JMIR Publications

ABSTRACT

Background:

Type 2 diabetes mellitus (DM) is a chronic condition that requires ongoing self-management. While chatbots offer scalable monitoring and management, evidence on their integration within structured hospital tele-support workflows, where patient engagement, and digital readiness may differ from standalone digital interventions is limited.

Objective:

This study aimed to describe the design of a clinical protocol-guided chatbot, Sharing Information with Users on Diabetes Actions and Interventions (Siu Dai), and evaluate its feasibility, usability, and acceptability among patients and telecarers within a hospital tele-support program.

Methods:

We utilised an embedded mixed-methods design (QUAL[quan]) guided by the WHO Monitoring and Evaluating Digital Health Interventions and Theoretical Framework of Acceptability. Through a co-design process involving clinicians, researchers, telecarers, and developers, the chatbot was aligned with established clinical protocols. It featured seven pre-call sessions designed to collect patient data, generate summary reports for staff, and deliver targeted educational content. Patients (≥21 years with type 2 DM) and telecarer nurses (≥6 months’ experience) were recruited from an existing tele-support program. Data sources included interviews, online surveys (5-point Likert scales), and chatbot usage logs. Qualitative data were analyzed thematically; quantitative data were summarized descriptively and integrated narratively.

Results:

Nineteen participants enrolled (11 patients, 8 telecarers), and 14 (7 patients, 7 telecarers) completed both interviews and surveys. Patients (mean: 49.6) had median diabetes duration of 10 years (range: 1 – 30) and all were digitally literate. Telecarers had a median of 5 years’ telehealth experience. Quantitatively, patients showed high engagement, completing 83% of started sessions with a median completion time of 2:54 minutes. Patient satisfaction was high, with 81.8% (9/11) willing to recommend the tool; however, telecarer endorsement for universal rollout was more cautious (50.0%, 4/8). Qualitative findings revealed five themes: (1) perceptions of chatbot usability, (2) alignment and integration into telecarers’ processes; (3) factors influencing acceptability of the chatbot; (4) perceived efficacy of the chatbot on DM self-management and care delivery, and (5) suggested improvements and enhancement. Integrated findings revealed that the chatbot was usable and functioned as a pre-call support tool that optimized the personalization of tele-support sessions. However, its perceived efficacy on self-management behavior was limited due to the well-versed experience of this cohort with DM management. Key barriers to adoption included administrative burden for telecarers due to a lack of electronic medical record integration and content redundancy for patients. Suggested enhancements included multilingual support and adaptive content catering to different levels of disease-specific literacy.

Conclusions:

A clinical protocol-guided chatbot is feasible for hospital tele-support, complementing rather than replacing human care. It automates routine assessments and reinforces education, but future iterations must prioritize workflow integration and adaptive content to sustain engagement. Clinical Trial: NA