User Experiences of a Chatbot for Supporting the Self-Management of Peripherally Inserted Central Catheter for Chemotherapy: Mixed-Methods Study
ABSTRACT
Background:
A peripherally inserted central catheter (PICC) for vesicant or long-term chemotherapy (CTx) is recommended for safe and sustainable administration. However, regular and careful management is essential to ensure the benefits. Although medical staff provide education and telephone consultation, proactive support at any time or location remains limited. Therefore, we developed a chatbot for PICC management to overcome this gap.
Objective:
To determine the feasibility of the rule-based chatbot for PICC management based on usage experience.
Methods:
A mixed-methods study was conducted from September to December 2022. Patients with cancer scheduled for PICC insertion and their caregivers were recruited. The chatbot was designed to provide structured answers according to prespecified dialog trees and to automatically understand users’ intent based on natural language processing. Participants were asked to voluntarily use the chatbot for about one month. Subsequently, we investigated the most frequently asked questions, usability, and perceived benefits and barriers associated with its use.
Results:
Among the 56 participants, 66.1% were patients and 69.6% were female, with a mean age of 55.4 years. A total of 28 participants used the chatbot at least once. Non-users stated that they had no PICC-related issues at the time (n = 14) or had difficulty using the chatbot (n = 5). The most frequently asked questions were related to catheter care, followed by daily life management, symptoms, and heparin use. Most users (95.7%) reported that the chatbot helped reduce their anxiety. Despite its potential, the chatbot faced key limitations related to conversational issues, user experience challenges, and a lack of personalization.
Conclusions:
The chatbot was found to be a feasible tool for supporting the self-management of PICC lines. The future incorporation of large language models (LLMs) may enhance the chatbot’s responsiveness, contextual understanding, and ability to deliver personalized support. Clinical Trial: The study was reviewed and approved by the Institutional Review Board of the Samsung Medical Center (IRB No. SMC 2022-07-059).
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.