Key points are not available for this paper at this time.
This study focuses on the application of process mining in the healthcare sector. Despite its potential to enhance efficiency, reduce costs, and improve patient satisfaction, the selection of process-mining software poses significant challenges due to the diverse nature of healthcare processes and the lack of comprehensive evaluation methods. To bridge this gap, this study employed a hybrid Multi-Criteria Decision-Making (MCDM) approach, integrating the Neural Network-Augmented Analytical Hierarchy Process (NNA-AHP) and Grey Relational Analysis—a technique for Order Preference by Similarity to Ideal Solution (GRA-TOPSIS). The study evaluated process mining software on functionalities, ease of use, cost, technical support, scalability, and security with their respective sub-criteria. The principal results indicate that Disco is the top-performing alternative, followed by Celonis and ProM. Sensitivity analysis was conducted to understand the influence of variations in criteria weights on evaluating alternatives. In the NNA-AHP, Celonis consistently scored the highest. The GRA-TOPSIS method provided performance scores, indicating that higher scores yield better performance. The new hybrid method consolidates evaluations from all methods and offers the most comprehensive and dependable alternative assessment. Disco and its alternatives, Celonis and ProM, are recommended for optimizing healthcare processes. Further research is needed to investigate the integration of NNA-AHP and GRA-TOPSIS in healthcare management, especially in areas beyond business process analysis. This study provides valuable insights for professionals and researchers in the field and contributes to understanding the effectiveness of process mining.
Matonya et al. (Wed,) studied this question.