Process-Oriented Iterative Multiple Alignment for Medical Process Mining

Abstract

Adapted from biological sequence alignment, trace alignment is a process mining technique used to visualize and analyze workflow data. Any analysis done with this method, however, is affected by the alignment quality. The best existing trace alignment techniques use progressive guide-trees to heuristically approximate the optimal alignment in O(N2L2) time. These algorithms are heavily dependent on the selected guide-tree metric, often return sum-of-pairs-score-reducing errors that interfere with interpretation, and are computationally intensive for large datasets. To alleviate these issues, we propose process-oriented iterative multiple alignment (PIMA), which contains specialized optimizations to better handle workflow data. We demonstrate that PIMA is a flexible framework capable of achieving better sum-of-pairs score than existing trace alignment algorithms in only O(NL2) time. We applied PIMA to analyzing medical workflow data, showing how iterative alignment can better represent the data and facilitate the extraction of insights from data visualization.

Discovering Interpretable Medical Workflow Models

“…For our experiments, we implemented the recently published PIMA [2] as our alignment algorithm. The threshold t was set to 0.5.…”

“…Given n activity traces T = { T 1 , …, T n }, where each T i has a variable number of ordered treatment activities, T i = { a 1 , …, a m }. The trace alignment algorithm [2] returns an alignment matrix M with the traces T as rows and activities of the same type as columns (Figure 1). For a given cell, if a matching activity cannot be found, a gap symbol (e.g., “-”) is inserted.…”

Process mining applications in the healthcare domain: A comprehensive review

“…Combined with visualization techniques, trace alignment is a powerful mean to detect deviation, analyze and discovery specific case (Figure 10a). S. Chen et al (2017) proposed PIMA (process‐oriented iterative multiple alignment), an algorithm optimized to handle workflow data, and tested with endotracheal intubation, primary survey, and trauma resuscitation data.…”

Process Mining in Healthcare Systems: A Critical Review and its Future

“…Process mining [1] is the mining process to combine process models and event log data in different techniques. By this process mining models, the management of the organization can find out what people and the organizations really do.…”