Considering patient safety in autonomous e-mental health systems - detecting risk situations and referring patients back to human care.

Publisher: BioMed Central Country of Publication: England NLM ID: 101088682 Publication Model: Electronic Cited Medium: Internet ISSN: 1472-6947 (Electronic) Linking ISSN: 14726947 NLM ISO Abbreviation: BMC Med Inform Decis Mak Subsets: MEDLINE

Original Publication: London : BioMed Central, [2001-

Mental Health Services* ; Patient Safety* ; Persuasive Communication* ; Referral and Consultation* ; Robotics* ; Telemedicine*; Mental Disorders/*therapy ; Risk Assessment/*methods; Adult ; Female ; Humans ; Male ; Middle Aged

Background: Digital health interventions can fill gaps in mental healthcare provision. However, autonomous e-mental health (AEMH) systems also present challenges for effective risk management. To balance autonomy and safety, AEMH systems need to detect risk situations and act on these appropriately. One option is sending automatic alerts to carers, but such 'auto-referral' could lead to missed cases or false alerts. Requiring users to actively self-refer offers an alternative, but this can also be risky as it relies on their motivation to do so. This study set out with two objectives. Firstly, to develop guidelines for risk detection and auto-referral systems. Secondly, to understand how persuasive techniques, mediated by a virtual agent, can facilitate self-referral.
Methods: In a formative phase, interviews with experts, alongside a literature review, were used to develop a risk detection protocol. Two referral protocols were developed - one involving auto-referral, the other motivating users to self-refer. This latter was tested via crowd-sourcing (n = 160). Participants were asked to imagine they had sleeping problems with differing severity and user stance on seeking help. They then chatted with a virtual agent, who either directly facilitated referral, tried to persuade the user, or accepted that they did not want help. After the conversation, participants rated their intention to self-refer, to chat with the agent again, and their feeling of being heard by the agent.
Results: Whether the virtual agent facilitated, persuaded or accepted, influenced all of these measures. Users who were initially negative or doubtful about self-referral could be persuaded. For users who were initially positive about seeking human care, this persuasion did not affect their intentions, indicating that a simply facilitating referral without persuasion was sufficient.
Conclusion: This paper presents a protocol that elucidates the steps and decisions involved in risk detection, something that is relevant for all types of AEMH systems. In the case of self-referral, our study shows that a virtual agent can increase users' intention to self-refer. Moreover, the strategy of the agent influenced the intentions of the user afterwards. This highlights the importance of a personalised approach to promote the user's access to appropriate care.

J Med Syst. 2017 Aug;41(8):125. (PMID: 28699083)
Behav Res Ther. 2016 Feb;77:147-56. (PMID: 26752328)
Harv Rev Psychiatry. 2010 Mar-Apr;18(2):80-95. (PMID: 20235773)
Community Ment Health J. 2015 Jul;51(5):509-12. (PMID: 25342076)
BMC Med Inform Decis Mak. 2019 Mar 18;19(1):47. (PMID: 30885190)
Artif Intell Med. 2014 Sep;62(1):1-10. (PMID: 25059820)
Ann N Y Acad Sci. 2001 Apr;932:200-21; discussion 221-4. (PMID: 11411187)
Nurs Health Sci. 2015 Jun;17(2):201-7. (PMID: 25472637)
J Gen Intern Med. 2017 Mar;32(3):245-255. (PMID: 27714649)
Psychol Bull. 1992 Jul;112(1):155-9. (PMID: 19565683)
Am J Public Health. 2007 Dec;97(12):2193-8. (PMID: 17971541)
Stud Health Technol Inform. 2012;181:329-33. (PMID: 22954882)
Sleep Med Rev. 2002 Apr;6(2):97-111. (PMID: 12531146)
Arch Gen Psychiatry. 2004 Aug;61(8):807-16. (PMID: 15289279)
Psychiatr Serv. 2013 Dec 1;64(12):1195-202. (PMID: 24036589)
Contemp Clin Trials. 2013 Nov;36(2):327-37. (PMID: 23974036)
J Ment Health. 2012 Aug;21(4):327-31. (PMID: 22823092)
J Nerv Ment Dis. 2013 Sep;201(9):802-12. (PMID: 23995037)
J Psychiatr Ment Health Nurs. 2009 Aug;16(6):501-7. (PMID: 19594671)
Psychol Med. 2015 Dec;45(16):3357-76. (PMID: 26235445)
Stud Health Technol Inform. 2013;184:151-7. (PMID: 23400148)
Lancet. 2016 Mar 19;387(10024):1227-39. (PMID: 26385066)
J Clin Nurs. 2013 Nov;22(21-22):3203-16. (PMID: 22860919)
J Psychosom Res. 2015 Apr;78(4):340-5. (PMID: 25592159)
Stud Health Technol Inform. 2011;163:503-9. (PMID: 21335847)
Community Ment Health J. 2014 Apr;50(3):339-42. (PMID: 23306676)
J Med Internet Res. 2017 May 09;19(5):e151. (PMID: 28487267)
Early Interv Psychiatry. 2015 Dec;9(6):498-506. (PMID: 24684927)
Br J Psychiatry. 2005 Jan;186:11-7. (PMID: 15630118)
Curr Psychiatry Rep. 2015 Jan;17(1):533. (PMID: 25413639)
Implement Sci. 2011 Apr 23;6:42. (PMID: 21513547)
Med Care Res Rev. 2002 Sep;59(3):293-318. (PMID: 12205830)
J Affect Disord. 2014 Jun;162:73-80. (PMID: 24767009)
Med Educ Online. 2013 Jul 23;18:21747. (PMID: 23883565)
Int J Environ Res Public Health. 2014 Aug 12;11(8):8193-212. (PMID: 25119698)

Keywords: Assistive technologies; Chatbots; Conversational agents; Persuasive computing; Risk; Robotics; Virtual agents; eHealth

Date Created: 20190320 Date Completed: 20190704 Latest Revision: 20240715

20260130

PMC6421702

10.1186/s12911-019-0796-x

30885190