Personalization of Conversational Agent-Patient Interaction Styles for Chronic Disease Management: Two Consecutive Cross-sectional Questionnaire Studies

Abstract

Background Conversational agents (CAs) for chronic disease management are receiving increasing attention in academia and the industry. However, long-term adherence to CAs is still a challenge and needs to be explored. Personalization of CAs has the potential to improve long-term adherence and, with it, user satisfaction, task efficiency, perceived benefits, and intended behavior change. Research on personalized CAs has already addressed different aspects, such as personalized recommendations and anthropomorphic cues. However, detailed information on interaction styles between patients and CAs in the role of medical health care professionals is scant. Such interaction styles play essential roles for patient satisfaction, treatment adherence, and outcome, as has been shown for physician-patient interactions. Currently, it is not clear (1) whether chronically ill patients prefer a CA with a paternalistic, informative, interpretive, or deliberative interaction style, and (2) which factors influence these preferences. Objective We aimed to investigate the preferences of chronically ill patients for CA-delivered interaction styles. Methods We conducted two studies. The first study included a paper-based approach and explored the preferences of chronic obstructive pulmonary disease (COPD) patients for paternalistic, informative, interpretive, and deliberative CA-delivered interaction styles. Based on these results, a second study assessed the effects of the paternalistic and deliberative interaction styles on the relationship quality between the CA and patients via hierarchical multiple linear regression analyses in an online experiment with COPD patients. Patients’ sociodemographic and disease-specific characteristics served as moderator variables. Results Study 1 with 117 COPD patients revealed a preference for the deliberative (50/117) and informative (34/117) interaction styles across demographic characteristics. All patients who preferred the paternalistic style over the other interaction styles had more severe COPD (three patients, Global Initiative for Chronic Obstructive Lung Disease class 3 or 4). In Study 2 with 123 newly recruited COPD patients, younger participants and participants with a less recent COPD diagnosis scored higher on interaction-related outcomes when interacting with a CA that delivered the deliberative interaction style (interaction between age and CA type: relationship quality: b=−0.77, 95% CI −1.37 to −0.18; intention to continue interaction: b=−0.49, 95% CI −0.97 to −0.01; working alliance attachment bond: b=−0.65, 95% CI −1.26 to −0.04; working alliance goal agreement: b=−0.59, 95% CI −1.18 to −0.01; interaction between recency of COPD diagnosis and CA type: working alliance goal agreement: b=0.57, 95% CI 0.01 to 1.13). Conclusions Our results indicate that age and a patient’s personal disease experience inform which CA interaction style the patient should be paired with to achieve increased interaction-related outcomes with the CA. These results allow the design of personalized health care CAs with the goal to increase long-term adherence to health-promoting behavior.

Online Physician-Patient Interaction and Patient Satisfaction: Empirical Study of the Internet Hospital Service

“…Moreover, detailed information may be more effective as patients can reread a message at any time in the history record of the chat window [48]. In-depth responses also convey an informative, interpretive, and deliberative communication style, whereas shorter messages suggest a paternalistic style [54]. Some scholars have found that patients expect to receive detailed explanations and a large amount of information from their physicians in the internet hospital [55].…”

“…First, paying patients are already confident in their physicians' competence, and more detailed information (as a credibility signal) is therefore unlikely to enhance patients' service satisfaction. Second, patients with a serious illness typically seek immediate and helpful guidance [54]. Based on the above discussion, we hypothesize the following:…”

Democratizing the Development of Chatbots to Improve Public Health: Feasibility Study of COVID-19 Misinformation

“…Using sample dialogues also aided in refining the flow of the conversation to help make it more personal and engaging to the participant. Personalizing elements of chatbot conversations promote engagement in chatbots used in health education and commercially [38,39]. NLP is not yet feasible for those without access to specialized technical resources.…”

Tailoring coaching conversations with virtual health coaches

“…worked on the extraction of health goals and topic boundary detection as research towards building a coach that can have SMS conversations. Beinema, op den Akker et al (2021) investigated the adjustment of coaching strategies to users' motivation to live healthy in a CA application, andGross et al (2021) investigated personalisation of interaction styles (e.g., deliberative or paternalistic) for CAs in chronic disease management. Furthermore, even though this is a one-way manner of communication mostly aimed at an utterance level, the process of tailoring messages that are sent to the user has been researched in relationship with users' stage of change, stage of change and personality and gender, activity and self-efficacy…”