Published on in Vol 11, No 10 (2022): October

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/40265, first published .
Interactive Conversational Agents for Health Promotion, Prevention, and Care: Protocol for a Mixed Methods Systematic Scoping Review

Interactive Conversational Agents for Health Promotion, Prevention, and Care: Protocol for a Mixed Methods Systematic Scoping Review

Interactive Conversational Agents for Health Promotion, Prevention, and Care: Protocol for a Mixed Methods Systematic Scoping Review

Protocol

1Faculté des Sciences Infirmières, Université Laval, Québec, QC, Canada

2Faculté de Médecine, Université Laval, Québec, QC, Canada

3Bibliothèque – Direction des Services-Conseils, Université Laval, Québec, QC, Canada

Corresponding Author:

Maxime Sasseville, RN, PhD

Faculté des Sciences Infirmières

Université Laval

1050, Avenue de la Médecine

Québec, QC, R-G1V 0A6

Canada

Phone: 1 418 656 3356

Email: maxime.sasseville@fsi.ulaval.ca


Background: Interactive conversational agents, also known as “chatbots,” are computer programs that use natural language processing to engage in conversations with humans to provide or collect information. Although the literature on the development and use of chatbots for health interventions is growing, important knowledge gaps remain, such as identifying design aspects relevant to health care and functions to offer transparency in decision-making automation.

Objective: This paper presents the protocol for a scoping review that aims to identify and categorize the interactive conversational agents currently used in health care.

Methods: A mixed methods systematic scoping review will be conducted according to the Arksey and O’Malley framework and the guidance of Peters et al for systematic scoping reviews. A specific search strategy will be formulated for 5 of the most relevant databases to identify studies published in the last 20 years. Two reviewers will independently apply the inclusion criteria using the full texts and extract data. We will use structured narrative summaries of main themes to present a portrait of the current scope of available interactive conversational agents targeting health promotion, prevention, and care. We will also summarize the differences and similarities between these conversational agents.

Results: The search strategy and screening steps were completed in March 2022. Data extraction and analysis started in May 2022, and the results are expected to be published in October 2022.

Conclusions: This fundamental knowledge will be useful for the development of interactive conversational agents adapted to specific groups in vulnerable situations in health care and community settings.

International Registered Report Identifier (IRRID): DERR1-10.2196/40265

JMIR Res Protoc 2022;11(10):e40265

doi:10.2196/40265

Keywords



Digital technologies are an engine of transformation in the health sector and represent a promising avenue for improving access to care, care personalization, health prevention, and health promotion, particularly for those in vulnerable situations [1]. Health technologies are increasingly necessary to support and improve health care access [2,3].

Conversational agents, also known as “chatbots,” are computer programs that use natural language processing to engage in conversations with humans to provide or collect information [4-6]. Chatbots use algorithms to simulate a human conversation via text or voice messages. They are easy to use for patients and require minimal computer literacy and knowledge [7,8]. Chatbots can use simple predetermined conversation algorithms to simulate conversation or more complex systems based on neural networks and deep learning to understand speech, produce a voiced answer, and simulate social interaction [9]. Chatbots allow for automated interventions with customizable, accessible, and cost-effective software [8].

Although the literature on the development and use of chatbots for patients’ health is growing, there are still important knowledge gaps that remain, such as identifying design aspects relevant to health care and functions to offer transparency in decision-making automation [7,10,11]. Moreover, despite increasing developments in digital technologies and the implementation of conversational agents in a wide range of domains, their use in health care is still limited [12]. Chatbots are primarily developed for a specific context of care, so little is known about the greater contextual application of chatbots in health care. Providing an exhaustive portrait of current chatbots used in health care is a significant step toward understanding the position of chatbots in the current infrastructure of care. This review is interested in chatbots that were able to adapt and simulate interactive conversations as opposed to chatbots offering users constrained multiple-choice options, thus limiting the impression of real and meaningful interactions.

The goal of this mixed methods systematic scoping review is to identify and categorize interactive conversational technologies currently used in health promotion, prevention, and care.


