Hybrid Ubiquitous Coaching With a Novel Combination of Mobile and Holographic Conversational Agents Targeting Adherence to Home Exercises: Four Design and Evaluation Studies

Abstract

Background Effective treatments for various conditions such as obesity, cardiac heart diseases, or low back pain require not only personal on-site coaching sessions by health care experts but also a significant amount of home exercises. However, nonadherence to home exercises is still a serious problem as it leads to increased costs due to prolonged treatments. Objective To improve adherence to home exercises, we propose, implement, and assess the novel coaching concept of hybrid ubiquitous coaching (HUC). In HUC, health care experts are complemented by a conversational agent (CA) that delivers psychoeducation and personalized motivational messages via a smartphone, as well as real-time exercise support, monitoring, and feedback in a hands-free augmented reality environment. Methods We applied HUC to the field of physiotherapy and conducted 4 design-and-evaluate loops with an interdisciplinary team to assess how HUC is perceived by patients and physiotherapists and whether HUC leads to treatment adherence. A first version of HUC was evaluated by 35 physiotherapy patients in a lab setting to identify patients’ perceptions of HUC. In addition, 11 physiotherapists were interviewed about HUC and assessed whether the CA could help them build up a working alliance with their patients. A second version was then tested by 15 patients in a within-subject experiment to identify the ability of HUC to address adherence and to build a working alliance between the patient and the CA. Finally, a 4-week n-of-1 trial was conducted with 1 patient to show one experience with HUC in depth and thereby potentially reveal real-world benefits and challenges. Results Patients perceived HUC to be useful, easy to use, and enjoyable, preferred it to state-of-the-art approaches, and expressed their intentions to use it. Moreover, patients built a working alliance with the CA. Physiotherapists saw a relative advantage of HUC compared to current approaches but initially did not see the potential in terms of a working alliance, which changed after seeing the results of HUC in the field. Qualitative feedback from patients indicated that they enjoyed doing the exercise with an augmented reality–based CA and understood better how to do the exercise correctly with HUC. Moreover, physiotherapists highlighted that HUC would be helpful to use in the therapy process. The longitudinal field study resulted in an adherence rate of 92% (11/12 sessions; 330/360 repetitions; 33/36 sets) and a substantial increase in exercise accuracy during the 4 weeks. Conclusions The overall positive assessments from both patients and health care experts suggest that HUC is a promising tool to be applied in various disorders with a relevant set of home exercises. Future research, however, must implement a variety of exercises and test HUC with patients suffering from different disorders.

Human Cues in eHealth to Promote Lifestyle Change: an Experimental Field Study to Examine Adherence to Self-help Interventions (Preprint)

“…Finally, we found that people who reported a better working alliance with the CA were more adherent to the intervention. This result is in line with studies about regular face-to-face interventions [24,25], digital therapy or treatment [26,27], and automated digital interventions [30,31,32,33,34]. Nonetheless, we did not find an effect of human cues on the reported working alliance with the CA.…”

“…Moreover, in studies that did find an improved working alliance with a CA either the interactions with the agent or the intervention itself were longer compared to those in our study [30,32]. In other studies, although a high working alliance was reported within shorter periods of time, the interactions with the CA followed after introduction by a human healthcare professional [33,34]. It is therefore unclear whether a TCA is less able to build a relationship with the user, or that it requires a longer time or introduction in a face-to-face introduction to do so.…”

“…People interact with computers as they would do with human beings, and apply similar social rules and heuristics [28,29]. Studies show that people can also develop a working alliance within fully automated digital interventions, and that this leads to more positive treatment outcomes [30][31][32][33][34].…”

The Use of Artificial Intelligence–Based Conversational Agents (Chatbots) for Weight Loss: Scoping Review and Practical Recommendations

“…A total of 20 studies were included in this review, of which 1 study comprised 4 separate studies [ 29 ], resulting in 23 studies (representing 2231 participants) evaluated in this review. A summary and detailed description of the study characteristics are shown in Table 1 and Multimedia Appendix 3 [ 25 , 26 , 29 - 47 ] and Multimedia Appendix 4 [ 25 , 26 , 29 - 37 , 39 - 47 ].…”

Neurorehabilitation From a Distance: Can Intelligent Technology Support Decentralized Access to Quality Therapy?

“…Algorithms should update therapy plans and other training parameters (e.g., suggest transfer to another RehabGym device/exercise), and inform on overall rehabilitation progress. Additionally, exercise adherence and motivation could be increased by integrating a conversational agent (i.e., chatbot) that educates users on relevant topics (e.g., healthy lifestyle) and provides personalized motivational messages, as well as real-time exercise support, monitoring, and feedback as previously shown for physiotherapy patients and home exercise in a hands-free augmented reality environment ( Kowatsch et al, 2021 ). Building a strong “virtual” working alliance between a chatbot interface and a patient might prove a promising tool to improve the acceptance of the connected RehabGym and avoid mental/social distress caused by isolation.…”