Personalised socially assistive robot for cardiac rehabilitation: Critical reflections on long-term interactions in the real world.

Cardiac rehabilitation Human–robot interaction Long-term interaction Personalisation in social robots Real-world study Socially assistive robotics

Journal

User modeling and user-adapted interaction
ISSN: 0924-1868
Titre abrégé: User Model User-adapt Interact
Pays: Netherlands
ID NLM: 101149751

Informations de publication

Date de publication:
2023
Historique:
received: 04 03 2021
accepted: 04 03 2022
medline: 26 7 2022
pubmed: 26 7 2022
entrez: 25 7 2022
Statut: ppublish

Résumé

Lack of motivation and low adherence rates are critical concerns of long-term rehabilitation programmes, such as cardiac rehabilitation. Socially assistive robots are known to be effective in improving motivation in therapy. However, over longer durations, generic and repetitive behaviours by the robot often result in a decrease in motivation and engagement, which can be overcome by personalising the interaction, such as recognising users, addressing them with their name, and providing feedback on their progress and adherence. We carried out a real-world clinical study, lasting 2.5 years with 43 patients to evaluate the effects of using a robot and personalisation in cardiac rehabilitation. Due to dropouts and other factors, 26 patients completed the programme. The results derived from these patients suggest that robots facilitate motivation and adherence, enable prompt detection of critical conditions by clinicians, and improve the cardiovascular functioning of the patients. Personalisation is further beneficial when providing high-intensity training, eliciting and maintaining engagement (as measured through gaze and social interactions) and motivation throughout the programme. However, relying on full autonomy for personalisation in a real-world environment resulted in sensor and user recognition failures, which caused negative user perceptions and lowered the perceived utility of the robot. Nonetheless, personalisation was positively perceived, suggesting that potential drawbacks need to be weighed against various benefits of the personalised interaction.

Identifiants

pubmed: 35874292
doi: 10.1007/s11257-022-09323-0
pii: 9323
pmc: PMC9294801
doi:

Types de publication

Journal Article

Langues

eng

Pagination

497-544

Informations de copyright

© The Author(s), under exclusive licence to Springer Nature B.V. 2022.

Déclaration de conflit d'intérêts

Conflict of interestThe authors have no conflicts of interest to declare that are relevant to the content of this article.

Références

Biochem Med (Zagreb). 2012;22(3):276-82
pubmed: 23092060
Front Robot AI. 2020 Aug 04;7:92
pubmed: 33501259
Patient Educ Couns. 2013 Aug;92(2):174-81
pubmed: 23684366
Circulation. 2010 Jan 5;121(1):63-70
pubmed: 20026778
Stud Health Technol Inform. 2009;145:249-62
pubmed: 19592798
Soc Sci Med. 2000 Feb;50(4):495-506
pubmed: 10641802
EClinicalMedicine. 2019 Jul 03;13:31-45
pubmed: 31517261
J Med Internet Res. 2018 Feb 13;20(2):e45
pubmed: 29439942
Front Neurorobot. 2021 Mar 16;15:633248
pubmed: 33828473
Heart. 2009 Feb;95(4):271-5
pubmed: 18208830
J Neuroeng Rehabil. 2007 Feb 19;4:5
pubmed: 17309795
Iran J Nurs Midwifery Res. 2012 May;17(4):318-24
pubmed: 23833634
Annu Int Conf IEEE Eng Med Biol Soc. 2011;2011:5368-71
pubmed: 22255551
Front Robot AI. 2019 Nov 06;6:110
pubmed: 33501125
Psychophysiology. 2003 Jul;40(4):586-96
pubmed: 14570166
Aging Ment Health. 2018 Feb;22(2):149-167
pubmed: 28282732
Neural Comput. 1998 Sep 15;10(7):1895-1923
pubmed: 9744903
Disabil Rehabil. 2004 Jan 7;26(1):1-8
pubmed: 14660192
Am J Cardiol. 2000 Jul 1;86(1):17-23
pubmed: 10867086
Health Technol Assess. 2007 Sep;11(35):1-118
pubmed: 17767899
Proc (Bayl Univ Med Cent). 2007 Oct;20(4):344-7
pubmed: 17948105
Circulation. 1972 Nov;46(5):956-62
pubmed: 5081147
Front Aging Neurosci. 2015 Jul 23;7:141
pubmed: 26257646
IEEE Int Conf Rehabil Robot. 2017 Jul;2017:1013-1018
pubmed: 28813954
Sensors (Basel). 2020 Jul 05;20(13):
pubmed: 32635640
Hum Factors. 2011 Oct;53(5):517-27
pubmed: 22046724
IEEE Trans Pattern Anal Mach Intell. 2018 Mar;40(3):762-768
pubmed: 28541894
BMC Geriatr. 2019 Aug 23;19(1):232
pubmed: 31443636
Med Educ. 2004 Dec;38(12):1217-8
pubmed: 15566531
J Am Coll Cardiol. 2009 Jun 30;54(1):25-33
pubmed: 19555836
Psychol Serv. 2016 Aug;13(3):292-299
pubmed: 27195530
Int J Soc Robot. 2018;10(3):343-355
pubmed: 30996753
J Sci Med Sport. 2014 Sep;17(5):541-5
pubmed: 23988787
Appl Physiol Nutr Metab. 2012 Apr;37(2):206-13
pubmed: 22360343
Sci Robot. 2018 Aug 22;3(21):
pubmed: 33141724

Auteurs

Bahar Irfan (B)

Centre for Robotics and Neural Systems, University of Plymouth, Plymouth, UK.
Present Address: Evinoks Service Equipment Industry and Commerce Inc., Bursa, Turkey.

Nathalia Céspedes (N)

Department of Biomedical Engineering, Colombian School of Engineering Julio Garavito, Bogotá, Colombia.
Present Address: Department of Computer Science and Electronic Engineering, Queen Mary University of London, London, UK.

Jonathan Casas (J)

Department of Biomedical Engineering, Colombian School of Engineering Julio Garavito, Bogotá, Colombia.
Present Address: Mechanical and Aerospace Engineering Department, Syracuse University, Syracuse, NY USA.

Emmanuel Senft (E)

Centre for Robotics and Neural Systems, University of Plymouth, Plymouth, UK.
Present Address: Department of Computer Sciences, University of Wisconsin-Madison, Madison, WI USA.

Luisa F Gutiérrez (LF)

Instituto de Cardiología, Fundación Cardioinfantil, Bogotá, Colombia.

Mónica Rincon-Roncancio (M)

Instituto de Cardiología, Fundación Cardioinfantil, Bogotá, Colombia.

Carlos A Cifuentes (CA)

Present Address: School of Engineering, Science and Technology, Universidad del Rosario, Bogotá, Colombia.

Tony Belpaeme (T)

Centre for Robotics and Neural Systems, University of Plymouth, Plymouth, UK.
IDLab-imec, Ghent University, Ghent, Belgium.

Marcela Múnera (M)

Department of Biomedical Engineering, Colombian School of Engineering Julio Garavito, Bogotá, Colombia.

Classifications MeSH