burden of IAPT’s waiting times. Int. J. Risk Saf. Med. 33 , S1–S8 (2022). Google Scholar Koutsouleris, N., Hauser, T. U., Skvortsova, V. & DeChoudhury, M. From promise to practice: towards the realisation of AI-informed mental healthcare. Lancet Digit Health. 4 , e829–e840 (2022). Article CAS PubMed Google Scholar Rodríguez-Rivas, M. E., Cangas, A. J., Cariola, L. A., Varela, J. J. & Valdebenito, S. Innovative technology-based interventions to reduce stigma toward people with mental illness: systematic review and meta-analysis. JMIR Serious Games 10 , e35099 (2022). Article PubMed PubMed Central Google Scholar Johnson, J. A., Sanghvi, P. & Mehrotra, S. Technology-based interventions to improve help-seeking for mental health concerns: a systematic review. Indian J. Psychol. Med. 44 , 332–340 (2022). Article PubMed Google Scholar Te Pas, M. E., Rutten, W. G., Bouwman, R. A. & Buise, M. P. User experience of a chatbot questionnaire versus a regular computer questionnaire: prospective comparative study. JMIR Med. Inform. 8 , e21982 (2020). Article Google Scholar Bhakta, R., Savin-Baden, M. & Tombs, G. Sharing secrets with robots? In Proc. EdMedia+ Innovate Learning (eds Viteli, J. & Leikomaa, M.) 2295–2301 (Association for the Advancement of Computing in Education, 2014). Kim, S., Lee, J. & Gweon, G. Comparing data from chatbot and web surveys: effects of platform and conversational style on survey response quality. In Proc. 2019 CHI Conference on Human Factors in Computing Systems 1–12 (Association for Computing Machinery, 2019). Lee, Y.-C. et al. ‘I hear you, I feel you’: encouraging deep self-disclosure through a chatbot. In Proc. 2020 CHI Conference on Human Factors in Computing Systems 1–12 (Association for Computing Machinery, 2020). Viduani, A. et al. in Digital Mental Health (eds Passos, I. C., Rabelo-da-Ponte, F. D. & Kapczinski, F.) 133–148 (Springer, 2023). https://doi.org/10.1007/978-3-031-10698-9 Lee, Y.-C. et al. Exploring effects of chatbot-based social contact on reducing mental illness stigma. In Proc. 2023 CHI Conference on Human Factors in Computing Systems (eds Schmidt, A. & Vaananen, K.) 1–16 (Association for Computing Machinery, 2023). Bansal, N. et al. Understanding ethnic inequalities in mental healthcare in the UK: a meta-ethnography. PLoS Med. 19 , e1004139 (2022). Article PubMed PubMed Central Google Scholar World Health Organization. Global strategy on digital health 2020–2025. www.who.int/docs/default-source/documents/gs4dhdaa2a9f352b0445bafbc79ca799dce4d.pdf (2021). The Lancet. Can digital technologies improve health? Lancet 398 , 1663 (2021). Article CAS PubMed PubMed Central Google Scholar Rollwage, M. et al. Conversational AI facilitates mental health assessments and is associated with improved recovery rates. Preprint at medRxiv https://doi.org/10.1101/2022.11.03.22281887 (2022). Kroenke, K., Spitzer, R. L. & Williams, J. B. The PHQ-9: validity of a brief depression severity measure. J. Gen. Intern Med. 16 , 606–613 (2001). Article CAS PubMed PubMed Central Google Scholar Spitzer, R. L., Kroenke, K., Williams, J. B. & Löwe, B. A brief measure for assessing generalized anxiety disorder: the GAD-7. Arch. Intern. Med. 166 , 1092–1097 (2006). Article PubMed Google Scholar Mundt, J. C., Marks, I. M., Shear, M. K. & Greist, J. M. The Work and Social Adjustment Scale: a simple measure of impairment in functioning. Br. J. Psychiatry 180 , 461–464 (2002). Article PubMed Google Scholar Rose, S. & Van der Laan, M. J. Why match? Investigating matched cag19se-control study designs with causal effect estimation. Int. J. Biostat. 5 , 1 (2009). Article PubMed Google Scholar NHS Digital. Psychological therapies: reports on the use of IAPT services, England September 2020 Final including report on the EA in IAPT pilot. digital.nhs.uk/data-and-information/publications/statistical/psychological-therapies-report-on-the-use-of-iapt-services/september-2020-final-including-a-report-on-the-iapt-employment-advisors-pilot (2001). National Institute for Clinical Excellence. Principles for Best Practice in Clinical Audit (Radcliffe Medical Press, 2002). Khanbhai, M. et al. Applying natural language processing and machine learning techniques to patient experience feedback: a systematic review. BMJ Health Care Inform. 28 , e100262 (2021). Article PubMed PubMed Central Google Scholar Clarke, V. & Braun, V. Thematic analysis. J. Posit. Psychol. 12 , 297–298 (2016). Article Google Scholar Laugwitz, B., Held, T. & Schrepp, M. Construction and evaluation of a user experience questionnaire. In HCI and Usability for Education and Work. USAB 2008. Lecture Notes in Computer Science , Vol. 5298 (ed. Holzinger, A.) 63–76 (Springer, 2008). Download references Acknowledgements This work was supported by Limbic Limited. We thank E. Ivanova for her contribution to the figures and illustrations and S. Pisupati for reviewing the analysis code. Author information Authors and Affiliations Limbic, London, UK Johanna Habicht, Sruthi Viswanathan, Ben Carrington, Tobias U. Hauser, Ross Harper & Max Rollwage Max Planck UCL Centre for Computational Psychiatry and Ageing Research, University College London, London, UK Tobias U. Hauser Department of Psychiatry and Psychotherapy, Medical School and University Hospital, Eberhard Karls University of Tübingen, Tübingen, Germany Tobias U. Hauser German Center for Mental Health (DZPG), Tübingen, Germany Tobias U. Hauser Authors Johanna Habicht View author publications Search author on: PubMed Google Scholar Sruthi Viswanathan View