University of Twente Student Theses
Tailoring AI Chatbots for Healthcare : The Impact of User Preferences on Design
Dokter, A.P. (2024) Tailoring AI Chatbots for Healthcare : The Impact of User Preferences on Design.
Full text not available from this repository.
| Full Text Status: | Access to this publication is restricted |
| Abstract: | Healthcare professionals working part-time or in extramural care face unique challenges, including irregular schedules, difficulty tracking hours, managing overtime, and planning vacations. This thesis addresses these issues by designing and evaluating two tools: an hour overview and a chatbot for vacation requests. The hour overview provides a clear interface for viewing worked hours, vacation balances, and schedule requests while integrating explainable AI (XAI) and adaptive user interfaces (AUI) for personalisation. The tools were refined through three iterative design rounds based on feedback from potential users. A final questionnaire gathered additional insights. Key findings reveal healthcare professionals value intuitive, transparent tools that foster trust. However, preferences for standardisation within facilities contrast with the need for adaptable designs across diverse organizations. Privacy concerns and trust in chatbot recommendations remain challenges. The research suggests starting with simple chatbot functions, such as addressing general questions about hours, to build user confidence. Balancing standardization with customization, addressing ethical concerns, and fostering trust in AI are crucial for the successful implementation of non-clinical tools in healthcare. These tools aim to simplify administrative tasks, supporting healthcare professionals in managing their complex schedules. |
| Item Type: | Essay (Master) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Programme: | Interaction Technology MSc (60030) |
| Link to this item: | https://purl.utwente.nl/essays/104711 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page