University of Twente Student Theses
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.
Leveraging Process Mining for Health Economic Evaluation : A Case Study in Skin Cancer Care
Mohammadkhani, Sara (2025) Leveraging Process Mining for Health Economic Evaluation : A Case Study in Skin Cancer Care.
Full text not available from this repository.
| Full Text Status: | Access to this publication is restricted |
| Embargo date: | 11 July 2027 |
| Abstract: | Introduction: The growing prevalence of melanoma in the Netherlands has underlined the critical need for efficient, patient-centered care delivery. In this context, health economic evaluation plays a vital role in guiding healthcare decision-making by identifying cost-effective treatment strategies and ensuring that limited healthcare resources are used efficiently. Traditional health economic models, such as Markov models, often simplify clinical pathways by using predefined abstract states, fixed cycle lengths, and memory-less assumptions limiting their ability to reflect real-world care dynamics. This study aims to leverage process mining techniques to understand the variability and complexity of patient pathways in skin cancer care and integrate these insights into health economic modeling. Method: A Process-Guided Markov Model (PGMM) was developed using real-world healthcare event logs from Dutch patients with stage III C melanoma, including those who experienced disease progression. Clinical activities were treated as health states, and transition probabilities and state durations were empirically derived from the logs. The model was structured in two phases—before and after disease progression with distinct transition matrices and cost-utility logic. Cost and Quality-Adjusted-Life Year (QALY) calculations were based on time-weighted utilities and differentiated between one-time and recurring costs. Result: The PGMM was able to reflect the heterogeneity and sequence-specific behavior of real care pathways. Validation against real-world data showed that the simulation could approximate the distribution of observed costs and QALYs, although differences existed due to individualized patterns and data sparsity. |
| Item Type: | Essay (Master) |
| Faculty: | TNW: Science and Technology |
| Subject: | 44 medicine, 83 economics |
| Programme: | Health Sciences MSc (66851) |
| Link to this item: | https://purl.utwente.nl/essays/107226 |
| 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