Overview

A mixed methods systematic scoping review will be conducted according to the Arksey and O’Malley [13] framework and the guidance of Peters et al [14] for systematic scoping reviews. This literature review will focus on studies on interactive conversational agents for health promotion, prevention, and care. As this topic is complex and heterogeneous, a review of the scope of the literature will help tailor future systematic reviews and research endeavors. The PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) criteria will be used to report the results [15].

Our key synthesis question is as follows: (1) in which population and settings are interactive conversational agents used for health promotion, prevention, and care? and (2) what are the characteristics of the technologies supporting these interactive conversational agents?

Eligibility Criteria

We will address all types of evidence matching the PICOS (population, intervention, comparison, outcomes, setting or context) criteria:

  • Participants or population: we will include all studies targeting laypeople (eg, patients, students, citizens). Studies targeting only health care providers will be excluded.
  • Interventions or phenomena of interest: we will include all interactive conversational agents, that is, those involving a 2-way exchange (written, oral, and visual dialogue), directed at laypeople for health promotion, prevention, and care.
  • Comparator: no restrictions will be applied.
  • Outcomes: we will consider all outcomes reported in the studies. We will seek outcomes related to patients, caregivers, health care providers, and policy makers. Those could include barriers, facilitators, acceptability, feasibility, adoption, fidelity, morbidity, mortality, quality of life, satisfaction, cost, and cost-effectiveness.
  • Setting: we will include studies taking place in a health care or community setting, in any geographical area. All types of studies will be included (qualitative, quantitative, and mixed methods).

Search Strategy

The search strategy was developed in collaboration with a university librarian who has experience in literature reviews (FB) (Multimedia Appendix 1). An iterative process of revision by members of the research team took place, and all relevant comments were integrated into the final version of the search strategy. The final version was approved by all team members. A specific search strategy was formulated for each of the following databases: MEDLINE (Ovid), Embase, Inspec (Engineering Village), Web of Science, and CINAHL. The search will be restricted to studies from the last 20 years because of the recent nature of conversational agents. No restriction on language was applied to the search. Terms such as chatbot, conversational agent, virtual embodied agent, and their spelling variants were used for the search. Additionally, since innovation implementations are often conducted by the private sector, we performed an internet search in the following sources and databases: Google, Google Scholar, Institut national d’excellence en santé et en services sociaux, Canadian Evaluation Society, EuroScan, OpenGrey, Grey Literature Report, GreyNet, and Grey Matters. The search also included a hand search, and bibliographies were reviewed for additional relevant references. The search strategy is presented in Multimedia Appendix 1.

Data Collection

All citations will be exported to the online collaboration tool Covidence (Veritas Health Innovation) [16], where duplicates will be removed by its automated function. An independent assessment of inclusion criteria will be done by at least 2 reviewers. Reviewers will search and obtain all the full texts of the selected references and will import the PDF files in Covidence. Two reviewers will independently apply the inclusion criteria using the full texts. Reasons for exclusion will be recorded in Covidence. A PRISMA flowchart will be used to describe the identifications of studies, the screening process, and the application of inclusion and exclusion criteria [17].

Data Extraction

Team members will complete the extraction, and the data will be reviewed by an experienced researcher (MPG or MS). We will extract descriptive data (title, year of publication, authors, country), study type (published or gray literature, study design), intervention data (name of the technology, language of the technology, implementation channel, and features like audio, text, voice, avatar), setting data (target population, place of implementation), sample data (comparator, number of participants, sample sizes), outcomes (process, patients, providers, or systems related), and outcome type (qualitative and quantitative). We will appraise the quality of the studies included by applying the Mixed Methods Appraisal Tool [18].

Data Synthesis

We will complete the data synthesis using structured narrative summaries of main themes and provide a portrait of the current scope of available technologies using descriptive analysis. A summary of the differences and similarities between conversational agents will highlight the following points: strengths and weaknesses, main outcomes, main resources used, and trade-offs. A map of outcomes and targeted populations will be built and presented [14].


The search strategy and screening steps of the review were completed in March 2022. Data extraction and analysis began in May 2022, and the results are expected to be published in October 2022.