author publications Search author on: PubMed Google Scholar Ben Carrington View author publications Search author on: PubMed Google Scholar Tobias U. Hauser View author publications Search author on: PubMed Google Scholar Ross Harper View author publications Search author on: PubMed Google Scholar Max Rollwage View author publications Search author on: PubMed Google Scholar Contributions J.H. and M.R. conceived and planned the study with input from B.C. and R.H. J.H. analyzed the data with input from M.R. and T.U.H. S.V. performed the thematic analysis, which was further discussed with J.H. and M.R.; M.R. and J.H. developed the NLP model. J.H. wrote the first draft of the manuscript with edits from all other authors. Corresponding author Correspondence to Johanna Habicht . Ethics declarations Competing interests J.H., S.V., B.C., R.H. and M.R. are employed by Limbic Limited and hold shares in the company. T.U.H. is working as a paid consultant for Limbic Limited and holds shares in the company. Peer review Peer review information Nature Medicine thanks Stefan Rennick-Egglestone and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. Primary Handling Editor: Lorenzo Righetto, in collaboration with the Nature Medicine team. Additional information Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Extended data Extended Data Fig. 1 Percentage change for different sexuality groups for services implementing the personalized self-referral chatbot (pink) and the matched control services (gray). No difference between the percentage change in referrals for services using the chatbot compared to the control services was observed for non-binary individuals (OR = 1.12, CI = [0.998, 1.251], p = 0.053) or gay and lesbians (OR = 1.01, CI = [0.838, 1.228], p = 0.882). There was a significant increase in heterosexual individuals in services using the chatbot compared to matched services (OR = 1.05, CI = [1.026, 1.084], p < 0.001). We did not find any difference between the referrals from bisexual and heterosexual individuals between services (interaction term: OR = 1.06, CI = [0.944,1.190], p = 0.326), or between gay/lesbian and heterosexual individuals (OR = 0.96, CI = [0.793,1.167], p = 0.695). ***p < 0.001, n.s. p > 0.05. Supplementary information Supplementary Information (download PDF ) Supplementary Figs. 1–5 and Supplementary Tables 1–4. Reporting Summary (download PDF ) Rights and permissions Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. Reprints and permissions About this article Cite this article Habicht, J., Viswanathan, S., Carrington, B. et al. Closing the accessibility gap to mental health treatment with a personalized self-referral chatbot. Nat Med 30 , 595–602 (2024). https://doi.org/10.1038/s41591-023-02766-x Download citation Received : 11 May 2023 Accepted : 14 December 2023 Published : 05 February 2024 Version of record : 05 February 2024 Issue date : February 2024 DOI : https://doi.org/10.1038/s41591-023-02766-x Share this article Anyone you share the following link with will be able to read this content: Get shareable link Sorry, a shareable link is not currently available for this article. Copy shareable link to clipboard Provided by the Springer Nature SharedIt content-sharing initiative Access through your institution Buy or subscribe Associated content Collection Digital Media and Mental Health An AI chatbot for talking therapy referrals Jacqueline Sin Nature Medicine News & Views 05 Feb 2024 Advertisement Explore content Research articles Reviews & Analysis News & Comment Podcasts Current issue Collections Follow us on Facebook Follow us on X Subscribe Sign up for alerts RSS feed About the journal Aims & Scope Journal Information Journal Metrics About the Editors Research Cross-Journal Editorial Team Reviews Cross-Journal Editorial Team Statistical Advisory Panel Our publishing models Editorial Values Statement Editorial Policies Content Types Web Feeds Contact Publish with us Submission Guidelines For Reviewers Language editing services Open access funding Submit manuscript Search Search articles by subject, keyword or author Show results from All journals This journal Search Advanced search Quick links Explore articles by subject Find a job Guide to authors Editorial policies Nature Medicine ( Nat Med ) ISSN 1546-170X (online) ISSN 1078-8956 (print) nature.com footer links About Nature Portfolio About us Press releases Press office Contact us Discover content Journals A-Z Articles by subject protocols.io Nature Index Publishing policies Nature portfolio policies Open access Author & Researcher services Reprints & permissions Research data Language editing Scientific editing Nature Masterclasses Research Solutions Libraries & institutions Librarian service & tools Librarian portal Open research Recommend to library Advertising & partnerships Advertising Partnerships & Services Media kits Branded content Professional development Nature Awards Nature Careers Nature Conferences Regional websites Nature Africa Nature China Nature India Nature Japan Nature Middle East Privacy Policy Use of cookies Your privacy choices/Manage cookies Legal notice Accessibility statement Terms & Conditions Your US state privacy rights © 2026 Springer Nature Limited Close banner Close Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily. Email address Sign up I agree my information will be processed in accordance with the Nature and Springer Nature Limited Privacy Policy . Close banner Close Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing