A multi-objective medical process mining model using event log and causal matrix

Abstract

Medical analytics in genetic process mining have developed models with multiple and often conflicting criteria. Some studies have reduced the complexities inherent in multiple and conflicting criteria by eliminating some criteria and solving the problem with a single or linear objective function. This study proposes a multi-objective model for obtaining Pareto without removing any conflicting criteria. Two multi-objective Pareto-based models of Non-dominated Ranked Genetic Algorithm (NRGA) and Non-dominated Sorting Genetic Algorithm (NSGAII) are developed. A comprehensive examination and statistical analysis are performed to analyze the performance of the two algorithms with five metrics of Mean Ideal Distance (MID), Cover Surface (CS), diversity, spacing, and time. In addition, sensitivity analysis examines the problem size and the coefficients of the different criteria on the objective functions. Finally, for the performance evaluation, a Data Envelopment Analysis (DEA) is developed based on some instances and benchmarks to assess the efficiency of the algorithms. We show that NSGAII outperforms the NRGA according to the performance metrics and statistical hypothesis testing.