Main Contributions of This Scoping Review

Literature reviews on chatbots in health care are available in specific contexts, such as mental health management [19-21], prevention of COVID-19 [22], health behavior change [23,24], chronic conditions management [25], and medical education [26]. A systematic review by Laranjo et al [12] was completed in 2018 with a global scope, but it was aimed at patients and providers and focused only on verbal communication. To our knowledge, our review is the first endeavor aiming to offer an overarching map of the research on interactive conversational agents targeting laypeople in all contexts of care. As there are many pilot and usability studies on the topic, summarizing evidence by context and type of technology will offer a unique view of how and for whom conversational agents are used. This review will also explore whether these technologies are useful and successful in managing health issues.

Potential Impact and Future Directions

There is a human resources crisis in health care. Worldwide shortages in health care professionals, increasing burnout rates, and an aging population are 3 major factors causing an imbalance in the offering and demand of health care services [27,28]. Focused technologies and tools such as interactive conversational agents are needed to overcome the potential abyss of human resource shortage in health care by reducing cost and improving access. Understanding what is currently offered in health care has the potential to help researchers, health care professionals, and decision-makers to develop, implement, or test solutions.

Accelerated by the COVID-19 pandemic, the shift to digital care has caused health inequities [29]. This review will thus pay particular attention to how equity, diversity, and inclusion have been considered in the development of conversational agents. Vulnerable populations often do not have the skills and opportunities to use chatbots [30]. Indeed, personal characteristics (eg, advanced age, chronic diseases, disability situation, lack of digital literacy) or contextual factors (eg, poverty, housing, irregular migrant status) may make chatbots unfavorable for use. Moreover, in their interaction with individuals, chatbots cannot always evolve with time and adapt to the user’s literacy skills and language level. Thus, they sometimes are unable to adapt to dynamic user behavior and offer customized responses tailored to the user’s personality [31,32]. Therefore, the development of conversational agents adapted to the needs of individuals, especially those in vulnerable situations, remains a major challenge for researchers [33]. This review could contribute to the inclusion of the needs of vulnerable populations when designing conversational agents [30].

Finally, the widespread implementation of conversational agents is still burdened by ethical and clinical implications [23]. Shifting to an artificial relationship removes human-to-human communication from the care process. Understanding the level of involvement of professionals in the human-machine relationship remains an area of research worth considering. The burden of decision-making also emanates from that problem. As professionals are assisted by technological tools, we need to think about who is responsible for the information and decisions offered by technology that can be potentially harmful to patients [34]. On a more macro level, the use of conversational agents could support a shift toward disease prevention rather than treatment, thus leading to large-scale benefits for the whole society [7].

Conclusion

The results of this scoping review will provide a portrait of interactive conversational agents and their various applications in health promotion, prevention, and care. This fundamental knowledge will be useful for the development of interactive conversational agents adapted to specific users and people in vulnerable situations.

Acknowledgments

This project is funded by a Research Development Grant from Université Laval’s Faculty of Nursing Sciences.

Data Availability

The data for this review will be deposited and made available online in the Open Science Framework depository.

Conflicts of Interest

None declared.

Multimedia Appendix 1

Detailed search strategy.

