Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 May;29(5):e70016.
doi: 10.1002/ejp.70016.

Conversational Agents to Support Pain Management: A Scoping Review

Filipe L Souza  1   2   3 , Hannah Bowman  2 , Francis Yang  2   3 , Negin Hesam-Shariati  3   4 , Jackson Linke  2   3 , Yannick L Gilanyi  2   3 , Matthew D Jones  2   3 , Rafael Z-Pinto  2   3 , James H McAuley  2   3 , Rodrigo R N Rizzo  2   3
Affiliations

Conversational Agents to Support Pain Management: A Scoping Review

Filipe L Souza et al. Eur J Pain. 2025 May.

Abstract

Background: Pain-related conditions are the leading cause of years lived with disability globally. Managing pain presents significant challenges, including the need to address multiple biopsychosocial factors and the difficulty in delivering evidence-based treatments. Digital health technologies, such as conversational agents, offer the potential for personalised and accessible pain management. However, the characteristics and effectiveness of these interventions are not yet fully understood. This scoping review aims to comprehensively evaluate the applications and effectiveness of conversational agents in supporting pain management in adults (i.e., healthy individuals at risk of developing pain, individuals currently experiencing pain and healthcare providers or students involved in managing pain conditions).

Methods: Searches were systematically conducted across six databases-MEDLINE PubMed, ACM Digital Library, CINAHL, Embase, PsycINFO, Cochrane CENTRAL-and five trial registries from inception.

Results: Twenty-eight studies were included, focusing on capturing health information (n = 8), providing emotional support (n = 7), facilitating adherence to self-management exercises (n = 6), delivering psychological treatment (n = 5), offering organisational support (n = 1) and educating healthcare providers (n = 1). These studies addressed conditions with pain as a central or common symptom, including dementia (n = 7), cancer (n = 5) and musculoskeletal disorders (n = 4), among others. None of the conversational agents on the market covered all four stages recommended for translational research (development, feasibility, effectiveness and implementation).

Conclusion: The use of conversational agents in pain management is relatively new and involves diverse and promising appllications. However, evidence supporting their effectiveness in improving pain-related outcomes remains limited and heterogeneous. Future reseacrh should prioritise feasibility, reliability, and user experience studies to inform the design of robust randomised controlled trials.

Significance: This scoping review comprehensively examines the use of conversational agents (CAs) in adult pain management. The study identified six applications of CAs to support pain management and highlights a lack of high-quality randomised controlled trials, particularly those preceded by development and feasibility studies. Clinicians and researchers can use these insights to guide future studies and improve applications of CAs in pain management.

Keywords: artificial intelligence; artificial intelligence assistants; chatbot; conversational agents; pain management; review.

PubMed Disclaimer

Conflict of interest statement

R.R.N.R. provided consultancy on pain education content for a digital health company not related to conversational agents. The other authors have no conflicts of interest to declare.

Figures

FIGURE 1
FIGURE 1
PRISMA flow diagram.
FIGURE 2
FIGURE 2
The purpose of the interventions used in the included studies.
FIGURE 3
FIGURE 3
Number of studies in each evaluation stage of the lifecycle of healthcare interventions.
FIGURE 4
FIGURE 4
Risk‐of‐bias summary of the included RCTs in the scoping review.
See this image and copyright information in PMC

References

    1. ACTRN12621001010886 . 2021. “Evaluating the Effectiveness of a Social Robot Intervention on Pain Management in People Older Than 65 and Older Who Have Dementia Living in Residential Aged Care Facilities: A Cluster Randomised Controlled Tria.” https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=382165.
    1. Allouch, M. , Azaria A., and Azoulay R.. 2021. “Conversational Agents: Goals, Technologies, Vision and Challenges.” Sensors 21, no. 24: 8448. 10.3390/s21248448. - DOI - PMC - PubMed
    1. Anan, T. , Kajiki S., Oka H., et al. 2021. “Effects of an Artificial Intelligence‐Assisted Health Program on Workers With Neck/Shoulder Pain/Stiffness and Low Back Pain: Randomized Controlled Trial.” JMIR mHealth and uHealth 9, no. 9: e27535. 10.2196/27535. - DOI - PMC - PubMed
    1. Blasco, J. M. , Diaz‐Diaz B., Igual‐Camacho C., Perez‐Maletzki J., Hernandez‐Guilen D., and Roig‐Casasus S.. 2023. “Effectiveness of Using a Chatbot to Promote Adherence to Home Physiotherapy After Total Knee Replacement, Rationale and Design of a Randomized Clinical Trial.” BMC Musculoskeletal Disorders 24, no. 1: 491. 10.1186/s12891-023-06607-3. - DOI - PMC - PubMed
    1. Brozek, J. , Canelo‐Aybar C., Akl E., et al. 2021. “GRADE Guidelines 30: The GRADE Approach to Assessing the Certainty of Modeled Evidence‐An Overview in the Context of Health Decision‐Making.” Journal of Clinical Epidemiology 129: 138–150. 10.1016/j.jclinepi.2020.09.018. - DOI - PMC - PubMed

Publication types