Introduction: Early intervention for exacerbations is crucial for enhancing patients’ quality of life, reducing mortality and impeding the progression of COPD. TeleCare Nord has pilottested a predictive algorithm which should help identify exacerbations 3 days prior. However, deploying AI outputs in healthcare without explainability is a barrier for effective use. This master's thesis aims to investigate the applicability of an explainable user interface (XUI) within telemedicine to support the remote monitoring of citizens with COPD

Methodology: Hevner’s design science research is used as a framework for the design and evaluation of the prototype. The framework involves exploring the environment and the knowledge base. The environment was explored by conducting a semi-structured interview with two telemedicine practitioners. The knowledge base was explored by conducting a systematic literature search for XUI within a healthcare context. These methods laid the foundation for development and evaluation of a prototype, which consisted of a two-part evaluation with two evaluators to assess the usability of the prototype.

Results: Four requirements were identified: a global and local explanation, increased or decreased risk, as well as an interactive graph. The most significant result indicated that the end-user preferred the global explanation over the local explanation. Additionally, the application-impact of the interactive graph did not meet the initial expectations.