PDF File (Adobe PDF File), 166 KB

  1. de Cock C, Milne-Ives M, van Velthoven MH, Alturkistani A, Lam C, Meinert E. Effectiveness of conversational agents (virtual assistants) in health care: protocol for a systematic review. JMIR Res Protoc 2020 Mar 9;9(3):e16934. [CrossRef]
  2. El Alami LSE, Nemoto A, Nakata Y. Investigation of users' experiences for online access to their electronic health records in Japan. Glob Health Med 2021 Feb 28;3(1):37-43 [FREE Full text] [CrossRef] [Medline]
  3. François J, Audrain-Pontevia AF. La santé numérique: un levier pour améliorer l'accessibilité aux soins de santé au Québec. Revue Organisations & Territoires 2020;29(3):41-55 [FREE Full text] [CrossRef]
  4. Denecke K, Tschanz M, Dorner TL, May R. Intelligent conversational agents in healthcare: hype or hope? Stud Health Technol Inform 2019;259:77-84. [Medline]
  5. Montenegro JLZ, da Costa CA, da Rosa Righi R. Survey of conversational agents in health. Expert Syst Appl 2019 Sep;129:56-67. [CrossRef]
  6. Tudor Car L, Dhinagaran DA, Kyaw BM, Kowatsch T, Joty S, Theng Y, et al. Conversational agents in health care: scoping review and conceptual analysis. J Med Internet Res 2020 Aug 07;22(8):e17158 [FREE Full text] [CrossRef] [Medline]
  7. Gabarron E, Larbi D, Denecke K, Årsand E. What do we know about the use of chatbots for public health? Stud Health Technol Inform 2020 Jun 16;270:796-800. [CrossRef] [Medline]
  8. Parmar P, Ryu J, Pandya S, Sedoc J, Agarwal S. Health-focused conversational agents in person-centered care: a review of apps. NPJ Digit Med 2022 Feb 17;5(1):21 [FREE Full text] [CrossRef] [Medline]
  9. Oh KJ, Lee D, Ko B, Choi HJ. A chatbot for psychiatric counseling in mental healthcare service based on emotional dialogue analysis and sentence generation. 2017 Presented at: 8th IEEE International Conference on Mobile Data Management (MDM); May 29 - Jun 1; Daejeon, Korea p. 371-375   URL: https://ieeexplore.ieee.org/document/7962482 [CrossRef]
  10. Jovanovic M, Baez M, Casati F. Chatbots as conversational healthcare services. IEEE Internet Comput 2021 May;25(3):44-51 [FREE Full text] [CrossRef]
  11. Chew HSJ, Achananuparp P. Perceptions and needs of artificial intelligence in health care to increase adoption: scoping review. J Med Internet Res 2022 Jan 14;24(1):e32939 [FREE Full text] [CrossRef] [Medline]
  12. Laranjo L, Dunn AG, Tong HL, Kocaballi AB, Chen J, Bashir R, et al. Conversational agents in healthcare: a systematic review. J Am Med Inform Assoc 2018 Sep 01;25(9):1248-1258 [FREE Full text] [CrossRef] [Medline]
  13. Arksey H, O'Malley L. Scoping studies: towards a methodological framework. Int J Soc Res 2005 Feb;8(1):19-32. [CrossRef]
  14. Peters MDJ, Godfrey C, McInerney P, Munn Z, Tricco AC, Khalil H. Chapter 11: Scoping reviews (2020 version). In: Aromataris E, Munn Z, editors. JBI Manual for Evidence Synthesis. Adelaide, Australia: JBI; 2020.
  15. Selçuk AA. A guide for systematic reviews: PRISMA. Turk Arch Otorhinolaryngol 2019 Mar 10;57(1):57-58 [FREE Full text] [CrossRef] [Medline]
  16. Covidence. Veritas Health Innovation.   URL: https://www.covidence.org/ [accessed 2022-10-03]
  17. Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ 2021 Mar 29;372:n71 [FREE Full text] [CrossRef] [Medline]
  18. Pace R, Pluye P, Bartlett G, Macaulay AC, Salsberg J, Jagosh J, et al. Testing the reliability and efficiency of the pilot Mixed Methods Appraisal Tool (MMAT) for systematic mixed studies review. Int J Nurs Stud 2012 Jan;49(1):47-53. [CrossRef] [Medline]
  19. Abd-Alrazaq AA, Rababeh A, Alajlani M, Bewick BM, Househ M. Effectiveness and safety of using chatbots to improve mental health: systematic review and meta-analysis. J Med Internet Res 2020 Jul 13;22(7):e16021 [FREE Full text] [CrossRef] [Medline]
  20. Vaidyam AN, Wisniewski H, Halamka JD, Kashavan MS, Torous JB. Chatbots and conversational agents in mental health: a review of the psychiatric landscape. Can J Psychiatry 2019 Jul;64(7):456-464 [FREE Full text] [CrossRef] [Medline]
  21. Abd-Alrazaq AA, Alajlani M, Alalwan AA, Bewick BM, Gardner P, Househ M. An overview of the features of chatbots in mental health: a scoping review. Int J Med Inform 2019 Dec;132:103978. [CrossRef] [Medline]
  22. Almalki M, Azeez F. Health chatbots for fighting COVID-19: a scoping review. Acta Inform Med 2020 Dec;28(4):241-247 [FREE Full text] [CrossRef] [Medline]
  23. Zhang J, Oh YJ, Lange P, Yu Z, Fukuoka Y. Artificial intelligence chatbot behavior change model for designing artificial intelligence chatbots to promote physical activity and a healthy diet: viewpoint. J Med Internet Res 2020 Sep 30;22(9):e22845 [FREE Full text] [CrossRef] [Medline]
  24. Pereira J, Díaz Ó. Using health chatbots for behavior change: a mapping study. J Med Syst 2019 Apr 04;43(5):135. [CrossRef] [Medline]
  25. Schachner T, Keller R, V Wangenheim F. Artificial intelligence-based conversational agents for chronic conditions: systematic literature review. J Med Internet Res 2020 Sep 14;22(9):e20701 [FREE Full text] [CrossRef] [Medline]
  26. Frangoudes F, Hadjiaros M, Schiza EC, Matsangidou M, Tsivitanidou O, Neokleous K. An overview of the use of chatbots in medical and healthcare education. In: Zaphiris P, Ioannou A, editors. Learning and Collaboration Technologies: Games and Virtual Environments for Learning. Lecture Notes in Computer Science, vol 12785. Cham: Springer; 2021:170-184.
  27. Meara JG, Leather AJM, Hagander L, Alkire BC, Alonso N, Ameh EA, et al. Global Surgery 2030: evidence and solutions for achieving health, welfare, and economic development. The Lancet 2015 Aug;386(9993):569-624. [CrossRef]
  28. Shanafelt TD, Hasan O, Dyrbye LN, Sinsky C, Satele D, Sloan J, et al. Changes in burnout and satisfaction with work-life balance in physicians and the general us working population between 2011 and 2014. Mayo Clin Proc 2015 Dec;90(12):1600-1613. [CrossRef] [Medline]
  29. Yao R, Zhang W, Evans R, Cao G, Rui T, Shen L. Inequities in health care services caused by the adoption of digital health technologies: scoping review. J Med Internet Res 2022 Mar 21;24(3):e34144 [FREE Full text] [CrossRef] [Medline]
  30. Luxton DD. Ethical implications of conversational agents in global public health. Bull World Health Organ 2020 Jan 27;98(4):285-287. [CrossRef]
  31. Ahmad R, Siemon D, Gnewuch U, Robra-Bissantz S. Designing personality-adaptive conversational agents for mental health care. Inf Syst Front 2022 Mar 02;24(3):923-943 [FREE Full text] [CrossRef] [Medline]
  32. Parviainen J, Rantala J. Chatbot breakthrough in the 2020s? An ethical reflection on the trend of automated consultations in health care. Med Health Care Philos 2022 Mar 04;25(1):61-71 [FREE Full text] [CrossRef] [Medline]
  33. Kocaballi AB, Berkovsky S, Quiroz JC, Laranjo L, Tong HL, Rezazadegan D, et al. The personalization of conversational agents in health care: systematic review. J Med Internet Res 2019 Nov 07;21(11):e15360 [FREE Full text] [CrossRef] [Medline]
  34. Powell J. Trust me, I’m a chatbot: how artificial intelligence in health care fails the Turing Test. J Med Internet Res 2019 Oct 28;21(10):e16222 [FREE Full text] [CrossRef] [Medline]


PRISMA: Preferred Reporting Items for Systematic Reviews and Meta-Analyses
PRISMA-ScR: Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews
PICOS: population, intervention, comparison, outcomes, setting or context


Edited by T Leung; submitted 13.06.22; peer-reviewed by E Da Silva, C Jacob; comments to author 23.08.22; revised version received 01.09.22; accepted 22.09.22; published 11.10.22

Copyright

©Maxime Sasseville, Romina H Barony Sanchez, Achille R Yameogo, Laurie-Ann Bergeron-Drolet, Frédéric Bergeron, Marie-Pierre Gagnon. Originally published in JMIR Research Protocols (https://www.researchprotocols.org), 11.10.2022.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Research Protocols, is properly cited. The complete bibliographic information, a link to the original publication on https://www.researchprotocols.org, as well as this copyright and license information must be included.